Model save

README.md

@@ -1,16 +1,13 @@
 ---
-license: apache-2.0
-base_model: mistralai/Mistral-7B-Instruct-v0.2
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 datasets:
-- nlee-208/uf-g0-sft
+- generator
 model-index:
 - name: uf-mistral-it-sft-g0
   results: []
@@ -19,10 +16,10 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nlee28/lucky/runs/x8z85cal)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nlee28/lucky/runs/pfdkvjut)
 # uf-mistral-it-sft-g0
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the nlee-208/uf-g0-sft dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
 
 ## Model description
 

all_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 0.9961802902979373,
-    "total_flos": 9.115042887803863e+17,
-    "train_loss": 1.117896075629018,
-    "train_runtime": 6585.7608,
+    "epoch": 0.9990884229717412,
+    "total_flos": 8.085894968356372e+17,
+    "train_loss": 1.1745838492456144,
+    "train_runtime": 5870.8803,
     "train_samples": 60915,
-    "train_samples_per_second": 3.18,
-    "train_steps_per_second": 0.025
+    "train_samples_per_second": 2.987,
+    "train_steps_per_second": 0.023
 }

generation_config.json

@@ -1,6 +1,12 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.42.4"
 }

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee45c24f139af5167a1d9d9be1e8ef2836e090af972658569a0d135f0ba8833
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705bf34393b40093646becb5ebfe77d49a799b8ece14aad50ce026c9cc9087e9
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b58422dce47b886c73b7f2bf2cd2691107b4c97d8ea6c05b7f105583da5135
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0d8cc3ced8b1c11b5d2718534e2bb249e560c3d9cf5807209114a3ab7133d4
+size 1168138808

model.safetensors.index.json

@@ -1,298 +1,298 @@
 {
   "metadata": {
-    "total_size": 14483464192
+    "total_size": 16060522496
   },
   "weight_map": {
-    "lm_head.weight": "model-00003-of-00003.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors"
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 0.9961802902979373,
-    "total_flos": 9.115042887803863e+17,
-    "train_loss": 1.117896075629018,
-    "train_runtime": 6585.7608,
+    "epoch": 0.9990884229717412,
+    "total_flos": 8.085894968356372e+17,
+    "train_loss": 1.1745838492456144,
+    "train_runtime": 5870.8803,
     "train_samples": 60915,
-    "train_samples_per_second": 3.18,
-    "train_steps_per_second": 0.025
+    "train_samples_per_second": 2.987,
+    "train_steps_per_second": 0.023
 }

trainer_state.json

@@ -1,137 +1,116 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9961802902979373,
+  "epoch": 0.9990884229717412,
   "eval_steps": 500,
-  "global_step": 163,
+  "global_step": 137,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.061115355233002294,
-      "grad_norm": 9.6875,
-      "learning_rate": 2.9411764705882354e-05,
-      "loss": 1.2797,
+      "epoch": 0.07292616226071102,
+      "grad_norm": 2.03125,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.4613,
       "step": 10
     },
     {
-      "epoch": 0.12223071046600459,
-      "grad_norm": 8.8125,
-      "learning_rate": 4.994792902163481e-05,
-      "loss": 1.1373,
+      "epoch": 0.14585232452142205,
+      "grad_norm": 1.21875,
+      "learning_rate": 4.970701059450872e-05,
+      "loss": 1.2568,
       "step": 20
     },
     {
-      "epoch": 0.18334606569900688,
-      "grad_norm": 5.375,
-      "learning_rate": 4.902824459680752e-05,
-      "loss": 1.1783,
+      "epoch": 0.2187784867821331,
+      "grad_norm": 0.9140625,
+      "learning_rate": 4.79413289650907e-05,
+      "loss": 1.2099,
       "step": 30
     },
     {
-      "epoch": 0.24446142093200918,
-      "grad_norm": 3.1875,
-      "learning_rate": 4.7000305099338396e-05,
-      "loss": 1.1725,
+      "epoch": 0.2917046490428441,
+      "grad_norm": 0.91015625,
+      "learning_rate": 4.468715765333664e-05,
+      "loss": 1.1924,
       "step": 40
     },
     {
-      "epoch": 0.30557677616501144,
-      "grad_norm": 2.5625,
-      "learning_rate": 4.395764521196406e-05,
-      "loss": 1.1683,
+      "epoch": 0.3646308113035551,
+      "grad_norm": 0.81640625,
+      "learning_rate": 4.015563527416595e-05,
+      "loss": 1.1706,
       "step": 50
     },
     {
-      "epoch": 0.36669213139801377,
-      "grad_norm": 2.6875,
-      "learning_rate": 4.004060158062306e-05,
-      "loss": 1.1519,
+      "epoch": 0.4375569735642662,
+      "grad_norm": 0.8046875,
+      "learning_rate": 3.46407781122034e-05,
+      "loss": 1.1576,
       "step": 60
     },
     {
-      "epoch": 0.42780748663101603,
-      "grad_norm": 2.53125,
-      "learning_rate": 3.542984006530792e-05,
-      "loss": 1.1442,
+      "epoch": 0.5104831358249772,
+      "grad_norm": 0.80859375,
+      "learning_rate": 2.8500403624215734e-05,
+      "loss": 1.14,
       "step": 70
     },
     {
-      "epoch": 0.48892284186401835,
-      "grad_norm": 2.171875,
-      "learning_rate": 3.0338022885994904e-05,
-      "loss": 1.1354,
+      "epoch": 0.5834092980856882,
+      "grad_norm": 0.79296875,
+      "learning_rate": 2.2132914365039993e-05,
+      "loss": 1.1243,
       "step": 80
     },
     {
-      "epoch": 0.5500381970970206,
-      "grad_norm": 1.90625,
-      "learning_rate": 2.5e-05,
-      "loss": 1.1259,
+      "epoch": 0.6563354603463992,
+      "grad_norm": 0.73828125,
+      "learning_rate": 1.5951448652822047e-05,
+      "loss": 1.1189,
       "step": 90
     },
     {
-      "epoch": 0.6111535523300229,
-      "grad_norm": 1.8828125,
-      "learning_rate": 1.9661977114005098e-05,
-      "loss": 1.0983,
+      "epoch": 0.7292616226071102,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.035707514179513e-05,
+      "loss": 1.122,
       "step": 100
     },
     {
-      "epoch": 0.6722689075630253,
-      "grad_norm": 1.6953125,
-      "learning_rate": 1.4570159934692085e-05,
-      "loss": 1.0884,
+      "epoch": 0.8021877848678214,
+      "grad_norm": 0.68359375,
+      "learning_rate": 5.712770504451426e-06,
+      "loss": 1.1159,
       "step": 110
     },
     {
-      "epoch": 0.7333842627960275,
-      "grad_norm": 1.7265625,
-      "learning_rate": 9.959398419376932e-06,
-      "loss": 1.0599,
+      "epoch": 0.8751139471285324,
+      "grad_norm": 0.69921875,
+      "learning_rate": 2.3198686149022013e-06,
+      "loss": 1.1201,
       "step": 120
     },
     {
-      "epoch": 0.7944996180290298,
-      "grad_norm": 1.625,
-      "learning_rate": 6.042354788035942e-06,
-      "loss": 1.0558,
+      "epoch": 0.9480401093892434,
+      "grad_norm": 0.76953125,
+      "learning_rate": 3.9850926816357157e-07,
+      "loss": 1.1217,
       "step": 130
     },
     {
-      "epoch": 0.8556149732620321,
-      "grad_norm": 1.5859375,
-      "learning_rate": 2.9996949006616094e-06,
-      "loss": 1.0508,
-      "step": 140
-    },
-    {
-      "epoch": 0.9167303284950343,
-      "grad_norm": 1.6640625,
-      "learning_rate": 9.71755403192484e-07,
-      "loss": 1.0264,
-      "step": 150
-    },
-    {
-      "epoch": 0.9778456837280367,
-      "grad_norm": 1.6015625,
-      "learning_rate": 5.20709783651957e-08,
-      "loss": 1.0426,
-      "step": 160
-    },
-    {
-      "epoch": 0.9961802902979373,
-      "step": 163,
-      "total_flos": 9.115042887803863e+17,
-      "train_loss": 1.117896075629018,
-      "train_runtime": 6585.7608,
-      "train_samples_per_second": 3.18,
-      "train_steps_per_second": 0.025
+      "epoch": 0.9990884229717412,
+      "step": 137,
+      "total_flos": 8.085894968356372e+17,
+      "train_loss": 1.1745838492456144,
+      "train_runtime": 5870.8803,
+      "train_samples_per_second": 2.987,
+      "train_steps_per_second": 0.023
     }
   ],
   "logging_steps": 10,
-  "max_steps": 163,
+  "max_steps": 137,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
@@ -147,7 +126,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.115042887803863e+17,
+  "total_flos": 8.085894968356372e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null