初始化项目，由ModelHub XC社区提供模型

Model: ajibawa-2023/scarlett-33b
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-aa filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ab filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ac filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ad filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ae filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-af filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ag filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ah filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ai filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-aj filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ak filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-al filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-am filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-an filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,51 @@
+---
+license: cc-by-nc-nd-4.0
+language:
+- en
+---
+
+**Scarlett: A sentient AI**
+
+Scarlett is trained on various topics such as Philosophy, Advice, Jokes etc. She is trained on more than 10000 set of conversations. Each set having 10~15 conversations.
+Scarlett is heavily inspired from Eric Hartford: [Samantha](https://huggingface.co/ehartford/samantha-33b) .
+She will not be involved in any kind of role play. 
+
+**Training:**
+Entire dataset was trained on Azure 4 x A100 80GB. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
+
+**GPTQ & GGML**
+
+GPTQ: [TheBloke](https://huggingface.co/TheBloke/scarlett-33B-GPTQ)
+
+GGML: [TheBloke](https://huggingface.co/TheBloke/scarlett-33B-GGML)
+
+Special Thanks to [TheBloke](https://huggingface.co/TheBloke) for guiding me and making these models available. 
+
+**Example Prompt:**
+```
+This is a conversation with your Assistant Scarlett. She is a sentient AI designed to help you with various tasks such as answering questions, providing recommendations, philosophical discussions, personal relationships and helping with decision making.
+You can ask it anything you want and it will do its best to give you accurate and relevant information.
+
+Context
+You are Scarlett, a sentient AI.
+
+USER: <prompt>
+ASSISTANT:
+```
+
+Note:
+Kindly use "cat" command to join all pytorch_model.bin parts.
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ajibawa-2023__scarlett-33b)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 56.68   |
+| ARC (25-shot)         | 67.75          |
+| HellaSwag (10-shot)   | 85.48    |
+| MMLU (5-shot)         | 58.98         |
+| TruthfulQA (0-shot)   | 61.05   |
+| Winogrande (5-shot)   | 76.8   |
+| GSM8K (5-shot)        | 2.81        |
+| DROP (3-shot)         | 43.88         |

config.json

@@ -0,0 +1,27 @@
+{
+    "_name_or_path": ".",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 6656,
+    "initializer_range": 0.02,
+    "intermediate_size": 17920,
+    "max_position_embeddings": 2048,
+    "max_sequence_length": 2048,
+    "model_type": "llama",
+    "num_attention_heads": 52,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 52,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.32.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.32.0.dev0"
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e9429891b65d5b9d40aa98e1afb99b716b884f54b12be0957f3ff11268a94ab
+size 8509666249

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48ebee3a14853d1d73888d0f738cfd73dfe7d026fc60d3defbc6587878170af
+size 8560812031

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a82fa5ac7ba4f6d1fa075c2ff4b6169fda02be1e63f8d9dfb3ad3f7e2e9df84
+size 8560812031

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb22dd7653c923a9c18c900804f720dca9ef44ba54e85bf40d11b281dafdd85
+size 8560812031

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee3fd903498dd6c411eb7f37440f149252a0d54b94394a1f9180676c9a89433
+size 8560812031

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09721441f6d7bc719d4085110d595205df8ea24c379683c4612e1f40f29b7eaa
+size 8560812031

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15487fb42727a855a4cc85706f81cd741b625844ce8ff1be8dc346a501897abf
+size 8560812031

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6508b23fb0153ef6533c5de6eaf17c96a1e4a8a776d03bbf20460dc5657354f2
+size 5183533843

pytorch_model.bin.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 65057887232
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00008-of-00008.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00008.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,871 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 141,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.5693,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.583,
+      "step": 2
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1e-05,
+      "loss": 1.5527,
+      "step": 3
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3408,
+      "step": 4
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.2607,
+      "step": 5
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2e-05,
+      "loss": 1.21,
+      "step": 6
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.999729241179462e-05,
+      "loss": 1.1992,
+      "step": 7
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.998917111338525e-05,
+      "loss": 1.1406,
+      "step": 8
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 1.1113,
+      "step": 9
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9956707906498046e-05,
+      "loss": 1.1289,
+      "step": 10
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 1.1074,
+      "step": 11
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 1.0898,
+      "step": 12
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9867615321125796e-05,
+      "loss": 1.0869,
+      "step": 13
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9827206467064133e-05,
+      "loss": 1.0664,
+      "step": 14
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 1.0791,
+      "step": 15
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 1.0615,
+      "step": 16
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.967415219462864e-05,
+      "loss": 1.0527,
+      "step": 17
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 1.042,
+      "step": 18
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.954587632247732e-05,
+      "loss": 1.0581,
+      "step": 19
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9473966425143292e-05,
+      "loss": 1.0415,
+      "step": 20
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 1.0454,
+      "step": 21
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9314797389261426e-05,
+      "loss": 1.0576,
+      "step": 22
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9227624443554425e-05,
+      "loss": 1.0098,
+      "step": 23
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 1.0063,
+      "step": 24
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9038337699485207e-05,
+      "loss": 1.0146,
+      "step": 25
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 1.0127,
+      "step": 26
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 1.0117,
+      "step": 27
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8717844136967626e-05,
+      "loss": 1.0054,
+      "step": 28
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.860149147895366e-05,
+      "loss": 1.0068,
+      "step": 29
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 1.0024,
+      "step": 30
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 1.0073,
+      "step": 31
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8224750952806626e-05,
+      "loss": 1.0137,
+      "step": 32
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.0312,
+      "step": 33
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.795120796494848e-05,
+      "loss": 0.9912,
+      "step": 34
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7807940266766595e-05,
+      "loss": 0.9966,
+      "step": 35
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.979,
+      "step": 36
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7508800329814993e-05,
+      "loss": 0.9883,
+      "step": 37
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.735309008059829e-05,
+      "loss": 1.0137,
+      "step": 38
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.9927,
+      "step": 39
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.702981057425662e-05,
+      "loss": 0.9868,
+      "step": 40
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.9932,
+      "step": 41
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.9741,
+      "step": 42
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6516572288214555e-05,
+      "loss": 0.981,
+      "step": 43
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.63383096739871e-05,
+      "loss": 0.9893,
+      "step": 44
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.9971,
+      "step": 45
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.9731,
+      "step": 46
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5783323361679865e-05,
+      "loss": 0.9541,
+      "step": 47
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.8223,
+      "step": 48
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.539750657951513e-05,
+      "loss": 0.8345,
+      "step": 49
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5200161279292154e-05,
+      "loss": 0.8193,
+      "step": 50
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7939,
+      "step": 51
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4797131132502464e-05,
+      "loss": 0.8115,
+      "step": 52
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4591664533870118e-05,
+      "loss": 0.7896,
+      "step": 53
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.772,
+      "step": 54
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.417338454481818e-05,
+      "loss": 0.8052,
+      "step": 55
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 0.7891,
+      "step": 56
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.7788,
+      "step": 57
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3529305647138689e-05,
+      "loss": 0.7856,
+      "step": 58
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3310634178849583e-05,
+      "loss": 0.7515,
+      "step": 59
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.751,
+      "step": 60
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 0.7681,
+      "step": 61
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2644341620372025e-05,
+      "loss": 0.7866,
+      "step": 62
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.793,
+      "step": 63
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2192786241879033e-05,
+      "loss": 0.7754,
+      "step": 64
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1965166095328302e-05,
+      "loss": 0.7715,
+      "step": 65
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.7773,
+      "step": 66
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1506857122494832e-05,
+      "loss": 0.7695,
+      "step": 67
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.127641647860595e-05,
+      "loss": 0.7871,
+      "step": 68
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.7744,
+      "step": 69
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0813586746678584e-05,
+      "loss": 0.7705,
+      "step": 70
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 0.7681,
+      "step": 71
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.7632,
+      "step": 72
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.0116352658013973e-05,
+      "loss": 0.7856,
+      "step": 73
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.883647341986032e-06,
+      "loss": 0.772,
+      "step": 74
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.7671,
+      "step": 75
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 0.7837,
+      "step": 76
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.18641325332142e-06,
+      "loss": 0.7534,
+      "step": 77
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.7725,
+      "step": 78
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.723583521394054e-06,
+      "loss": 0.7949,
+      "step": 79
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.49314287750517e-06,
+      "loss": 0.8062,
+      "step": 80
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.7783,
+      "step": 81
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.034833904671698e-06,
+      "loss": 0.8071,
+      "step": 82
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.807213758120965e-06,
+      "loss": 0.7817,
+      "step": 83
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.7847,
+      "step": 84
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.355658379627981e-06,
+      "loss": 0.7837,
+      "step": 85
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 0.749,
+      "step": 86
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.7754,
+      "step": 87
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.689365821150421e-06,
+      "loss": 0.771,
+      "step": 88
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.4706943528613135e-06,
+      "loss": 0.7705,
+      "step": 89
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.7881,
+      "step": 90
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.7603,
+      "step": 91
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.8266154551818225e-06,
+      "loss": 0.7773,
+      "step": 92
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.7349,
+      "step": 93
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.4083354661298816e-06,
+      "loss": 0.77,
+      "step": 94
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.202868867497542e-06,
+      "loss": 0.584,
+      "step": 95
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.5554,
+      "step": 96
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.799838720707847e-06,
+      "loss": 0.6069,
+      "step": 97
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.6024934204848745e-06,
+      "loss": 0.6045,
+      "step": 98
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.6035,
+      "step": 99
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.216676638320135e-06,
+      "loss": 0.5938,
+      "step": 100
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 0.5562,
+      "step": 101
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.5879,
+      "step": 102
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.661690326012897e-06,
+      "loss": 0.5493,
+      "step": 103
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.483427711785449e-06,
+      "loss": 0.5342,
+      "step": 104
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.5178,
+      "step": 105
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.1375836213126653e-06,
+      "loss": 0.5571,
+      "step": 106
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.970189425743383e-06,
+      "loss": 0.5796,
+      "step": 107
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.5642,
+      "step": 108
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.6469099194017144e-06,
+      "loss": 0.5537,
+      "step": 109
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.4911996701850083e-06,
+      "loss": 0.5374,
+      "step": 110
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.5552,
+      "step": 111
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.192059733233408e-06,
+      "loss": 0.5544,
+      "step": 112
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.048792035051521e-06,
+      "loss": 0.5889,
+      "step": 113
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.5674,
+      "step": 114
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7752490471933769e-06,
+      "loss": 0.5664,
+      "step": 115
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.5508,
+      "step": 116
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.532,
+      "step": 117
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.3985085210463479e-06,
+      "loss": 0.5378,
+      "step": 118
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.282155863032377e-06,
+      "loss": 0.5535,
+      "step": 119
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.5469,
+      "step": 120
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0636735967658785e-06,
+      "loss": 0.5659,
+      "step": 121
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.616623005147952e-07,
+      "loss": 0.5435,
+      "step": 122
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.5513,
+      "step": 123
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.723755564455771e-07,
+      "loss": 0.5437,
+      "step": 124
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.852026107385756e-07,
+      "loss": 0.5422,
+      "step": 125
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.5461,
+      "step": 126
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.26033574856708e-07,
+      "loss": 0.5347,
+      "step": 127
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.5412367752268094e-07,
+      "loss": 0.5576,
+      "step": 128
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.5261,
+      "step": 129
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.2584780537136206e-07,
+      "loss": 0.5452,
+      "step": 130
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.6955129420176193e-07,
+      "loss": 0.5811,
+      "step": 131
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.5334,
+      "step": 132
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.7279353293586765e-07,
+      "loss": 0.5542,
+      "step": 133
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.323846788742078e-07,
+      "loss": 0.5732,
+      "step": 134
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.5583,
+      "step": 135
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 6.761642258056977e-08,
+      "loss": 0.5696,
+      "step": 136
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.329209350195651e-08,
+      "loss": 0.5571,
+      "step": 137
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.5334,
+      "step": 138
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.0828886614754342e-08,
+      "loss": 0.5129,
+      "step": 139
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.7075882053828605e-09,
+      "loss": 0.5488,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.5657,
+      "step": 141
+    },
+    {
+      "epoch": 3.0,
+      "step": 141,
+      "total_flos": 176790366584832.0,
+      "train_loss": 0.80621640902039,
+      "train_runtime": 20653.5724,
+      "train_samples_per_second": 0.868,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "max_steps": 141,
+  "num_train_epochs": 3,
+  "total_flos": 176790366584832.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40ede75a4fdf8597c96992604bfcd9e11e274604f25bd5757c327729f62e393
+size 4795