diff --git a/README.md b/README.md
index 5c0d499d78b811d53f0056c53cd1d031d55cdcad..1e3637f645b79c1dff559d466047b102e3892f5d 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,21 @@
 ---
-license: other
+library_name: peft
 ---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/adapter_config.json b/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3958451b2551a7766d76c84304260071ab14ec5
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/adapter_model.bin b/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ffba115bdd8c65f5a9ada357c3e61e3560a83277
--- /dev/null
+++ b/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11213a0c00bc5430a832af35fa25de9d9592072a55593290454c5487e99e5a21
+size 500897101
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cbce74e5c64b97114098962fa58454a57d7fb532
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}
diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1e3637f645b79c1dff559d466047b102e3892f5d
--- /dev/null
+++ b/checkpoint-100/README.md
@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-100/adapter_config.json b/checkpoint-100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3958451b2551a7766d76c84304260071ab14ec5
--- /dev/null
+++ b/checkpoint-100/adapter_config.json
@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-100/adapter_model.bin b/checkpoint-100/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ffba115bdd8c65f5a9ada357c3e61e3560a83277
--- /dev/null
+++ b/checkpoint-100/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11213a0c00bc5430a832af35fa25de9d9592072a55593290454c5487e99e5a21
+size 500897101
diff --git a/checkpoint-100/adapter_model/README.md b/checkpoint-100/adapter_model/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1e3637f645b79c1dff559d466047b102e3892f5d
--- /dev/null
+++ b/checkpoint-100/adapter_model/README.md
@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-100/adapter_model/adapter_config.json b/checkpoint-100/adapter_model/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3958451b2551a7766d76c84304260071ab14ec5
--- /dev/null
+++ b/checkpoint-100/adapter_model/adapter_config.json
@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-100/adapter_model/adapter_model.bin b/checkpoint-100/adapter_model/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ffba115bdd8c65f5a9ada357c3e61e3560a83277
--- /dev/null
+++ b/checkpoint-100/adapter_model/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11213a0c00bc5430a832af35fa25de9d9592072a55593290454c5487e99e5a21
+size 500897101
diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..71af508a82a3179baf35022408649a954bb1f163
--- /dev/null
+++ b/checkpoint-100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c02d23e0bd4a6cef73a32ebf8402a8b1e1a8f18cbebb1526b512a32ee37be5d
+size 1001736445
diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7efe7ad2666741d8272f18f1741493bea1b3e547
--- /dev/null
+++ b/checkpoint-100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c465c2771dab9ba6f712e86e9b71c6011a3dc6f2893016c97be18f355357c6b5
+size 14575
diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ebc626f0568a6d7901706cd93e46f76a293ec91e
--- /dev/null
+++ b/checkpoint-100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef30a43d20754fbeee89803ef955a46ca7e92fb8c40af3bdae2eaff291dcf94
+size 627
diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..39b961d9cb09e596aeda80a308e764968ffda653
--- /dev/null
+++ b/checkpoint-100/trainer_state.json
@@ -0,0 +1,619 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.8192771084337345,
+  "eval_steps": 150,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.2314,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.4026,
+      "step": 2
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.8531,
+      "step": 3
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.3763,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00015,
+      "loss": 0.961,
+      "step": 5
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.2005,
+      "step": 6
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.1054,
+      "step": 7
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.0114,
+      "step": 8
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00027,
+      "loss": 1.1386,
+      "step": 9
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9856,
+      "step": 10
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00029990862405286433,
+      "loss": 0.7562,
+      "step": 11
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002996346075389736,
+      "loss": 1.0498,
+      "step": 12
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00029917828430524096,
+      "loss": 1.2559,
+      "step": 13
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002985402103112355,
+      "loss": 1.0074,
+      "step": 14
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002977211629518312,
+      "loss": 1.0239,
+      "step": 15
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002967221401100708,
+      "loss": 1.3441,
+      "step": 16
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002955443589413994,
+      "loss": 1.1692,
+      "step": 17
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002941892543907478,
+      "loss": 1.3764,
+      "step": 18
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 0.9064,
+      "step": 19
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002909538931178862,
+      "loss": 1.4608,
+      "step": 20
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002890775781850181,
+      "loss": 1.0947,
+      "step": 21
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0002870318186463901,
+      "loss": 1.113,
+      "step": 22
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.000284819106944875,
+      "loss": 0.9546,
+      "step": 23
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.000282442138928839,
+      "loss": 1.1469,
+      "step": 24
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002799038105676658,
+      "loss": 1.3102,
+      "step": 25
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027720721442346387,
+      "loss": 1.4763,
+      "step": 26
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002743556358832562,
+      "loss": 1.0281,
+      "step": 27
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002713525491562421,
+      "loss": 1.0988,
+      "step": 28
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00026820161304100823,
+      "loss": 1.1848,
+      "step": 29
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00026490666646784665,
+      "loss": 0.9901,
+      "step": 30
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00026147172382160914,
+      "loss": 0.8676,
+      "step": 31
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00025790097005079764,
+      "loss": 1.0521,
+      "step": 32
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0002541987555688496,
+      "loss": 1.0436,
+      "step": 33
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.0002503695909538287,
+      "loss": 0.9511,
+      "step": 34
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002464181414529809,
+      "loss": 1.2208,
+      "step": 35
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002423492212988487,
+      "loss": 1.1128,
+      "step": 36
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00023816778784387094,
+      "loss": 1.114,
+      "step": 37
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023387893552061199,
+      "loss": 0.9318,
+      "step": 38
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.0002294878896349807,
+      "loss": 1.6424,
+      "step": 39
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.000225,
+      "loss": 0.7759,
+      "step": 40
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00022042073441788358,
+      "loss": 0.8061,
+      "step": 41
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0002157556720183616,
+      "loss": 1.2972,
+      "step": 42
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00021101049646137003,
+      "loss": 0.9694,
+      "step": 43
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.0002061909890123868,
+      "loss": 0.7951,
+      "step": 44
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.00020130302149885031,
+      "loss": 0.8049,
+      "step": 45
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 0.7308,
+      "step": 46
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00019134560337254986,
+      "loss": 1.4495,
+      "step": 47
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00018628828433995013,
+      "loss": 0.8338,
+      "step": 48
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.00018118675362266385,
+      "loss": 0.8706,
+      "step": 49
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.00017604722665003956,
+      "loss": 1.3767,
+      "step": 50
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.0001708759651440098,
+      "loss": 1.5032,
+      "step": 51
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.000165679269490148,
+      "loss": 1.3356,
+      "step": 52
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.00016046347106161876,
+      "loss": 1.0869,
+      "step": 53
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.00015523492450537517,
+      "loss": 0.8374,
+      "step": 54
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.00015,
+      "loss": 0.9144,
+      "step": 55
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0001447650754946249,
+      "loss": 0.7246,
+      "step": 56
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.00013953652893838119,
+      "loss": 1.0432,
+      "step": 57
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.000134320730509852,
+      "loss": 0.9271,
+      "step": 58
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0001291240348559902,
+      "loss": 0.7968,
+      "step": 59
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.00012395277334996044,
+      "loss": 0.9131,
+      "step": 60
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.00011881324637733611,
+      "loss": 0.937,
+      "step": 61
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.00011371171566004985,
+      "loss": 0.8228,
+      "step": 62
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.00010865439662745013,
+      "loss": 1.0797,
+      "step": 63
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 0.0001036474508437579,
+      "loss": 0.8893,
+      "step": 64
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 9.869697850114969e-05,
+      "loss": 0.5448,
+      "step": 65
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 9.380901098761319e-05,
+      "loss": 0.6197,
+      "step": 66
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 8.898950353862998e-05,
+      "loss": 0.6925,
+      "step": 67
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 8.424432798163836e-05,
+      "loss": 0.6065,
+      "step": 68
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 7.957926558211642e-05,
+      "loss": 0.9739,
+      "step": 69
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 7.500000000000002e-05,
+      "loss": 0.8073,
+      "step": 70
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 7.051211036501928e-05,
+      "loss": 1.5069,
+      "step": 71
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 6.612106447938799e-05,
+      "loss": 0.5149,
+      "step": 72
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 0.8116,
+      "step": 73
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 5.765077870115125e-05,
+      "loss": 0.5185,
+      "step": 74
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 5.358185854701909e-05,
+      "loss": 0.8031,
+      "step": 75
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 4.963040904617131e-05,
+      "loss": 0.5611,
+      "step": 76
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 4.5801244431150394e-05,
+      "loss": 0.7082,
+      "step": 77
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 4.209902994920235e-05,
+      "loss": 0.8057,
+      "step": 78
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 3.852827617839084e-05,
+      "loss": 1.8981,
+      "step": 79
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 3.509333353215331e-05,
+      "loss": 0.8772,
+      "step": 80
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 3.1798386958991714e-05,
+      "loss": 1.1716,
+      "step": 81
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 2.8647450843757897e-05,
+      "loss": 0.949,
+      "step": 82
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.5644364116743755e-05,
+      "loss": 0.901,
+      "step": 83
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 2.2792785576536105e-05,
+      "loss": 1.0778,
+      "step": 84
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 2.009618943233419e-05,
+      "loss": 1.0495,
+      "step": 85
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 1.755786107116095e-05,
+      "loss": 1.1405,
+      "step": 86
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 1.5180893055124977e-05,
+      "loss": 0.6457,
+      "step": 87
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 1.2968181353609852e-05,
+      "loss": 0.7194,
+      "step": 88
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 1.0922421814981901e-05,
+      "loss": 0.768,
+      "step": 89
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 9.046106882113751e-06,
+      "loss": 0.7015,
+      "step": 90
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 7.34152255572697e-06,
+      "loss": 0.9132,
+      "step": 91
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 5.810745609252165e-06,
+      "loss": 0.703,
+      "step": 92
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 4.455641058600528e-06,
+      "loss": 0.8964,
+      "step": 93
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 3.2778598899291465e-06,
+      "loss": 0.9267,
+      "step": 94
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 2.2788370481687965e-06,
+      "loss": 0.7872,
+      "step": 95
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 1.4597896887644456e-06,
+      "loss": 0.7648,
+      "step": 96
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 8.217156947590064e-07,
+      "loss": 0.5883,
+      "step": 97
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 3.653924610263703e-07,
+      "loss": 0.6093,
+      "step": 98
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 9.137594713563568e-08,
+      "loss": 0.8796,
+      "step": 99
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 0.0,
+      "loss": 0.5744,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2.55142096011264e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d9e4b64c077627c8c7d90a31379e1085611b967f
--- /dev/null
+++ b/checkpoint-100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7871ddb870dca149c8bd176c33a0174c54ce7f51f1623c6ad82c38e78485c96
+size 4411
diff --git a/checkpoint-41/README.md b/checkpoint-41/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1e3637f645b79c1dff559d466047b102e3892f5d
--- /dev/null
+++ b/checkpoint-41/README.md
@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-41/adapter_config.json b/checkpoint-41/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3958451b2551a7766d76c84304260071ab14ec5
--- /dev/null
+++ b/checkpoint-41/adapter_config.json
@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-41/adapter_model.bin b/checkpoint-41/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..21372bbd61eed2462d408974e1ffbda7ec824f18
--- /dev/null
+++ b/checkpoint-41/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ddbd889686556508110f942061578825177da74856785e15f97c63d4f4b005
+size 500897101
diff --git a/checkpoint-41/adapter_model/README.md b/checkpoint-41/adapter_model/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1e3637f645b79c1dff559d466047b102e3892f5d
--- /dev/null
+++ b/checkpoint-41/adapter_model/README.md
@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-41/adapter_model/adapter_config.json b/checkpoint-41/adapter_model/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3958451b2551a7766d76c84304260071ab14ec5
--- /dev/null
+++ b/checkpoint-41/adapter_model/adapter_config.json
@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-41/adapter_model/adapter_model.bin b/checkpoint-41/adapter_model/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..21372bbd61eed2462d408974e1ffbda7ec824f18
--- /dev/null
+++ b/checkpoint-41/adapter_model/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ddbd889686556508110f942061578825177da74856785e15f97c63d4f4b005
+size 500897101
diff --git a/checkpoint-41/optimizer.pt b/checkpoint-41/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3328f00c335805548852f3f5f761015ec8da2fdf
--- /dev/null
+++ b/checkpoint-41/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa675f9cb3260fc969d19ad606acdb7a06f4141a35b38cbe2965d83b8d6ff59
+size 1001736445
diff --git a/checkpoint-41/rng_state.pth b/checkpoint-41/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..72fb44df9bc2f865afdfe2999801bda0312b7a18
--- /dev/null
+++ b/checkpoint-41/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf410588401c344d577bf277e576cb89ffef47ae39cc4edbb9da08ba2fbb438
+size 14575
diff --git a/checkpoint-41/scheduler.pt b/checkpoint-41/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..51dc90191037ad240c4c73b0d97c2498b1ed13c1
--- /dev/null
+++ b/checkpoint-41/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145b10f6d4a353b24514b0dab0a1f00a25175216b6926714cd4f2a5bf613b00b
+size 627
diff --git a/checkpoint-41/trainer_state.json b/checkpoint-41/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e622958c3738de98a17ef942bac58260d05e7e85
--- /dev/null
+++ b/checkpoint-41/trainer_state.json
@@ -0,0 +1,265 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9759036144578315,
+  "eval_steps": 150,
+  "global_step": 41,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.2314,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.4026,
+      "step": 2
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.8531,
+      "step": 3
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.3763,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00015,
+      "loss": 0.961,
+      "step": 5
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.2005,
+      "step": 6
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.1054,
+      "step": 7
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.0114,
+      "step": 8
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00027,
+      "loss": 1.1386,
+      "step": 9
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9856,
+      "step": 10
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00029990862405286433,
+      "loss": 0.7562,
+      "step": 11
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002996346075389736,
+      "loss": 1.0498,
+      "step": 12
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00029917828430524096,
+      "loss": 1.2559,
+      "step": 13
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002985402103112355,
+      "loss": 1.0074,
+      "step": 14
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002977211629518312,
+      "loss": 1.0239,
+      "step": 15
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002967221401100708,
+      "loss": 1.3441,
+      "step": 16
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002955443589413994,
+      "loss": 1.1692,
+      "step": 17
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002941892543907478,
+      "loss": 1.3764,
+      "step": 18
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 0.9064,
+      "step": 19
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002909538931178862,
+      "loss": 1.4608,
+      "step": 20
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002890775781850181,
+      "loss": 1.0947,
+      "step": 21
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0002870318186463901,
+      "loss": 1.113,
+      "step": 22
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.000284819106944875,
+      "loss": 0.9546,
+      "step": 23
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.000282442138928839,
+      "loss": 1.1469,
+      "step": 24
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002799038105676658,
+      "loss": 1.3102,
+      "step": 25
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027720721442346387,
+      "loss": 1.4763,
+      "step": 26
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002743556358832562,
+      "loss": 1.0281,
+      "step": 27
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002713525491562421,
+      "loss": 1.0988,
+      "step": 28
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00026820161304100823,
+      "loss": 1.1848,
+      "step": 29
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00026490666646784665,
+      "loss": 0.9901,
+      "step": 30
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00026147172382160914,
+      "loss": 0.8676,
+      "step": 31
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00025790097005079764,
+      "loss": 1.0521,
+      "step": 32
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0002541987555688496,
+      "loss": 1.0436,
+      "step": 33
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.0002503695909538287,
+      "loss": 0.9511,
+      "step": 34
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002464181414529809,
+      "loss": 1.2208,
+      "step": 35
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002423492212988487,
+      "loss": 1.1128,
+      "step": 36
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00023816778784387094,
+      "loss": 1.114,
+      "step": 37
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023387893552061199,
+      "loss": 0.9318,
+      "step": 38
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.0002294878896349807,
+      "loss": 1.6424,
+      "step": 39
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.000225,
+      "loss": 0.7759,
+      "step": 40
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00022042073441788358,
+      "loss": 0.8061,
+      "step": 41
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.0588396984467456e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-41/training_args.bin b/checkpoint-41/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d9e4b64c077627c8c7d90a31379e1085611b967f
--- /dev/null
+++ b/checkpoint-41/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7871ddb870dca149c8bd176c33a0174c54ce7f51f1623c6ad82c38e78485c96
+size 4411
diff --git a/checkpoint-62/README.md b/checkpoint-62/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1e3637f645b79c1dff559d466047b102e3892f5d
--- /dev/null
+++ b/checkpoint-62/README.md
@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-62/adapter_config.json b/checkpoint-62/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3958451b2551a7766d76c84304260071ab14ec5
--- /dev/null
+++ b/checkpoint-62/adapter_config.json
@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-62/adapter_model.bin b/checkpoint-62/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b0a47c92691fdcce0ba1303a5539f359b53bf3f5
--- /dev/null
+++ b/checkpoint-62/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3996fa6cd634cef2e886ba53704cdaf585f63488956dc493d6208f5bd88b5f89
+size 500897101
diff --git a/checkpoint-62/adapter_model/README.md b/checkpoint-62/adapter_model/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1e3637f645b79c1dff559d466047b102e3892f5d
--- /dev/null
+++ b/checkpoint-62/adapter_model/README.md
@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-62/adapter_model/adapter_config.json b/checkpoint-62/adapter_model/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3958451b2551a7766d76c84304260071ab14ec5
--- /dev/null
+++ b/checkpoint-62/adapter_model/adapter_config.json
@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-62/adapter_model/adapter_model.bin b/checkpoint-62/adapter_model/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b0a47c92691fdcce0ba1303a5539f359b53bf3f5
--- /dev/null
+++ b/checkpoint-62/adapter_model/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3996fa6cd634cef2e886ba53704cdaf585f63488956dc493d6208f5bd88b5f89
+size 500897101
diff --git a/checkpoint-62/optimizer.pt b/checkpoint-62/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..84485c4f98b752a10af7d33c94674f750e620771
--- /dev/null
+++ b/checkpoint-62/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0ad741144f35cb085b4e4b6f6090ac1ee2d46ee5d3b4c75e1c88dde85c72d1
+size 1001736445
diff --git a/checkpoint-62/rng_state.pth b/checkpoint-62/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..27463b54f84b79ecfb984b2bc3d286bd8c721300
--- /dev/null
+++ b/checkpoint-62/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819629affa360efc5b4f9241c8241641e09fe79d70e6c056cd560592ddce2847
+size 14575
diff --git a/checkpoint-62/scheduler.pt b/checkpoint-62/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4da276e96190d0b68e11daf82a4675b780a5fa7f
--- /dev/null
+++ b/checkpoint-62/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885848ada3813b8df84a9c8eb6f0a75ba666603a30e5d56b09dfd1fbca05085f
+size 627
diff --git a/checkpoint-62/trainer_state.json b/checkpoint-62/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..681ac28ac59584c244ebacfc6b7f31cd1ef69bcb
--- /dev/null
+++ b/checkpoint-62/trainer_state.json
@@ -0,0 +1,391 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9879518072289155,
+  "eval_steps": 150,
+  "global_step": 62,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.2314,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.4026,
+      "step": 2
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.8531,
+      "step": 3
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.3763,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00015,
+      "loss": 0.961,
+      "step": 5
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.2005,
+      "step": 6
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.1054,
+      "step": 7
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.0114,
+      "step": 8
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00027,
+      "loss": 1.1386,
+      "step": 9
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9856,
+      "step": 10
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00029990862405286433,
+      "loss": 0.7562,
+      "step": 11
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002996346075389736,
+      "loss": 1.0498,
+      "step": 12
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00029917828430524096,
+      "loss": 1.2559,
+      "step": 13
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002985402103112355,
+      "loss": 1.0074,
+      "step": 14
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002977211629518312,
+      "loss": 1.0239,
+      "step": 15
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002967221401100708,
+      "loss": 1.3441,
+      "step": 16
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002955443589413994,
+      "loss": 1.1692,
+      "step": 17
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002941892543907478,
+      "loss": 1.3764,
+      "step": 18
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 0.9064,
+      "step": 19
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002909538931178862,
+      "loss": 1.4608,
+      "step": 20
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002890775781850181,
+      "loss": 1.0947,
+      "step": 21
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0002870318186463901,
+      "loss": 1.113,
+      "step": 22
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.000284819106944875,
+      "loss": 0.9546,
+      "step": 23
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.000282442138928839,
+      "loss": 1.1469,
+      "step": 24
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002799038105676658,
+      "loss": 1.3102,
+      "step": 25
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027720721442346387,
+      "loss": 1.4763,
+      "step": 26
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002743556358832562,
+      "loss": 1.0281,
+      "step": 27
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002713525491562421,
+      "loss": 1.0988,
+      "step": 28
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00026820161304100823,
+      "loss": 1.1848,
+      "step": 29
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00026490666646784665,
+      "loss": 0.9901,
+      "step": 30
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00026147172382160914,
+      "loss": 0.8676,
+      "step": 31
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00025790097005079764,
+      "loss": 1.0521,
+      "step": 32
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0002541987555688496,
+      "loss": 1.0436,
+      "step": 33
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.0002503695909538287,
+      "loss": 0.9511,
+      "step": 34
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002464181414529809,
+      "loss": 1.2208,
+      "step": 35
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002423492212988487,
+      "loss": 1.1128,
+      "step": 36
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00023816778784387094,
+      "loss": 1.114,
+      "step": 37
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023387893552061199,
+      "loss": 0.9318,
+      "step": 38
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.0002294878896349807,
+      "loss": 1.6424,
+      "step": 39
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.000225,
+      "loss": 0.7759,
+      "step": 40
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00022042073441788358,
+      "loss": 0.8061,
+      "step": 41
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0002157556720183616,
+      "loss": 1.2972,
+      "step": 42
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00021101049646137003,
+      "loss": 0.9694,
+      "step": 43
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.0002061909890123868,
+      "loss": 0.7951,
+      "step": 44
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.00020130302149885031,
+      "loss": 0.8049,
+      "step": 45
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 0.7308,
+      "step": 46
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00019134560337254986,
+      "loss": 1.4495,
+      "step": 47
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00018628828433995013,
+      "loss": 0.8338,
+      "step": 48
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.00018118675362266385,
+      "loss": 0.8706,
+      "step": 49
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.00017604722665003956,
+      "loss": 1.3767,
+      "step": 50
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.0001708759651440098,
+      "loss": 1.5032,
+      "step": 51
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.000165679269490148,
+      "loss": 1.3356,
+      "step": 52
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.00016046347106161876,
+      "loss": 1.0869,
+      "step": 53
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.00015523492450537517,
+      "loss": 0.8374,
+      "step": 54
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.00015,
+      "loss": 0.9144,
+      "step": 55
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0001447650754946249,
+      "loss": 0.7246,
+      "step": 56
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.00013953652893838119,
+      "loss": 1.0432,
+      "step": 57
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.000134320730509852,
+      "loss": 0.9271,
+      "step": 58
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0001291240348559902,
+      "loss": 0.7968,
+      "step": 59
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.00012395277334996044,
+      "loss": 0.9131,
+      "step": 60
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.00011881324637733611,
+      "loss": 0.937,
+      "step": 61
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.00011371171566004985,
+      "loss": 0.8228,
+      "step": 62
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.5882595476701184e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-62/training_args.bin b/checkpoint-62/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d9e4b64c077627c8c7d90a31379e1085611b967f
--- /dev/null
+++ b/checkpoint-62/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7871ddb870dca149c8bd176c33a0174c54ce7f51f1623c6ad82c38e78485c96
+size 4411
diff --git a/checkpoint-83/README.md b/checkpoint-83/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1e3637f645b79c1dff559d466047b102e3892f5d
--- /dev/null
+++ b/checkpoint-83/README.md
@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-83/adapter_config.json b/checkpoint-83/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3958451b2551a7766d76c84304260071ab14ec5
--- /dev/null
+++ b/checkpoint-83/adapter_config.json
@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-83/adapter_model.bin b/checkpoint-83/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0e8b94a6bfe3b88c4b81e9a8285b030c7ed89fd2
--- /dev/null
+++ b/checkpoint-83/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879cb7c9f89b873d886fb62e7cdcf8a9440aab1e33335fe885cb7d5a49ae78ae
+size 500897101
diff --git a/checkpoint-83/adapter_model/README.md b/checkpoint-83/adapter_model/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1e3637f645b79c1dff559d466047b102e3892f5d
--- /dev/null
+++ b/checkpoint-83/adapter_model/README.md
@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-83/adapter_model/adapter_config.json b/checkpoint-83/adapter_model/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3958451b2551a7766d76c84304260071ab14ec5
--- /dev/null
+++ b/checkpoint-83/adapter_model/adapter_config.json
@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-83/adapter_model/adapter_model.bin b/checkpoint-83/adapter_model/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0e8b94a6bfe3b88c4b81e9a8285b030c7ed89fd2
--- /dev/null
+++ b/checkpoint-83/adapter_model/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879cb7c9f89b873d886fb62e7cdcf8a9440aab1e33335fe885cb7d5a49ae78ae
+size 500897101
diff --git a/checkpoint-83/optimizer.pt b/checkpoint-83/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6a314d3c3a450362e5c7706e275c6d3e4dd3b100
--- /dev/null
+++ b/checkpoint-83/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd942b91e8b634407667729822b11d68150258cb2c2c428268928f0a1dcc7c83
+size 1001736445
diff --git a/checkpoint-83/rng_state.pth b/checkpoint-83/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..35dd085f6f80d624a49961fc5c053170600fc5b4
--- /dev/null
+++ b/checkpoint-83/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54251fd1f9b73f220ddc492ed2e7d2b0f6cd2f7c70974412a6eccd366a58c77
+size 14575
diff --git a/checkpoint-83/scheduler.pt b/checkpoint-83/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f04dbbd856e9a992744e3f723a737bca2cee6b31
--- /dev/null
+++ b/checkpoint-83/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877f8c8498f1154c5fce2ccfa856cadaf35802ef3e318bde01bf77c6f3f136b9
+size 627
diff --git a/checkpoint-83/trainer_state.json b/checkpoint-83/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..99922f0e9b6b575390d1e2e4e92dd3357316be3c
--- /dev/null
+++ b/checkpoint-83/trainer_state.json
@@ -0,0 +1,517 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 150,
+  "global_step": 83,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.2314,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.4026,
+      "step": 2
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.8531,
+      "step": 3
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.3763,
+      "step": 4
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00015,
+      "loss": 0.961,
+      "step": 5
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.2005,
+      "step": 6
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.1054,
+      "step": 7
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.0114,
+      "step": 8
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00027,
+      "loss": 1.1386,
+      "step": 9
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9856,
+      "step": 10
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00029990862405286433,
+      "loss": 0.7562,
+      "step": 11
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002996346075389736,
+      "loss": 1.0498,
+      "step": 12
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00029917828430524096,
+      "loss": 1.2559,
+      "step": 13
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002985402103112355,
+      "loss": 1.0074,
+      "step": 14
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002977211629518312,
+      "loss": 1.0239,
+      "step": 15
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002967221401100708,
+      "loss": 1.3441,
+      "step": 16
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002955443589413994,
+      "loss": 1.1692,
+      "step": 17
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002941892543907478,
+      "loss": 1.3764,
+      "step": 18
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 0.9064,
+      "step": 19
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002909538931178862,
+      "loss": 1.4608,
+      "step": 20
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002890775781850181,
+      "loss": 1.0947,
+      "step": 21
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0002870318186463901,
+      "loss": 1.113,
+      "step": 22
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.000284819106944875,
+      "loss": 0.9546,
+      "step": 23
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.000282442138928839,
+      "loss": 1.1469,
+      "step": 24
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002799038105676658,
+      "loss": 1.3102,
+      "step": 25
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00027720721442346387,
+      "loss": 1.4763,
+      "step": 26
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0002743556358832562,
+      "loss": 1.0281,
+      "step": 27
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002713525491562421,
+      "loss": 1.0988,
+      "step": 28
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00026820161304100823,
+      "loss": 1.1848,
+      "step": 29
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00026490666646784665,
+      "loss": 0.9901,
+      "step": 30
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00026147172382160914,
+      "loss": 0.8676,
+      "step": 31
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00025790097005079764,
+      "loss": 1.0521,
+      "step": 32
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0002541987555688496,
+      "loss": 1.0436,
+      "step": 33
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.0002503695909538287,
+      "loss": 0.9511,
+      "step": 34
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002464181414529809,
+      "loss": 1.2208,
+      "step": 35
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002423492212988487,
+      "loss": 1.1128,
+      "step": 36
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00023816778784387094,
+      "loss": 1.114,
+      "step": 37
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023387893552061199,
+      "loss": 0.9318,
+      "step": 38
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.0002294878896349807,
+      "loss": 1.6424,
+      "step": 39
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.000225,
+      "loss": 0.7759,
+      "step": 40
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00022042073441788358,
+      "loss": 0.8061,
+      "step": 41
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0002157556720183616,
+      "loss": 1.2972,
+      "step": 42
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00021101049646137003,
+      "loss": 0.9694,
+      "step": 43
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.0002061909890123868,
+      "loss": 0.7951,
+      "step": 44
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.00020130302149885031,
+      "loss": 0.8049,
+      "step": 45
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 0.7308,
+      "step": 46
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00019134560337254986,
+      "loss": 1.4495,
+      "step": 47
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00018628828433995013,
+      "loss": 0.8338,
+      "step": 48
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.00018118675362266385,
+      "loss": 0.8706,
+      "step": 49
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.00017604722665003956,
+      "loss": 1.3767,
+      "step": 50
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.0001708759651440098,
+      "loss": 1.5032,
+      "step": 51
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.000165679269490148,
+      "loss": 1.3356,
+      "step": 52
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.00016046347106161876,
+      "loss": 1.0869,
+      "step": 53
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.00015523492450537517,
+      "loss": 0.8374,
+      "step": 54
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.00015,
+      "loss": 0.9144,
+      "step": 55
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0001447650754946249,
+      "loss": 0.7246,
+      "step": 56
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.00013953652893838119,
+      "loss": 1.0432,
+      "step": 57
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.000134320730509852,
+      "loss": 0.9271,
+      "step": 58
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0001291240348559902,
+      "loss": 0.7968,
+      "step": 59
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.00012395277334996044,
+      "loss": 0.9131,
+      "step": 60
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.00011881324637733611,
+      "loss": 0.937,
+      "step": 61
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.00011371171566004985,
+      "loss": 0.8228,
+      "step": 62
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.00010865439662745013,
+      "loss": 1.0797,
+      "step": 63
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 0.0001036474508437579,
+      "loss": 0.8893,
+      "step": 64
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 9.869697850114969e-05,
+      "loss": 0.5448,
+      "step": 65
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 9.380901098761319e-05,
+      "loss": 0.6197,
+      "step": 66
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 8.898950353862998e-05,
+      "loss": 0.6925,
+      "step": 67
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 8.424432798163836e-05,
+      "loss": 0.6065,
+      "step": 68
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 7.957926558211642e-05,
+      "loss": 0.9739,
+      "step": 69
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 7.500000000000002e-05,
+      "loss": 0.8073,
+      "step": 70
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 7.051211036501928e-05,
+      "loss": 1.5069,
+      "step": 71
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 6.612106447938799e-05,
+      "loss": 0.5149,
+      "step": 72
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 0.8116,
+      "step": 73
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 5.765077870115125e-05,
+      "loss": 0.5185,
+      "step": 74
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 5.358185854701909e-05,
+      "loss": 0.8031,
+      "step": 75
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 4.963040904617131e-05,
+      "loss": 0.5611,
+      "step": 76
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 4.5801244431150394e-05,
+      "loss": 0.7082,
+      "step": 77
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 4.209902994920235e-05,
+      "loss": 0.8057,
+      "step": 78
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 3.852827617839084e-05,
+      "loss": 1.8981,
+      "step": 79
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 3.509333353215331e-05,
+      "loss": 0.8772,
+      "step": 80
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 3.1798386958991714e-05,
+      "loss": 1.1716,
+      "step": 81
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 2.8647450843757897e-05,
+      "loss": 0.949,
+      "step": 82
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.5644364116743755e-05,
+      "loss": 0.901,
+      "step": 83
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2.1176793968934912e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-83/training_args.bin b/checkpoint-83/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d9e4b64c077627c8c7d90a31379e1085611b967f
--- /dev/null
+++ b/checkpoint-83/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7871ddb870dca149c8bd176c33a0174c54ce7f51f1623c6ad82c38e78485c96
+size 4411
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1481b7c42e4373f0f7e68732c552b88007c38d63
--- /dev/null
+++ b/config.json
@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..09a41a350e349ab0990be2f5cab2b105fad54199
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fd424505b407346d4847dea9d3a9226671071460
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": null,
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}