diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..97b11d22ef295d896f095aca16f96b41531e9ed7
--- /dev/null
+++ b/README.md
@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- 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: float16
+### Framework versions
+
+
+- PEFT 0.4.0
diff --git a/adapter_config.json b/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5a626b5a4361e575a3b10980e75841d933625faf
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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..43b497138bc822749c05be2ca5af88f5da5f37e7
--- /dev/null
+++ b/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2caaad197530a3965a22162a1a4f134ea47bedb0764e975de78c12c02243c5bb
+size 16821197
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..248f4746dfaf12c269b170e89a82f6b14f006611
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.09018798397804953,
+    "train_runtime": 3518.059,
+    "train_samples_per_second": 17.302,
+    "train_steps_per_second": 0.135
+}
\ No newline at end of file
diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..97b11d22ef295d896f095aca16f96b41531e9ed7
--- /dev/null
+++ b/checkpoint-100/README.md
@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- 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: float16
+### Framework versions
+
+
+- PEFT 0.4.0
diff --git a/checkpoint-100/adapter_config.json b/checkpoint-100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5a626b5a4361e575a3b10980e75841d933625faf
--- /dev/null
+++ b/checkpoint-100/adapter_config.json
@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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..475fe9aeb3e954b550aa90bed518647c2653dd08
--- /dev/null
+++ b/checkpoint-100/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda278e5ace76c536aa3bf1c85fe37dee7c1f6ac6d8437aa7124a5892bd0b5dc
+size 16821197
diff --git a/checkpoint-100/finetuning_args.json b/checkpoint-100/finetuning_args.json
new file mode 100644
index 0000000000000000000000000000000000000000..d01efc206b59c6f88548e8f3940579f2ed2af33b
--- /dev/null
+++ b/checkpoint-100/finetuning_args.json
@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}
diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..54b1da46d31647f9ffc8b4debcc99188040c063b
--- /dev/null
+++ b/checkpoint-100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d29bf607d1e1afe671d6ca5da3455e86cdf11d536eef4799cbf210d6b1ba39e3
+size 33661637
diff --git a/checkpoint-100/rng_state_0.pth b/checkpoint-100/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..26357f08d84b728df262fc481ad9047050409ae7
--- /dev/null
+++ b/checkpoint-100/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05af7fd19119f832a74957287aac384167fca8c622934e8187e2f1b6ccab763
+size 18679
diff --git a/checkpoint-100/rng_state_1.pth b/checkpoint-100/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..77d129fbe03b8a7b1602088e42c090985125d793
--- /dev/null
+++ b/checkpoint-100/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e7a3cfb6182f86fd8c287f157dbf17a51e3d41ef4900a9c1d16683de988a06
+size 18679
diff --git a/checkpoint-100/rng_state_2.pth b/checkpoint-100/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7178291ccbcfd1e9d474806b01ae270b19e23c4f
--- /dev/null
+++ b/checkpoint-100/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f739cfd665b8f02ff81eac08273474054f733be834d9f5ad06c198f35c200180
+size 18679
diff --git a/checkpoint-100/rng_state_3.pth b/checkpoint-100/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c0eb54fb91e28825b87795b5a282bf85a62524ee
--- /dev/null
+++ b/checkpoint-100/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85947e197d907567a060baad9da4201ccb50033e71315bdad2473b6c8a9cdd46
+size 18679
diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ad2b4828f6cacfde967869e937adf60424a9efbf
--- /dev/null
+++ b/checkpoint-100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fc3d581e094b837788a14789aed7dda2dc957371e27a9e11c540ba1d15ff44
+size 627
diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..733f91cc9f9125486fab218d59862b9570538892
--- /dev/null
+++ b/checkpoint-100/trainer_state.json
@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.21019442984760903,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994534068046937e-05,
+      "loss": 2.0664,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.978160173317438e-05,
+      "loss": 1.2851,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9509499146870236e-05,
+      "loss": 0.6483,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.913022275693372e-05,
+      "loss": 0.2406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.864543104251587e-05,
+      "loss": 0.0239,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.805724387443462e-05,
+      "loss": 0.0034,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.736823324551909e-05,
+      "loss": 0.0016,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6581412023939354e-05,
+      "loss": 0.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.5700220778700504e-05,
+      "loss": 0.0008,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.0007,
+      "step": 100
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 1.437155155991593e+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..e14c77d2905ba9d555f20cd21583cd156e0fd6e8
--- /dev/null
+++ b/checkpoint-100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4d4776971676826edc330ee61437e7a54bfe686c560913bd8069abb82f5e49
+size 3233
diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..97b11d22ef295d896f095aca16f96b41531e9ed7
--- /dev/null
+++ b/checkpoint-200/README.md
@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- 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: float16
+### Framework versions
+
+
+- PEFT 0.4.0
diff --git a/checkpoint-200/adapter_config.json b/checkpoint-200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5a626b5a4361e575a3b10980e75841d933625faf
--- /dev/null
+++ b/checkpoint-200/adapter_config.json
@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-200/adapter_model.bin b/checkpoint-200/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e48d1ba52d90ece42756462732e4788fcf320e6e
--- /dev/null
+++ b/checkpoint-200/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e7c8df461492fdbde37f96b850b7e78d1c5e76726aa6d370fbeba1ed1c4929
+size 16821197
diff --git a/checkpoint-200/finetuning_args.json b/checkpoint-200/finetuning_args.json
new file mode 100644
index 0000000000000000000000000000000000000000..d01efc206b59c6f88548e8f3940579f2ed2af33b
--- /dev/null
+++ b/checkpoint-200/finetuning_args.json
@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}
diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..38d5e59d1d6ddd1e3e2246168658ee4895f149ba
--- /dev/null
+++ b/checkpoint-200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26051ca8e1622e381cc98e0223e28fa1c5c7bb748de47545c2ca1eeb809cd71e
+size 33661637
diff --git a/checkpoint-200/rng_state_0.pth b/checkpoint-200/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bdd16706c97502b17fb0e0c82a9cc71b11c9e5ef
--- /dev/null
+++ b/checkpoint-200/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0203839e375e297c063f0be527508574258a71b3ef7eb8d60f5ceaaf649b3b1e
+size 18679
diff --git a/checkpoint-200/rng_state_1.pth b/checkpoint-200/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e955d449b2d72ce586a1bd88577e54950d7f81a9
--- /dev/null
+++ b/checkpoint-200/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dab47960e0999cd4f368eb5a167c3f87d3a411f657152e7b67fa055326ad114
+size 18679
diff --git a/checkpoint-200/rng_state_2.pth b/checkpoint-200/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1e44aad8fe664abca66cc445363836815815929f
--- /dev/null
+++ b/checkpoint-200/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0398e0ba30bd59ef210aec509d09e2c236bb6f7ff86f0b3833b3bd95c043974e
+size 18679
diff --git a/checkpoint-200/rng_state_3.pth b/checkpoint-200/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..48e8a4412e0ae6b23967f0fcfbe120080289b235
--- /dev/null
+++ b/checkpoint-200/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa99c0e254813c49ef236c5f2d087a2bdaebf52f8a64f426abb81fa5baa3f4d7
+size 18679
diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6b8c4af09ab9dc26232d73f20d9e857b37bedb9c
--- /dev/null
+++ b/checkpoint-200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893ca84874bd9c2338ac0a97b3de6e0ec91bb60ea1db89177a64098c99125236
+size 627
diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..fdbe73de282c3e767aedaad1c45e30d696010a4a
--- /dev/null
+++ b/checkpoint-200/trainer_state.json
@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.42038885969521805,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994534068046937e-05,
+      "loss": 2.0664,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.978160173317438e-05,
+      "loss": 1.2851,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9509499146870236e-05,
+      "loss": 0.6483,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.913022275693372e-05,
+      "loss": 0.2406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.864543104251587e-05,
+      "loss": 0.0239,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.805724387443462e-05,
+      "loss": 0.0034,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.736823324551909e-05,
+      "loss": 0.0016,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6581412023939354e-05,
+      "loss": 0.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.5700220778700504e-05,
+      "loss": 0.0008,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.0007,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.367053692460385e-05,
+      "loss": 0.0006,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.2530919606812216e-05,
+      "loss": 0.0006,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.131464403810422e-05,
+      "loss": 0.0005,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.002702868207563e-05,
+      "loss": 0.0005,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.867370395306068e-05,
+      "loss": 0.0005,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.726058759576271e-05,
+      "loss": 0.0004,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.579385880846232e-05,
+      "loss": 0.0004,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.427993122295552e-05,
+      "loss": 0.0004,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.0004,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1137137178519985e-05,
+      "loss": 0.0004,
+      "step": 200
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 2.873967036722053e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e14c77d2905ba9d555f20cd21583cd156e0fd6e8
--- /dev/null
+++ b/checkpoint-200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4d4776971676826edc330ee61437e7a54bfe686c560913bd8069abb82f5e49
+size 3233
diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..97b11d22ef295d896f095aca16f96b41531e9ed7
--- /dev/null
+++ b/checkpoint-300/README.md
@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- 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: float16
+### Framework versions
+
+
+- PEFT 0.4.0
diff --git a/checkpoint-300/adapter_config.json b/checkpoint-300/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5a626b5a4361e575a3b10980e75841d933625faf
--- /dev/null
+++ b/checkpoint-300/adapter_config.json
@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-300/adapter_model.bin b/checkpoint-300/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..86f3077818858ddcffd9c8e32fe258a51a78378c
--- /dev/null
+++ b/checkpoint-300/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67afa29920d2fdd88fc572710616aae99bc119a9b324f0484c8bc24be01ea25c
+size 16821197
diff --git a/checkpoint-300/finetuning_args.json b/checkpoint-300/finetuning_args.json
new file mode 100644
index 0000000000000000000000000000000000000000..d01efc206b59c6f88548e8f3940579f2ed2af33b
--- /dev/null
+++ b/checkpoint-300/finetuning_args.json
@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}
diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7a78ced2c75468d9b778292c2ccb3c99aae54d26
--- /dev/null
+++ b/checkpoint-300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6cb61c7e7a6c9212fd13bf186651779365f85b3e4522d49f2cc7080d90909c7
+size 33661637
diff --git a/checkpoint-300/rng_state_0.pth b/checkpoint-300/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..90a8305e0aac36be0e23adf53cbcdfda9f37937b
--- /dev/null
+++ b/checkpoint-300/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e119d10ba4d8e22aaa3ad4fba2f801258396c5fc1f35f4d35ff7c67d85d093
+size 18679
diff --git a/checkpoint-300/rng_state_1.pth b/checkpoint-300/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ea8584de293fed89a403048c0a952348f4ccb957
--- /dev/null
+++ b/checkpoint-300/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006add7f74badc1fcd18e5aa4575f72d37f9ecb8c77edd49ca46735c15e0dcf7
+size 18679
diff --git a/checkpoint-300/rng_state_2.pth b/checkpoint-300/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cee68f710f97b12004f51c0034bf037a71d6d35d
--- /dev/null
+++ b/checkpoint-300/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6cd1596b1eac1b4c3cd748cc1ed511cc8aa6aac36df17540c2c1b726ecc75e8
+size 18679
diff --git a/checkpoint-300/rng_state_3.pth b/checkpoint-300/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..29f4c0df8fef7d4ca51fab21846e6de370169533
--- /dev/null
+++ b/checkpoint-300/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d104156c0b3cb1bfc7442325adf59332e75b57234ca2e3c8e362f1e11d477371
+size 18679
diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6e307497fc88f95e6c819a95a19d96cacaa54448
--- /dev/null
+++ b/checkpoint-300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a611d74221f03f472fa8be6b8d9dcfe898c28b46f2edc8cec83be11539a7887
+size 627
diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9dec3951f65590223bcee371496e1a3ba9ce857c
--- /dev/null
+++ b/checkpoint-300/trainer_state.json
@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6305832895428272,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994534068046937e-05,
+      "loss": 2.0664,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.978160173317438e-05,
+      "loss": 1.2851,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9509499146870236e-05,
+      "loss": 0.6483,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.913022275693372e-05,
+      "loss": 0.2406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.864543104251587e-05,
+      "loss": 0.0239,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.805724387443462e-05,
+      "loss": 0.0034,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.736823324551909e-05,
+      "loss": 0.0016,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6581412023939354e-05,
+      "loss": 0.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.5700220778700504e-05,
+      "loss": 0.0008,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.0007,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.367053692460385e-05,
+      "loss": 0.0006,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.2530919606812216e-05,
+      "loss": 0.0006,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.131464403810422e-05,
+      "loss": 0.0005,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.002702868207563e-05,
+      "loss": 0.0005,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.867370395306068e-05,
+      "loss": 0.0005,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.726058759576271e-05,
+      "loss": 0.0004,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.579385880846232e-05,
+      "loss": 0.0004,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.427993122295552e-05,
+      "loss": 0.0004,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.0004,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1137137178519985e-05,
+      "loss": 0.0004,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.952201335830275e-05,
+      "loss": 0.0003,
+      "step": 210
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.788711592423966e-05,
+      "loss": 0.0003,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.623959386683056e-05,
+      "loss": 0.0003,
+      "step": 230
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.458665138084104e-05,
+      "loss": 0.0003,
+      "step": 240
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2935516363191693e-05,
+      "loss": 0.0003,
+      "step": 250
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1293408807203947e-05,
+      "loss": 0.0003,
+      "step": 260
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9667509231406334e-05,
+      "loss": 0.0003,
+      "step": 270
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.806492728095389e-05,
+      "loss": 0.0003,
+      "step": 280
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6492670638958924e-05,
+      "loss": 0.0003,
+      "step": 290
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.495761438367577e-05,
+      "loss": 0.0003,
+      "step": 300
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 4.311371526302597e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e14c77d2905ba9d555f20cd21583cd156e0fd6e8
--- /dev/null
+++ b/checkpoint-300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4d4776971676826edc330ee61437e7a54bfe686c560913bd8069abb82f5e49
+size 3233
diff --git a/checkpoint-400/README.md b/checkpoint-400/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..97b11d22ef295d896f095aca16f96b41531e9ed7
--- /dev/null
+++ b/checkpoint-400/README.md
@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- 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: float16
+### Framework versions
+
+
+- PEFT 0.4.0
diff --git a/checkpoint-400/adapter_config.json b/checkpoint-400/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5a626b5a4361e575a3b10980e75841d933625faf
--- /dev/null
+++ b/checkpoint-400/adapter_config.json
@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-400/adapter_model.bin b/checkpoint-400/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c2917856f91e694e54f0107d1262bf90a81f6950
--- /dev/null
+++ b/checkpoint-400/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fd70b326a6697e1a82379ba9c06b287cc8ee698d808cfa21a7537b857ee605
+size 16821197
diff --git a/checkpoint-400/finetuning_args.json b/checkpoint-400/finetuning_args.json
new file mode 100644
index 0000000000000000000000000000000000000000..d01efc206b59c6f88548e8f3940579f2ed2af33b
--- /dev/null
+++ b/checkpoint-400/finetuning_args.json
@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}
diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bf292c4b6d73e9af25d75749bb4ff3f54336e045
--- /dev/null
+++ b/checkpoint-400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8202fda93eab44854c6ddcfa01e34c522af24909fcfa74f06f3e10232e7a7a2
+size 33661637
diff --git a/checkpoint-400/rng_state_0.pth b/checkpoint-400/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..647f87f74c9aecf8128d6a674c4def997fdf94e7
--- /dev/null
+++ b/checkpoint-400/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9339f5ba504bd7e6c3838357145b22a63fe93f3cbda16765783c9f6ca7e88f4d
+size 18679
diff --git a/checkpoint-400/rng_state_1.pth b/checkpoint-400/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b856734d44bef85a1f82528c97068a3080931913
--- /dev/null
+++ b/checkpoint-400/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def61d8ae44359a8cba9c62b9dd81352520cc1a9048bbd8b47b06e3e32262cf5
+size 18679
diff --git a/checkpoint-400/rng_state_2.pth b/checkpoint-400/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ec4f0a35b42f8d1dcb664e6d293cb470d0ffbf9e
--- /dev/null
+++ b/checkpoint-400/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308b0154faf07284bf01c71c1aaa5284e1186f6ab682693f519f295a98f6ef3f
+size 18679
diff --git a/checkpoint-400/rng_state_3.pth b/checkpoint-400/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e34636ab82d9c4e36877b20acc50d3a570dd52cb
--- /dev/null
+++ b/checkpoint-400/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af9908fa1c4458f08404ed789ea1c784606ac07ca08486673d8f3e3522a2105
+size 18679
diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d928dd2f5423d293ca89b147144db1e071480bf6
--- /dev/null
+++ b/checkpoint-400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dee0767eaefa25af7080534beb0e2e99f2c8c9364e6b61372d798c11efa0dae
+size 627
diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3a0169779a448f3a3ed32f4edf2bcdfe4ddb5986
--- /dev/null
+++ b/checkpoint-400/trainer_state.json
@@ -0,0 +1,256 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8407777193904361,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994534068046937e-05,
+      "loss": 2.0664,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.978160173317438e-05,
+      "loss": 1.2851,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9509499146870236e-05,
+      "loss": 0.6483,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.913022275693372e-05,
+      "loss": 0.2406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.864543104251587e-05,
+      "loss": 0.0239,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.805724387443462e-05,
+      "loss": 0.0034,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.736823324551909e-05,
+      "loss": 0.0016,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6581412023939354e-05,
+      "loss": 0.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.5700220778700504e-05,
+      "loss": 0.0008,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.0007,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.367053692460385e-05,
+      "loss": 0.0006,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.2530919606812216e-05,
+      "loss": 0.0006,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.131464403810422e-05,
+      "loss": 0.0005,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.002702868207563e-05,
+      "loss": 0.0005,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.867370395306068e-05,
+      "loss": 0.0005,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.726058759576271e-05,
+      "loss": 0.0004,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.579385880846232e-05,
+      "loss": 0.0004,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.427993122295552e-05,
+      "loss": 0.0004,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.0004,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1137137178519985e-05,
+      "loss": 0.0004,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.952201335830275e-05,
+      "loss": 0.0003,
+      "step": 210
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.788711592423966e-05,
+      "loss": 0.0003,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.623959386683056e-05,
+      "loss": 0.0003,
+      "step": 230
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.458665138084104e-05,
+      "loss": 0.0003,
+      "step": 240
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2935516363191693e-05,
+      "loss": 0.0003,
+      "step": 250
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1293408807203947e-05,
+      "loss": 0.0003,
+      "step": 260
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9667509231406334e-05,
+      "loss": 0.0003,
+      "step": 270
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.806492728095389e-05,
+      "loss": 0.0003,
+      "step": 280
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6492670638958924e-05,
+      "loss": 0.0003,
+      "step": 290
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.495761438367577e-05,
+      "loss": 0.0003,
+      "step": 300
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.346647092553281e-05,
+      "loss": 0.0003,
+      "step": 310
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.202576065546963e-05,
+      "loss": 0.0003,
+      "step": 320
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.064178343292641e-05,
+      "loss": 0.0003,
+      "step": 330
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.320591038161574e-06,
+      "loss": 0.0003,
+      "step": 340
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.067960709356478e-06,
+      "loss": 0.0003,
+      "step": 350
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.889369880222776e-06,
+      "loss": 0.0002,
+      "step": 360
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.78997222857853e-06,
+      "loss": 0.0002,
+      "step": 370
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.0002,
+      "step": 380
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.847618689476612e-06,
+      "loss": 0.0002,
+      "step": 390
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.013156219837776e-06,
+      "loss": 0.0002,
+      "step": 400
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 5.748761477418844e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e14c77d2905ba9d555f20cd21583cd156e0fd6e8
--- /dev/null
+++ b/checkpoint-400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4d4776971676826edc330ee61437e7a54bfe686c560913bd8069abb82f5e49
+size 3233
diff --git a/finetuning_args.json b/finetuning_args.json
new file mode 100644
index 0000000000000000000000000000000000000000..d01efc206b59c6f88548e8f3940579f2ed2af33b
--- /dev/null
+++ b/finetuning_args.json
@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..248f4746dfaf12c269b170e89a82f6b14f006611
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.09018798397804953,
+    "train_runtime": 3518.059,
+    "train_samples_per_second": 17.302,
+    "train_steps_per_second": 0.135
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..814031b87587a40d4dd8ffffc3865d32a4bb1461
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,48 @@
+{"current_steps": 10, "total_steps": 475, "loss": 2.0664, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.994534068046937e-05, "epoch": 0.02, "percentage": 2.11, "elapsed_time": "0:01:13", "remaining_time": "0:56:54"}
+{"current_steps": 20, "total_steps": 475, "loss": 1.2851, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.978160173317438e-05, "epoch": 0.04, "percentage": 4.21, "elapsed_time": "0:02:26", "remaining_time": "0:55:36"}
+{"current_steps": 30, "total_steps": 475, "loss": 0.6483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9509499146870236e-05, "epoch": 0.06, "percentage": 6.32, "elapsed_time": "0:03:40", "remaining_time": "0:54:26"}
+{"current_steps": 40, "total_steps": 475, "loss": 0.2406, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.913022275693372e-05, "epoch": 0.08, "percentage": 8.42, "elapsed_time": "0:04:54", "remaining_time": "0:53:18"}
+{"current_steps": 50, "total_steps": 475, "loss": 0.0239, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.864543104251587e-05, "epoch": 0.11, "percentage": 10.53, "elapsed_time": "0:06:08", "remaining_time": "0:52:10"}
+{"current_steps": 60, "total_steps": 475, "loss": 0.0034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.805724387443462e-05, "epoch": 0.13, "percentage": 12.63, "elapsed_time": "0:07:22", "remaining_time": "0:51:01"}
+{"current_steps": 70, "total_steps": 475, "loss": 0.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.736823324551909e-05, "epoch": 0.15, "percentage": 14.74, "elapsed_time": "0:08:36", "remaining_time": "0:49:50"}
+{"current_steps": 80, "total_steps": 475, "loss": 0.001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6581412023939354e-05, "epoch": 0.17, "percentage": 16.84, "elapsed_time": "0:09:50", "remaining_time": "0:48:37"}
+{"current_steps": 90, "total_steps": 475, "loss": 0.0008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5700220778700504e-05, "epoch": 0.19, "percentage": 18.95, "elapsed_time": "0:11:05", "remaining_time": "0:47:24"}
+{"current_steps": 100, "total_steps": 475, "loss": 0.0007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4728512734909844e-05, "epoch": 0.21, "percentage": 21.05, "elapsed_time": "0:12:19", "remaining_time": "0:46:12"}
+{"current_steps": 110, "total_steps": 475, "loss": 0.0006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.367053692460385e-05, "epoch": 0.23, "percentage": 23.16, "elapsed_time": "0:13:33", "remaining_time": "0:45:00"}
+{"current_steps": 120, "total_steps": 475, "loss": 0.0006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2530919606812216e-05, "epoch": 0.25, "percentage": 25.26, "elapsed_time": "0:14:48", "remaining_time": "0:43:47"}
+{"current_steps": 130, "total_steps": 475, "loss": 0.0005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.131464403810422e-05, "epoch": 0.27, "percentage": 27.37, "elapsed_time": "0:16:02", "remaining_time": "0:42:33"}
+{"current_steps": 140, "total_steps": 475, "loss": 0.0005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.002702868207563e-05, "epoch": 0.29, "percentage": 29.47, "elapsed_time": "0:17:16", "remaining_time": "0:41:20"}
+{"current_steps": 150, "total_steps": 475, "loss": 0.0005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.867370395306068e-05, "epoch": 0.32, "percentage": 31.58, "elapsed_time": "0:18:31", "remaining_time": "0:40:07"}
+{"current_steps": 160, "total_steps": 475, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.726058759576271e-05, "epoch": 0.34, "percentage": 33.68, "elapsed_time": "0:19:45", "remaining_time": "0:38:53"}
+{"current_steps": 170, "total_steps": 475, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.579385880846232e-05, "epoch": 0.36, "percentage": 35.79, "elapsed_time": "0:20:59", "remaining_time": "0:37:39"}
+{"current_steps": 180, "total_steps": 475, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.427993122295552e-05, "epoch": 0.38, "percentage": 37.89, "elapsed_time": "0:22:13", "remaining_time": "0:36:25"}
+{"current_steps": 190, "total_steps": 475, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.272542485937369e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:23:27", "remaining_time": "0:35:11"}
+{"current_steps": 200, "total_steps": 475, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1137137178519985e-05, "epoch": 0.42, "percentage": 42.11, "elapsed_time": "0:24:41", "remaining_time": "0:33:57"}
+{"current_steps": 210, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.952201335830275e-05, "epoch": 0.44, "percentage": 44.21, "elapsed_time": "0:25:56", "remaining_time": "0:32:43"}
+{"current_steps": 220, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.788711592423966e-05, "epoch": 0.46, "percentage": 46.32, "elapsed_time": "0:27:10", "remaining_time": "0:31:29"}
+{"current_steps": 230, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.623959386683056e-05, "epoch": 0.48, "percentage": 48.42, "elapsed_time": "0:28:24", "remaining_time": "0:30:15"}
+{"current_steps": 240, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.458665138084104e-05, "epoch": 0.5, "percentage": 50.53, "elapsed_time": "0:29:37", "remaining_time": "0:29:00"}
+{"current_steps": 250, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2935516363191693e-05, "epoch": 0.53, "percentage": 52.63, "elapsed_time": "0:30:52", "remaining_time": "0:27:46"}
+{"current_steps": 260, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1293408807203947e-05, "epoch": 0.55, "percentage": 54.74, "elapsed_time": "0:32:06", "remaining_time": "0:26:32"}
+{"current_steps": 270, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9667509231406334e-05, "epoch": 0.57, "percentage": 56.84, "elapsed_time": "0:33:20", "remaining_time": "0:25:19"}
+{"current_steps": 280, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.806492728095389e-05, "epoch": 0.59, "percentage": 58.95, "elapsed_time": "0:34:34", "remaining_time": "0:24:05"}
+{"current_steps": 290, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6492670638958924e-05, "epoch": 0.61, "percentage": 61.05, "elapsed_time": "0:35:49", "remaining_time": "0:22:50"}
+{"current_steps": 300, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.495761438367577e-05, "epoch": 0.63, "percentage": 63.16, "elapsed_time": "0:37:03", "remaining_time": "0:21:36"}
+{"current_steps": 310, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.346647092553281e-05, "epoch": 0.65, "percentage": 65.26, "elapsed_time": "0:38:17", "remaining_time": "0:20:22"}
+{"current_steps": 320, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.202576065546963e-05, "epoch": 0.67, "percentage": 67.37, "elapsed_time": "0:39:31", "remaining_time": "0:19:08"}
+{"current_steps": 330, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.064178343292641e-05, "epoch": 0.69, "percentage": 69.47, "elapsed_time": "0:40:45", "remaining_time": "0:17:54"}
+{"current_steps": 340, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.320591038161574e-06, "epoch": 0.71, "percentage": 71.58, "elapsed_time": "0:41:59", "remaining_time": "0:16:40"}
+{"current_steps": 350, "total_steps": 475, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.067960709356478e-06, "epoch": 0.74, "percentage": 73.68, "elapsed_time": "0:43:13", "remaining_time": "0:15:26"}
+{"current_steps": 360, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.889369880222776e-06, "epoch": 0.76, "percentage": 75.79, "elapsed_time": "0:44:27", "remaining_time": "0:14:12"}
+{"current_steps": 370, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.78997222857853e-06, "epoch": 0.78, "percentage": 77.89, "elapsed_time": "0:45:41", "remaining_time": "0:12:58"}
+{"current_steps": 380, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7745751406263165e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:46:55", "remaining_time": "0:11:43"}
+{"current_steps": 390, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.847618689476612e-06, "epoch": 0.82, "percentage": 82.11, "elapsed_time": "0:48:09", "remaining_time": "0:10:29"}
+{"current_steps": 400, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.013156219837776e-06, "epoch": 0.84, "percentage": 84.21, "elapsed_time": "0:49:23", "remaining_time": "0:09:15"}
+{"current_steps": 410, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2748366237709374e-06, "epoch": 0.86, "percentage": 86.32, "elapsed_time": "0:50:37", "remaining_time": "0:08:01"}
+{"current_steps": 420, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6358883850134816e-06, "epoch": 0.88, "percentage": 88.42, "elapsed_time": "0:51:51", "remaining_time": "0:06:47"}
+{"current_steps": 430, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0991054616410589e-06, "epoch": 0.9, "percentage": 90.53, "elapsed_time": "0:53:05", "remaining_time": "0:05:33"}
+{"current_steps": 440, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.668350687998565e-07, "epoch": 0.92, "percentage": 92.63, "elapsed_time": "0:54:19", "remaining_time": "0:04:19"}
+{"current_steps": 450, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4096741493194197e-07, "epoch": 0.95, "percentage": 94.74, "elapsed_time": "0:55:33", "remaining_time": "0:03:05"}
+{"current_steps": 460, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.229274363747146e-07, "epoch": 0.97, "percentage": 96.84, "elapsed_time": "0:56:46", "remaining_time": "0:01:51"}
+{"current_steps": 470, "total_steps": 475, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3668566476848777e-08, "epoch": 0.99, "percentage": 98.95, "elapsed_time": "0:58:00", "remaining_time": "0:00:37"}
+{"current_steps": 475, "total_steps": 475, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:58:38", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..41f2a79330db9c6899107c5befcb6b1be684e537
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,307 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984235417761429,
+  "global_step": 475,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994534068046937e-05,
+      "loss": 2.0664,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.978160173317438e-05,
+      "loss": 1.2851,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9509499146870236e-05,
+      "loss": 0.6483,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.913022275693372e-05,
+      "loss": 0.2406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.864543104251587e-05,
+      "loss": 0.0239,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.805724387443462e-05,
+      "loss": 0.0034,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.736823324551909e-05,
+      "loss": 0.0016,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6581412023939354e-05,
+      "loss": 0.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.5700220778700504e-05,
+      "loss": 0.0008,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.0007,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.367053692460385e-05,
+      "loss": 0.0006,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.2530919606812216e-05,
+      "loss": 0.0006,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.131464403810422e-05,
+      "loss": 0.0005,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.002702868207563e-05,
+      "loss": 0.0005,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.867370395306068e-05,
+      "loss": 0.0005,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.726058759576271e-05,
+      "loss": 0.0004,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.579385880846232e-05,
+      "loss": 0.0004,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.427993122295552e-05,
+      "loss": 0.0004,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.0004,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1137137178519985e-05,
+      "loss": 0.0004,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.952201335830275e-05,
+      "loss": 0.0003,
+      "step": 210
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.788711592423966e-05,
+      "loss": 0.0003,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.623959386683056e-05,
+      "loss": 0.0003,
+      "step": 230
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.458665138084104e-05,
+      "loss": 0.0003,
+      "step": 240
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2935516363191693e-05,
+      "loss": 0.0003,
+      "step": 250
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1293408807203947e-05,
+      "loss": 0.0003,
+      "step": 260
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9667509231406334e-05,
+      "loss": 0.0003,
+      "step": 270
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.806492728095389e-05,
+      "loss": 0.0003,
+      "step": 280
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6492670638958924e-05,
+      "loss": 0.0003,
+      "step": 290
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.495761438367577e-05,
+      "loss": 0.0003,
+      "step": 300
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.346647092553281e-05,
+      "loss": 0.0003,
+      "step": 310
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.202576065546963e-05,
+      "loss": 0.0003,
+      "step": 320
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.064178343292641e-05,
+      "loss": 0.0003,
+      "step": 330
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.320591038161574e-06,
+      "loss": 0.0003,
+      "step": 340
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.067960709356478e-06,
+      "loss": 0.0003,
+      "step": 350
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.889369880222776e-06,
+      "loss": 0.0002,
+      "step": 360
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.78997222857853e-06,
+      "loss": 0.0002,
+      "step": 370
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.0002,
+      "step": 380
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.847618689476612e-06,
+      "loss": 0.0002,
+      "step": 390
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.013156219837776e-06,
+      "loss": 0.0002,
+      "step": 400
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.2748366237709374e-06,
+      "loss": 0.0002,
+      "step": 410
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6358883850134816e-06,
+      "loss": 0.0002,
+      "step": 420
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.0991054616410589e-06,
+      "loss": 0.0002,
+      "step": 430
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 6.668350687998565e-07,
+      "loss": 0.0002,
+      "step": 440
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.4096741493194197e-07,
+      "loss": 0.0002,
+      "step": 450
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.229274363747146e-07,
+      "loss": 0.0002,
+      "step": 460
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3668566476848777e-08,
+      "loss": 0.0002,
+      "step": 470
+    },
+    {
+      "epoch": 1.0,
+      "step": 475,
+      "total_flos": 6.826782473972613e+17,
+      "train_loss": 0.09018798397804953,
+      "train_runtime": 3518.059,
+      "train_samples_per_second": 17.302,
+      "train_steps_per_second": 0.135
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 6.826782473972613e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e14c77d2905ba9d555f20cd21583cd156e0fd6e8
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4d4776971676826edc330ee61437e7a54bfe686c560913bd8069abb82f5e49
+size 3233
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..c2b00f567dd1f1947184afd7cf19ea5a30727730
Binary files /dev/null and b/training_loss.png differ