diff --git a/adapter_config.json b/adapter_config.json
index 6984f5fd4bab99ec956ebe3bf12d7b823649c936..dca2f2f9b1cb6bbf83fbb8065749a4d18905e681 100644
--- a/adapter_config.json
+++ b/adapter_config.json
@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
     "gate_proj",
     "v_proj",
-    "o_proj",
+    "k_proj",
     "q_proj",
-    "up_proj"
+    "up_proj",
+    "o_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }
\ No newline at end of file
diff --git a/adapter_model.bin b/adapter_model.bin
index 9983417f84d25dbcb0ce2f5f4845d2e07f37baac..558fc37fdb360c0c71f8b5c5f07d76454d85038d 100644
--- a/adapter_model.bin
+++ b/adapter_model.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5a92be0cd5f8b38b328e0f82e62452a3fa7b5052a0a1f93fd8c4b1dd18b7a7
+oid sha256:dd1d9047d90b00aaf0a6c21147e9789af5c4ef9e3c1df5179a1b86f66b610c52
 size 500897101
diff --git a/checkpoint-2900/README.md b/checkpoint-2900/README.md
deleted file mode 100644
index f2208b0ded6c10ed47b2ea9df5ab7c8dd721a53c..0000000000000000000000000000000000000000
--- a/checkpoint-2900/README.md
+++ /dev/null
@@ -1,20 +0,0 @@
----
-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: bfloat16
-### Framework versions
-
-
-- PEFT 0.5.0.dev0
diff --git a/checkpoint-2900/adapter_config.json b/checkpoint-2900/adapter_config.json
deleted file mode 100644
index 6984f5fd4bab99ec956ebe3bf12d7b823649c936..0000000000000000000000000000000000000000
--- a/checkpoint-2900/adapter_config.json
+++ /dev/null
@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
-  "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": [
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}
\ No newline at end of file
diff --git a/checkpoint-2900/adapter_model.bin b/checkpoint-2900/adapter_model.bin
deleted file mode 100644
index 0e01f2caf060c4519b73a276a9a033a6d99e6d04..0000000000000000000000000000000000000000
--- a/checkpoint-2900/adapter_model.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:69e75ae7e1f69a41e91706ac778c4176886a39e991e0545bde52d6c1f744f678
-size 500897101
diff --git a/checkpoint-2900/adapter_model/README.md b/checkpoint-2900/adapter_model/README.md
deleted file mode 100644
index f2208b0ded6c10ed47b2ea9df5ab7c8dd721a53c..0000000000000000000000000000000000000000
--- a/checkpoint-2900/adapter_model/README.md
+++ /dev/null
@@ -1,20 +0,0 @@
----
-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: bfloat16
-### Framework versions
-
-
-- PEFT 0.5.0.dev0
diff --git a/checkpoint-2900/adapter_model/adapter_config.json b/checkpoint-2900/adapter_model/adapter_config.json
deleted file mode 100644
index 6984f5fd4bab99ec956ebe3bf12d7b823649c936..0000000000000000000000000000000000000000
--- a/checkpoint-2900/adapter_model/adapter_config.json
+++ /dev/null
@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
-  "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": [
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}
\ No newline at end of file
diff --git a/checkpoint-2900/adapter_model/adapter_model.bin b/checkpoint-2900/adapter_model/adapter_model.bin
deleted file mode 100644
index 0e01f2caf060c4519b73a276a9a033a6d99e6d04..0000000000000000000000000000000000000000
--- a/checkpoint-2900/adapter_model/adapter_model.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:69e75ae7e1f69a41e91706ac778c4176886a39e991e0545bde52d6c1f744f678
-size 500897101
diff --git a/checkpoint-2900/optimizer.pt b/checkpoint-2900/optimizer.pt
deleted file mode 100644
index 8474a8e8d05575d6099412cb5ad050dd2f1f1b43..0000000000000000000000000000000000000000
--- a/checkpoint-2900/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c87b4dae7f70055caf6d97c6be4cde96969b4b232d33f2ec8df44468892e94ae
-size 1001752701
diff --git a/checkpoint-2900/rng_state_0.pth b/checkpoint-2900/rng_state_0.pth
deleted file mode 100644
index f79b83259792dffe57634581a2a672cf046f726b..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_0.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ef95949da63c44bf2803034d897cf02b2c1404fb37a4930aa3e5a0ec33f3e973
-size 27772
diff --git a/checkpoint-2900/rng_state_1.pth b/checkpoint-2900/rng_state_1.pth
deleted file mode 100644
index c61db5b564881f61f4c37f6d13df0dd28791bffd..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_1.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d659d12bcecefb93ed656fc3f6ed770926a62be67a034197a8fc61d6626623aa
-size 27772
diff --git a/checkpoint-2900/rng_state_10.pth b/checkpoint-2900/rng_state_10.pth
deleted file mode 100644
index 91703dceb44bf355deb72239217b8fb0afb7e846..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_10.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3c8b3dd09b89ccf70ecfb60c04b41270829ea90cfa0f805505a977df5bed72a8
-size 27789
diff --git a/checkpoint-2900/rng_state_11.pth b/checkpoint-2900/rng_state_11.pth
deleted file mode 100644
index 71dd3078ed5beefd3c50ab839bf51c78cfbbb998..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_11.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3a529130f265d55a197418034304b29c2f30e5460bdc34974ffa7dc75b218dee
-size 27789
diff --git a/checkpoint-2900/rng_state_12.pth b/checkpoint-2900/rng_state_12.pth
deleted file mode 100644
index 8286add7c4aa2ffef0fd5f0eaafab933eb7991d5..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_12.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:364a7220780238b4e23965c23a3f97f81bcf3f5672fb2c6ba1f95a8ce81dcd6a
-size 27789
diff --git a/checkpoint-2900/rng_state_13.pth b/checkpoint-2900/rng_state_13.pth
deleted file mode 100644
index 855aa83a6d8f0b9fe70db0c4caa52374ea6dc1ee..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_13.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ca8a5bf47b25db91e77352018364ed5cb8658c4ab84c74754d600a671025b52
-size 27789
diff --git a/checkpoint-2900/rng_state_2.pth b/checkpoint-2900/rng_state_2.pth
deleted file mode 100644
index 64aae3442f1ab92a342dc2dab330563a68e132f8..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_2.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e38e3caba0fb2345524e8ba51c489e590ff9c29f6b6b1852244b5b876edef717
-size 27772
diff --git a/checkpoint-2900/rng_state_3.pth b/checkpoint-2900/rng_state_3.pth
deleted file mode 100644
index 01b1781a3ce90af12bac00aef0d846d9019dd2d0..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_3.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e25391629539867dd50549dd648e30136ff0695597362098b5348ddfb9b13591
-size 27772
diff --git a/checkpoint-2900/rng_state_4.pth b/checkpoint-2900/rng_state_4.pth
deleted file mode 100644
index faed7b9620bac7edf431140ea99c0d1e47be184e..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_4.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:05c76df7735faef919f1d2529cb22dc8b258235397aea29e5d522f742f0378d3
-size 27772
diff --git a/checkpoint-2900/rng_state_5.pth b/checkpoint-2900/rng_state_5.pth
deleted file mode 100644
index 7b8dcaf84a4eb5ecca0d3a7401598b89a1d3837f..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_5.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:04f49ff59341bf10436ddf12dfda352e27600dda201e545e829be606ffa4a75b
-size 27772
diff --git a/checkpoint-2900/rng_state_6.pth b/checkpoint-2900/rng_state_6.pth
deleted file mode 100644
index 869b648f171f0dfa18c414bd69ad610bd3ef1081..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_6.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5235f6c75f2e3a3b228ad84d02c69e6e58f2c65de54d888dd789ea3de5eccaae
-size 27772
diff --git a/checkpoint-2900/rng_state_7.pth b/checkpoint-2900/rng_state_7.pth
deleted file mode 100644
index f50e129b72ec486b2e229cb1f16fc95c11f296fe..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_7.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6d1e22c7b9e7f7aea18263f185bde2560e57a023912a137341f61fe9d96545ab
-size 27772
diff --git a/checkpoint-2900/rng_state_8.pth b/checkpoint-2900/rng_state_8.pth
deleted file mode 100644
index 129db455492da242ee686fe22c9e30d467ca82c2..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_8.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:466fa25c9331cd4ea53315fb2b9f257aa0623587238faa3ca9b184ccb63c1756
-size 27772
diff --git a/checkpoint-2900/rng_state_9.pth b/checkpoint-2900/rng_state_9.pth
deleted file mode 100644
index 05df8534aafa7b4fd29c853c7d099d422cf8817e..0000000000000000000000000000000000000000
--- a/checkpoint-2900/rng_state_9.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:71dcdb5ca148232df1ccde976ae62a837427d137bd880eb213220fe9d130a051
-size 27772
diff --git a/checkpoint-2900/scheduler.pt b/checkpoint-2900/scheduler.pt
deleted file mode 100644
index 426769270ce969e3d658cea22246fe6ca1e97104..0000000000000000000000000000000000000000
--- a/checkpoint-2900/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7bdab61020affcb7675661f6f3289658a70b84200495ea5e8c5d13b32c66edcc
-size 627
diff --git a/checkpoint-2900/trainer_state.json b/checkpoint-2900/trainer_state.json
deleted file mode 100644
index b6b16164b8f888d78a3677c708d66ed5443dfa49..0000000000000000000000000000000000000000
--- a/checkpoint-2900/trainer_state.json
+++ /dev/null
@@ -1,704 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.1244668476153548,
-  "global_step": 2900,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.02,
-      "learning_rate": 0.0001999867761371633,
-      "loss": 1.0435,
-      "step": 50
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 0.00019993306018843102,
-      "loss": 0.8918,
-      "step": 100
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 0.00019983804784290833,
-      "loss": 0.8874,
-      "step": 150
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 0.00019970177836355307,
-      "loss": 0.8839,
-      "step": 200
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 0.00019961818913082012,
-      "loss": 0.8801,
-      "step": 225
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 0.00019952430806244534,
-      "loss": 0.8753,
-      "step": 250
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 0.00019942014485754635,
-      "loss": 0.8754,
-      "step": 275
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 0.00019930571027751713,
-      "loss": 0.8751,
-      "step": 300
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 0.0001991810161449164,
-      "loss": 0.8819,
-      "step": 325
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 0.00019904607534224612,
-      "loss": 0.8744,
-      "step": 350
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 0.00019890090181062063,
-      "loss": 0.8735,
-      "step": 375
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019874551054832625,
-      "loss": 0.8703,
-      "step": 400
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019857991760927193,
-      "loss": 0.8715,
-      "step": 425
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 0.00019840414010133045,
-      "loss": 0.8714,
-      "step": 450
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 0.00019821819618457114,
-      "loss": 0.8653,
-      "step": 475
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 0.0001980221050693837,
-      "loss": 0.8716,
-      "step": 500
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 0.00019781588701449338,
-      "loss": 0.8695,
-      "step": 525
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 0.0001975995633248682,
-      "loss": 0.8746,
-      "step": 550
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 0.00019737315634951762,
-      "loss": 0.8731,
-      "step": 575
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 0.00019713668947918386,
-      "loss": 0.867,
-      "step": 600
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 0.0001968901871439252,
-      "loss": 0.8706,
-      "step": 625
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 0.000196633674810592,
-      "loss": 0.8595,
-      "step": 650
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 0.0001963671789801958,
-      "loss": 0.8627,
-      "step": 675
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 0.0001960907271851712,
-      "loss": 0.8607,
-      "step": 700
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 0.00019580434798653173,
-      "loss": 0.858,
-      "step": 725
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 0.00019550807097091876,
-      "loss": 0.8589,
-      "step": 750
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 0.00019520192674754515,
-      "loss": 0.8561,
-      "step": 775
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 0.00019488594694503264,
-      "loss": 0.8576,
-      "step": 800
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 0.00019456016420814446,
-      "loss": 0.8597,
-      "step": 825
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 0.00019422461219441254,
-      "loss": 0.862,
-      "step": 850
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 0.00019387932557066035,
-      "loss": 0.8577,
-      "step": 875
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 0.00019352434000942127,
-      "loss": 0.8632,
-      "step": 900
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 0.00019315969218525333,
-      "loss": 0.8567,
-      "step": 925
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 0.00019278541977095005,
-      "loss": 0.8501,
-      "step": 950
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 0.00019240156143364844,
-      "loss": 0.8596,
-      "step": 975
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 0.00019200815683083434,
-      "loss": 0.8556,
-      "step": 1000
-    },
-    {
-      "epoch": 0.39,
-      "eval_loss": 0.8521950244903564,
-      "eval_runtime": 59.8838,
-      "eval_samples_per_second": 12.19,
-      "eval_steps_per_second": 0.885,
-      "step": 1000
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 0.00019160524660624505,
-      "loss": 0.8531,
-      "step": 1025
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 0.00019119287238567045,
-      "loss": 0.8513,
-      "step": 1050
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 0.00019077107677265253,
-      "loss": 0.8502,
-      "step": 1075
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 0.00019033990334408384,
-      "loss": 0.8469,
-      "step": 1100
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 0.00018989939664570545,
-      "loss": 0.8495,
-      "step": 1125
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 0.00018944960218750484,
-      "loss": 0.8485,
-      "step": 1150
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 0.00018899056643901404,
-      "loss": 0.8534,
-      "step": 1175
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018852233682450893,
-      "loss": 0.8531,
-      "step": 1200
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018804496171810948,
-      "loss": 0.8509,
-      "step": 1225
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 0.00018755849043878222,
-      "loss": 0.8445,
-      "step": 1250
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 0.0001870629732452449,
-      "loss": 0.8548,
-      "step": 1275
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 0.00018655846133077417,
-      "loss": 0.8441,
-      "step": 1300
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 0.00018604500681791656,
-      "loss": 0.8533,
-      "step": 1325
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 0.00018552266275310373,
-      "loss": 0.8505,
-      "step": 1350
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 0.0001849914831011719,
-      "loss": 0.8544,
-      "step": 1375
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 0.00018445152273978668,
-      "loss": 0.845,
-      "step": 1400
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 0.00018390283745377354,
-      "loss": 0.8376,
-      "step": 1425
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 0.0001833454839293545,
-      "loss": 0.847,
-      "step": 1450
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 0.00018277951974829163,
-      "loss": 0.8473,
-      "step": 1475
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.0001822050033819382,
-      "loss": 0.8438,
-      "step": 1500
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 0.00018162199418519785,
-      "loss": 0.8418,
-      "step": 1525
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 0.00018103055239039243,
-      "loss": 0.842,
-      "step": 1550
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 0.0001804307391010393,
-      "loss": 0.8435,
-      "step": 1575
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 0.00017982261628553842,
-      "loss": 0.8349,
-      "step": 1600
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 0.0001792062467707703,
-      "loss": 0.8483,
-      "step": 1625
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 0.0001785816942356052,
-      "loss": 0.8387,
-      "step": 1650
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 0.00017794902320432429,
-      "loss": 0.843,
-      "step": 1675
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 0.00017730829903995333,
-      "loss": 0.8424,
-      "step": 1700
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 0.00017665958793751006,
-      "loss": 0.8418,
-      "step": 1725
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 0.00017600295691716522,
-      "loss": 0.8384,
-      "step": 1750
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 0.00017533847381731856,
-      "loss": 0.8445,
-      "step": 1775
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.00017466620728759033,
-      "loss": 0.8446,
-      "step": 1800
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 0.00017398622678172878,
-      "loss": 0.838,
-      "step": 1825
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0001732986025504348,
-      "loss": 0.8415,
-      "step": 1850
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 0.000172603405634104,
-      "loss": 0.8357,
-      "step": 1875
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 0.00017190070785548755,
-      "loss": 0.8311,
-      "step": 1900
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 0.0001711905818122717,
-      "loss": 0.8333,
-      "step": 1925
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 0.0001704731008695777,
-      "loss": 0.8387,
-      "step": 1950
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 0.0001697483391523821,
-      "loss": 0.8442,
-      "step": 1975
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.00016901637153785885,
-      "loss": 0.8399,
-      "step": 2000
-    },
-    {
-      "epoch": 0.78,
-      "eval_loss": 0.8339959383010864,
-      "eval_runtime": 58.5829,
-      "eval_samples_per_second": 12.461,
-      "eval_steps_per_second": 0.905,
-      "step": 2000
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001682772736476434,
-      "loss": 0.8334,
-      "step": 2025
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001675311218400201,
-      "loss": 0.835,
-      "step": 2050
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.00016677799320203332,
-      "loss": 0.8368,
-      "step": 2075
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 0.00016601796554152344,
-      "loss": 0.8278,
-      "step": 2100
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 0.00016525111737908827,
-      "loss": 0.8334,
-      "step": 2125
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 0.00016447752793997096,
-      "loss": 0.8416,
-      "step": 2150
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.00016369727714587483,
-      "loss": 0.8297,
-      "step": 2175
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 0.0001629104456067066,
-      "loss": 0.8327,
-      "step": 2200
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.00016211711461224825,
-      "loss": 0.8324,
-      "step": 2225
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 0.0001613173661237589,
-      "loss": 0.8313,
-      "step": 2250
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 0.0001605112827655069,
-      "loss": 0.8292,
-      "step": 2275
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0001596989478162339,
-      "loss": 0.8334,
-      "step": 2300
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 0.00015888044520055106,
-      "loss": 0.8352,
-      "step": 2325
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.00015805585948026852,
-      "loss": 0.823,
-      "step": 2350
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 0.000157225275845659,
-      "loss": 0.8293,
-      "step": 2375
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 0.00015638878010665672,
-      "loss": 0.8289,
-      "step": 2400
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 0.00015554645868399205,
-      "loss": 0.832,
-      "step": 2425
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.00015469839860026308,
-      "loss": 0.8294,
-      "step": 2450
-    },
-    {
-      "epoch": 0.96,
-      "learning_rate": 0.0001538446874709452,
-      "loss": 0.8281,
-      "step": 2475
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 0.00015298541349533925,
-      "loss": 0.8314,
-      "step": 2500
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.00015212066544745926,
-      "loss": 0.831,
-      "step": 2525
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 0.00015125053266686124,
-      "loss": 0.8319,
-      "step": 2550
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 0.00015037510504941303,
-      "loss": 0.8259,
-      "step": 2575
-    },
-    {
-      "epoch": 1.01,
-      "learning_rate": 0.00014949447303800695,
-      "loss": 0.8133,
-      "step": 2600
-    },
-    {
-      "epoch": 1.02,
-      "learning_rate": 0.00014860872761321593,
-      "loss": 0.8139,
-      "step": 2625
-    },
-    {
-      "epoch": 1.03,
-      "learning_rate": 0.00014771796028389405,
-      "loss": 0.804,
-      "step": 2650
-    },
-    {
-      "epoch": 1.04,
-      "learning_rate": 0.0001468222630777225,
-      "loss": 0.8011,
-      "step": 2675
-    },
-    {
-      "epoch": 1.05,
-      "learning_rate": 0.00014592172853170193,
-      "loss": 0.8037,
-      "step": 2700
-    },
-    {
-      "epoch": 1.06,
-      "learning_rate": 0.00014501644968259212,
-      "loss": 0.8063,
-      "step": 2725
-    },
-    {
-      "epoch": 1.07,
-      "learning_rate": 0.00014410652005730025,
-      "loss": 0.8155,
-      "step": 2750
-    },
-    {
-      "epoch": 1.08,
-      "learning_rate": 0.00014319203366321826,
-      "loss": 0.8066,
-      "step": 2775
-    },
-    {
-      "epoch": 1.09,
-      "learning_rate": 0.0001422730849785107,
-      "loss": 0.8091,
-      "step": 2800
-    },
-    {
-      "epoch": 1.1,
-      "learning_rate": 0.0001413497689423539,
-      "loss": 0.8067,
-      "step": 2825
-    },
-    {
-      "epoch": 1.11,
-      "learning_rate": 0.00014042218094512755,
-      "loss": 0.8046,
-      "step": 2850
-    },
-    {
-      "epoch": 1.11,
-      "learning_rate": 0.00013949041681855985,
-      "loss": 0.8053,
-      "step": 2875
-    },
-    {
-      "epoch": 1.12,
-      "learning_rate": 0.0001385545728258264,
-      "loss": 0.8075,
-      "step": 2900
-    }
-  ],
-  "max_steps": 7737,
-  "num_train_epochs": 3,
-  "total_flos": 1.248869156726086e+19,
-  "trial_name": null,
-  "trial_params": null
-}
diff --git a/checkpoint-2900/training_args.bin b/checkpoint-2900/training_args.bin
deleted file mode 100644
index 89b6f6487f3e8cc200589fafc4378937a3fadf66..0000000000000000000000000000000000000000
--- a/checkpoint-2900/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7292138fecd854f5f17371c439bbd450ee3c48e738b75818b778a55f4e26ef57
-size 4027
diff --git a/checkpoint-3000/README.md b/checkpoint-3000/README.md
deleted file mode 100644
index f2208b0ded6c10ed47b2ea9df5ab7c8dd721a53c..0000000000000000000000000000000000000000
--- a/checkpoint-3000/README.md
+++ /dev/null
@@ -1,20 +0,0 @@
----
-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: bfloat16
-### Framework versions
-
-
-- PEFT 0.5.0.dev0
diff --git a/checkpoint-3000/adapter_config.json b/checkpoint-3000/adapter_config.json
deleted file mode 100644
index 6984f5fd4bab99ec956ebe3bf12d7b823649c936..0000000000000000000000000000000000000000
--- a/checkpoint-3000/adapter_config.json
+++ /dev/null
@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
-  "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": [
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}
\ No newline at end of file
diff --git a/checkpoint-3000/adapter_model.bin b/checkpoint-3000/adapter_model.bin
deleted file mode 100644
index f79a334e9a57ad38eb01a57c4bc21fe08f374f97..0000000000000000000000000000000000000000
--- a/checkpoint-3000/adapter_model.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3768dd1339753637e98fb5a78e49089bfc20cfbb2e5d5ab1d79b249f12bd91d6
-size 500897101
diff --git a/checkpoint-3000/adapter_model/README.md b/checkpoint-3000/adapter_model/README.md
deleted file mode 100644
index f2208b0ded6c10ed47b2ea9df5ab7c8dd721a53c..0000000000000000000000000000000000000000
--- a/checkpoint-3000/adapter_model/README.md
+++ /dev/null
@@ -1,20 +0,0 @@
----
-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: bfloat16
-### Framework versions
-
-
-- PEFT 0.5.0.dev0
diff --git a/checkpoint-3000/adapter_model/adapter_config.json b/checkpoint-3000/adapter_model/adapter_config.json
deleted file mode 100644
index 6984f5fd4bab99ec956ebe3bf12d7b823649c936..0000000000000000000000000000000000000000
--- a/checkpoint-3000/adapter_model/adapter_config.json
+++ /dev/null
@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
-  "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": [
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}
\ No newline at end of file
diff --git a/checkpoint-3000/adapter_model/adapter_model.bin b/checkpoint-3000/adapter_model/adapter_model.bin
deleted file mode 100644
index f79a334e9a57ad38eb01a57c4bc21fe08f374f97..0000000000000000000000000000000000000000
--- a/checkpoint-3000/adapter_model/adapter_model.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3768dd1339753637e98fb5a78e49089bfc20cfbb2e5d5ab1d79b249f12bd91d6
-size 500897101
diff --git a/checkpoint-3000/optimizer.pt b/checkpoint-3000/optimizer.pt
deleted file mode 100644
index fa6996cae1b0cc628c935b8728cbabaaa4546684..0000000000000000000000000000000000000000
--- a/checkpoint-3000/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:43dd2594437f90014ceb24dae35f0caf1408f106ca0640abfdb6f930ec7d1917
-size 1001752701
diff --git a/checkpoint-3000/rng_state_0.pth b/checkpoint-3000/rng_state_0.pth
deleted file mode 100644
index 510336d4202f191ba61185c520d4ae54884583ef..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_0.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:372977c5ad5707d01ab93c603a2084e21dcc5bbe3746e25cbd04e791984a40ad
-size 27772
diff --git a/checkpoint-3000/rng_state_1.pth b/checkpoint-3000/rng_state_1.pth
deleted file mode 100644
index d6060d886c1817a8864c1749c754d798213beeda..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_1.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0cf974f69d3a79d20401ab16c60981d40397dff4557e89f3fb4f166a1c2b6988
-size 27772
diff --git a/checkpoint-3000/rng_state_10.pth b/checkpoint-3000/rng_state_10.pth
deleted file mode 100644
index 3b8cd54c3b3fc41c81b070409c53ee1d226aa39b..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_10.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f46cf42d5b149dfdabbc17334f090d493267bd9a2a1e982e5a7904ba8ad96c66
-size 27789
diff --git a/checkpoint-3000/rng_state_11.pth b/checkpoint-3000/rng_state_11.pth
deleted file mode 100644
index 4fe7e9b680808b89e2beeb8d24b7d6a5c32d51c6..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_11.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0d782b19c86bb619094e572c4d5fa6b1b8aff8745fd27fd20d67ad46b26e3500
-size 27789
diff --git a/checkpoint-3000/rng_state_12.pth b/checkpoint-3000/rng_state_12.pth
deleted file mode 100644
index 7510083919a37c116ce27099ad5c4487a14c2db6..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_12.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:46ed59f9d93f80f01f93314ed6347cd1950aad081d7b1afa92318f622eae07dc
-size 27789
diff --git a/checkpoint-3000/rng_state_13.pth b/checkpoint-3000/rng_state_13.pth
deleted file mode 100644
index 93625cc9a2dcfa01a5cff10c787c1fd15facf191..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_13.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de734c628aa46f0b8f66418bc77802de4cf179c013f3fa6520a4c967c9c44ee9
-size 27789
diff --git a/checkpoint-3000/rng_state_2.pth b/checkpoint-3000/rng_state_2.pth
deleted file mode 100644
index f344946020efc1b17146971b1fb54e53df596e00..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_2.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8b3ee02de5d832b0550492ad9197099cc49a1ef39883f9f21d43ee5eb7abbe91
-size 27772
diff --git a/checkpoint-3000/rng_state_3.pth b/checkpoint-3000/rng_state_3.pth
deleted file mode 100644
index 1dcc4209ae1a2eda4450efbc9374dc11d689c520..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_3.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f47b89653cf7379ccd6b6642b1cb9305e7b0ff4639356066795aec75e109dcd0
-size 27772
diff --git a/checkpoint-3000/rng_state_4.pth b/checkpoint-3000/rng_state_4.pth
deleted file mode 100644
index 6cf6ec04a76e01315f6444460afbb6d4d77522ae..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_4.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:896ef18d13ff8a9f7f4850c38ec321a8050c0001f5f2abe7e1f217fabe5940c7
-size 27772
diff --git a/checkpoint-3000/rng_state_5.pth b/checkpoint-3000/rng_state_5.pth
deleted file mode 100644
index 4d5b3d0f734b63a8efb6f6966a3e8159c5e71b96..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_5.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f03081aff382542ac4332b7380a218da9fc6f3cc8c0e182a596a1aa05e2c4a86
-size 27772
diff --git a/checkpoint-3000/rng_state_6.pth b/checkpoint-3000/rng_state_6.pth
deleted file mode 100644
index 757389e834c2c8a7b9b4949aaf429905e9def0e3..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_6.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ba56e43a346f575d11975e33c17fd24d061dc495ff64f652662b4fe2bd5ba2a
-size 27772
diff --git a/checkpoint-3000/rng_state_7.pth b/checkpoint-3000/rng_state_7.pth
deleted file mode 100644
index dec1ed920426e60cae6d9c216b7956bbe8cb82e9..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_7.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cd77f76c2f0d692464a663d61dae016bcf5dd8966ed8742d59dea407d2a7048f
-size 27772
diff --git a/checkpoint-3000/rng_state_8.pth b/checkpoint-3000/rng_state_8.pth
deleted file mode 100644
index d975d181308b679a3d20c6691c8b8fcb8401ce51..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_8.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:20c5b17ace5a48bc38935d68f2ceef000b52c248bec852ba042e42f55d1fdcec
-size 27772
diff --git a/checkpoint-3000/rng_state_9.pth b/checkpoint-3000/rng_state_9.pth
deleted file mode 100644
index 3f72afd6b4b543c9eec9741b036191689e53f96e..0000000000000000000000000000000000000000
--- a/checkpoint-3000/rng_state_9.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2362bce85dfe8a924fd3e27761bcd0046ea4d1f8b878596ba3abccb85ffaaa3d
-size 27772
diff --git a/checkpoint-3000/scheduler.pt b/checkpoint-3000/scheduler.pt
deleted file mode 100644
index 9495f8c0328e5475cf01b45c659cb42f5e076afc..0000000000000000000000000000000000000000
--- a/checkpoint-3000/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f5eb3f4a2e8a234b77c028b4206015afec84f155c6d5bcb4ec7cd2c9f89b304b
-size 627
diff --git a/checkpoint-3000/trainer_state.json b/checkpoint-3000/trainer_state.json
deleted file mode 100644
index 14fcb7acf5d6d39c026f127a8eccfcc6afab2437..0000000000000000000000000000000000000000
--- a/checkpoint-3000/trainer_state.json
+++ /dev/null
@@ -1,736 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.1632415664986429,
-  "global_step": 3000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.02,
-      "learning_rate": 0.0001999867761371633,
-      "loss": 1.0435,
-      "step": 50
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 0.00019993306018843102,
-      "loss": 0.8918,
-      "step": 100
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 0.00019983804784290833,
-      "loss": 0.8874,
-      "step": 150
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 0.00019970177836355307,
-      "loss": 0.8839,
-      "step": 200
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 0.00019961818913082012,
-      "loss": 0.8801,
-      "step": 225
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 0.00019952430806244534,
-      "loss": 0.8753,
-      "step": 250
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 0.00019942014485754635,
-      "loss": 0.8754,
-      "step": 275
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 0.00019930571027751713,
-      "loss": 0.8751,
-      "step": 300
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 0.0001991810161449164,
-      "loss": 0.8819,
-      "step": 325
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 0.00019904607534224612,
-      "loss": 0.8744,
-      "step": 350
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 0.00019890090181062063,
-      "loss": 0.8735,
-      "step": 375
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019874551054832625,
-      "loss": 0.8703,
-      "step": 400
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019857991760927193,
-      "loss": 0.8715,
-      "step": 425
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 0.00019840414010133045,
-      "loss": 0.8714,
-      "step": 450
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 0.00019821819618457114,
-      "loss": 0.8653,
-      "step": 475
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 0.0001980221050693837,
-      "loss": 0.8716,
-      "step": 500
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 0.00019781588701449338,
-      "loss": 0.8695,
-      "step": 525
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 0.0001975995633248682,
-      "loss": 0.8746,
-      "step": 550
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 0.00019737315634951762,
-      "loss": 0.8731,
-      "step": 575
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 0.00019713668947918386,
-      "loss": 0.867,
-      "step": 600
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 0.0001968901871439252,
-      "loss": 0.8706,
-      "step": 625
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 0.000196633674810592,
-      "loss": 0.8595,
-      "step": 650
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 0.0001963671789801958,
-      "loss": 0.8627,
-      "step": 675
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 0.0001960907271851712,
-      "loss": 0.8607,
-      "step": 700
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 0.00019580434798653173,
-      "loss": 0.858,
-      "step": 725
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 0.00019550807097091876,
-      "loss": 0.8589,
-      "step": 750
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 0.00019520192674754515,
-      "loss": 0.8561,
-      "step": 775
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 0.00019488594694503264,
-      "loss": 0.8576,
-      "step": 800
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 0.00019456016420814446,
-      "loss": 0.8597,
-      "step": 825
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 0.00019422461219441254,
-      "loss": 0.862,
-      "step": 850
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 0.00019387932557066035,
-      "loss": 0.8577,
-      "step": 875
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 0.00019352434000942127,
-      "loss": 0.8632,
-      "step": 900
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 0.00019315969218525333,
-      "loss": 0.8567,
-      "step": 925
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 0.00019278541977095005,
-      "loss": 0.8501,
-      "step": 950
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 0.00019240156143364844,
-      "loss": 0.8596,
-      "step": 975
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 0.00019200815683083434,
-      "loss": 0.8556,
-      "step": 1000
-    },
-    {
-      "epoch": 0.39,
-      "eval_loss": 0.8521950244903564,
-      "eval_runtime": 59.8838,
-      "eval_samples_per_second": 12.19,
-      "eval_steps_per_second": 0.885,
-      "step": 1000
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 0.00019160524660624505,
-      "loss": 0.8531,
-      "step": 1025
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 0.00019119287238567045,
-      "loss": 0.8513,
-      "step": 1050
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 0.00019077107677265253,
-      "loss": 0.8502,
-      "step": 1075
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 0.00019033990334408384,
-      "loss": 0.8469,
-      "step": 1100
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 0.00018989939664570545,
-      "loss": 0.8495,
-      "step": 1125
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 0.00018944960218750484,
-      "loss": 0.8485,
-      "step": 1150
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 0.00018899056643901404,
-      "loss": 0.8534,
-      "step": 1175
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018852233682450893,
-      "loss": 0.8531,
-      "step": 1200
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018804496171810948,
-      "loss": 0.8509,
-      "step": 1225
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 0.00018755849043878222,
-      "loss": 0.8445,
-      "step": 1250
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 0.0001870629732452449,
-      "loss": 0.8548,
-      "step": 1275
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 0.00018655846133077417,
-      "loss": 0.8441,
-      "step": 1300
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 0.00018604500681791656,
-      "loss": 0.8533,
-      "step": 1325
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 0.00018552266275310373,
-      "loss": 0.8505,
-      "step": 1350
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 0.0001849914831011719,
-      "loss": 0.8544,
-      "step": 1375
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 0.00018445152273978668,
-      "loss": 0.845,
-      "step": 1400
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 0.00018390283745377354,
-      "loss": 0.8376,
-      "step": 1425
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 0.0001833454839293545,
-      "loss": 0.847,
-      "step": 1450
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 0.00018277951974829163,
-      "loss": 0.8473,
-      "step": 1475
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.0001822050033819382,
-      "loss": 0.8438,
-      "step": 1500
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 0.00018162199418519785,
-      "loss": 0.8418,
-      "step": 1525
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 0.00018103055239039243,
-      "loss": 0.842,
-      "step": 1550
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 0.0001804307391010393,
-      "loss": 0.8435,
-      "step": 1575
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 0.00017982261628553842,
-      "loss": 0.8349,
-      "step": 1600
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 0.0001792062467707703,
-      "loss": 0.8483,
-      "step": 1625
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 0.0001785816942356052,
-      "loss": 0.8387,
-      "step": 1650
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 0.00017794902320432429,
-      "loss": 0.843,
-      "step": 1675
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 0.00017730829903995333,
-      "loss": 0.8424,
-      "step": 1700
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 0.00017665958793751006,
-      "loss": 0.8418,
-      "step": 1725
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 0.00017600295691716522,
-      "loss": 0.8384,
-      "step": 1750
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 0.00017533847381731856,
-      "loss": 0.8445,
-      "step": 1775
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.00017466620728759033,
-      "loss": 0.8446,
-      "step": 1800
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 0.00017398622678172878,
-      "loss": 0.838,
-      "step": 1825
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0001732986025504348,
-      "loss": 0.8415,
-      "step": 1850
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 0.000172603405634104,
-      "loss": 0.8357,
-      "step": 1875
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 0.00017190070785548755,
-      "loss": 0.8311,
-      "step": 1900
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 0.0001711905818122717,
-      "loss": 0.8333,
-      "step": 1925
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 0.0001704731008695777,
-      "loss": 0.8387,
-      "step": 1950
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 0.0001697483391523821,
-      "loss": 0.8442,
-      "step": 1975
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.00016901637153785885,
-      "loss": 0.8399,
-      "step": 2000
-    },
-    {
-      "epoch": 0.78,
-      "eval_loss": 0.8339959383010864,
-      "eval_runtime": 58.5829,
-      "eval_samples_per_second": 12.461,
-      "eval_steps_per_second": 0.905,
-      "step": 2000
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001682772736476434,
-      "loss": 0.8334,
-      "step": 2025
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001675311218400201,
-      "loss": 0.835,
-      "step": 2050
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.00016677799320203332,
-      "loss": 0.8368,
-      "step": 2075
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 0.00016601796554152344,
-      "loss": 0.8278,
-      "step": 2100
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 0.00016525111737908827,
-      "loss": 0.8334,
-      "step": 2125
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 0.00016447752793997096,
-      "loss": 0.8416,
-      "step": 2150
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.00016369727714587483,
-      "loss": 0.8297,
-      "step": 2175
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 0.0001629104456067066,
-      "loss": 0.8327,
-      "step": 2200
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.00016211711461224825,
-      "loss": 0.8324,
-      "step": 2225
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 0.0001613173661237589,
-      "loss": 0.8313,
-      "step": 2250
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 0.0001605112827655069,
-      "loss": 0.8292,
-      "step": 2275
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0001596989478162339,
-      "loss": 0.8334,
-      "step": 2300
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 0.00015888044520055106,
-      "loss": 0.8352,
-      "step": 2325
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.00015805585948026852,
-      "loss": 0.823,
-      "step": 2350
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 0.000157225275845659,
-      "loss": 0.8293,
-      "step": 2375
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 0.00015638878010665672,
-      "loss": 0.8289,
-      "step": 2400
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 0.00015554645868399205,
-      "loss": 0.832,
-      "step": 2425
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.00015469839860026308,
-      "loss": 0.8294,
-      "step": 2450
-    },
-    {
-      "epoch": 0.96,
-      "learning_rate": 0.0001538446874709452,
-      "loss": 0.8281,
-      "step": 2475
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 0.00015298541349533925,
-      "loss": 0.8314,
-      "step": 2500
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.00015212066544745926,
-      "loss": 0.831,
-      "step": 2525
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 0.00015125053266686124,
-      "loss": 0.8319,
-      "step": 2550
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 0.00015037510504941303,
-      "loss": 0.8259,
-      "step": 2575
-    },
-    {
-      "epoch": 1.01,
-      "learning_rate": 0.00014949447303800695,
-      "loss": 0.8133,
-      "step": 2600
-    },
-    {
-      "epoch": 1.02,
-      "learning_rate": 0.00014860872761321593,
-      "loss": 0.8139,
-      "step": 2625
-    },
-    {
-      "epoch": 1.03,
-      "learning_rate": 0.00014771796028389405,
-      "loss": 0.804,
-      "step": 2650
-    },
-    {
-      "epoch": 1.04,
-      "learning_rate": 0.0001468222630777225,
-      "loss": 0.8011,
-      "step": 2675
-    },
-    {
-      "epoch": 1.05,
-      "learning_rate": 0.00014592172853170193,
-      "loss": 0.8037,
-      "step": 2700
-    },
-    {
-      "epoch": 1.06,
-      "learning_rate": 0.00014501644968259212,
-      "loss": 0.8063,
-      "step": 2725
-    },
-    {
-      "epoch": 1.07,
-      "learning_rate": 0.00014410652005730025,
-      "loss": 0.8155,
-      "step": 2750
-    },
-    {
-      "epoch": 1.08,
-      "learning_rate": 0.00014319203366321826,
-      "loss": 0.8066,
-      "step": 2775
-    },
-    {
-      "epoch": 1.09,
-      "learning_rate": 0.0001422730849785107,
-      "loss": 0.8091,
-      "step": 2800
-    },
-    {
-      "epoch": 1.1,
-      "learning_rate": 0.0001413497689423539,
-      "loss": 0.8067,
-      "step": 2825
-    },
-    {
-      "epoch": 1.11,
-      "learning_rate": 0.00014042218094512755,
-      "loss": 0.8046,
-      "step": 2850
-    },
-    {
-      "epoch": 1.11,
-      "learning_rate": 0.00013949041681855985,
-      "loss": 0.8053,
-      "step": 2875
-    },
-    {
-      "epoch": 1.12,
-      "learning_rate": 0.0001385545728258264,
-      "loss": 0.8075,
-      "step": 2900
-    },
-    {
-      "epoch": 1.13,
-      "learning_rate": 0.0001376147456516055,
-      "loss": 0.8015,
-      "step": 2925
-    },
-    {
-      "epoch": 1.14,
-      "learning_rate": 0.00013667103239208903,
-      "loss": 0.8016,
-      "step": 2950
-    },
-    {
-      "epoch": 1.15,
-      "learning_rate": 0.00013572353054495126,
-      "loss": 0.8029,
-      "step": 2975
-    },
-    {
-      "epoch": 1.16,
-      "learning_rate": 0.0001347723379992762,
-      "loss": 0.8017,
-      "step": 3000
-    },
-    {
-      "epoch": 1.16,
-      "eval_loss": 0.8229297995567322,
-      "eval_runtime": 59.3398,
-      "eval_samples_per_second": 12.302,
-      "eval_steps_per_second": 0.893,
-      "step": 3000
-    }
-  ],
-  "max_steps": 7737,
-  "num_train_epochs": 3,
-  "total_flos": 1.2918900565647294e+19,
-  "trial_name": null,
-  "trial_params": null
-}
diff --git a/checkpoint-3000/training_args.bin b/checkpoint-3000/training_args.bin
deleted file mode 100644
index 89b6f6487f3e8cc200589fafc4378937a3fadf66..0000000000000000000000000000000000000000
--- a/checkpoint-3000/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7292138fecd854f5f17371c439bbd450ee3c48e738b75818b778a55f4e26ef57
-size 4027
diff --git a/checkpoint-3100/README.md b/checkpoint-3100/README.md
deleted file mode 100644
index f2208b0ded6c10ed47b2ea9df5ab7c8dd721a53c..0000000000000000000000000000000000000000
--- a/checkpoint-3100/README.md
+++ /dev/null
@@ -1,20 +0,0 @@
----
-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: bfloat16
-### Framework versions
-
-
-- PEFT 0.5.0.dev0
diff --git a/checkpoint-3100/adapter_config.json b/checkpoint-3100/adapter_config.json
deleted file mode 100644
index 6984f5fd4bab99ec956ebe3bf12d7b823649c936..0000000000000000000000000000000000000000
--- a/checkpoint-3100/adapter_config.json
+++ /dev/null
@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
-  "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": [
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}
\ No newline at end of file
diff --git a/checkpoint-3100/adapter_model.bin b/checkpoint-3100/adapter_model.bin
deleted file mode 100644
index c15fa3db3fa10e4e183953719d7e0696bdb42120..0000000000000000000000000000000000000000
--- a/checkpoint-3100/adapter_model.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:604d08ed43fee049ea3799c6450a4a1d5f8cc6e58ddf33f377215e77f03ec769
-size 500897101
diff --git a/checkpoint-3100/adapter_model/README.md b/checkpoint-3100/adapter_model/README.md
deleted file mode 100644
index f2208b0ded6c10ed47b2ea9df5ab7c8dd721a53c..0000000000000000000000000000000000000000
--- a/checkpoint-3100/adapter_model/README.md
+++ /dev/null
@@ -1,20 +0,0 @@
----
-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: bfloat16
-### Framework versions
-
-
-- PEFT 0.5.0.dev0
diff --git a/checkpoint-3100/adapter_model/adapter_config.json b/checkpoint-3100/adapter_model/adapter_config.json
deleted file mode 100644
index 6984f5fd4bab99ec956ebe3bf12d7b823649c936..0000000000000000000000000000000000000000
--- a/checkpoint-3100/adapter_model/adapter_config.json
+++ /dev/null
@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
-  "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": [
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}
\ No newline at end of file
diff --git a/checkpoint-3100/adapter_model/adapter_model.bin b/checkpoint-3100/adapter_model/adapter_model.bin
deleted file mode 100644
index c15fa3db3fa10e4e183953719d7e0696bdb42120..0000000000000000000000000000000000000000
--- a/checkpoint-3100/adapter_model/adapter_model.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:604d08ed43fee049ea3799c6450a4a1d5f8cc6e58ddf33f377215e77f03ec769
-size 500897101
diff --git a/checkpoint-3100/optimizer.pt b/checkpoint-3100/optimizer.pt
deleted file mode 100644
index 2113c46d598579c16d2a4b5ecaa23eed143bd496..0000000000000000000000000000000000000000
--- a/checkpoint-3100/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:94469f937804d5ce0461fe1eb4aba770ee24539198898ed26597db99e8a9be8c
-size 1001752701
diff --git a/checkpoint-3100/rng_state_0.pth b/checkpoint-3100/rng_state_0.pth
deleted file mode 100644
index 8c701fecdc36714bdbd9809d3ecea407aab49e46..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_0.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cccffebda14d72607655c8cc414bc2d644ff4850957bc97842d7ad5b4e8a35c7
-size 27772
diff --git a/checkpoint-3100/rng_state_1.pth b/checkpoint-3100/rng_state_1.pth
deleted file mode 100644
index 7c229c02dec63bdc2e781dbd03d8fdfbda5c0bf9..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_1.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bf748078b6d64f54a4c82c901a07fa9a0b12ed31fbdb377aed3baece602b7886
-size 27772
diff --git a/checkpoint-3100/rng_state_10.pth b/checkpoint-3100/rng_state_10.pth
deleted file mode 100644
index 7010d794264a6f79b34c3d5f9960f5e60cd4dc62..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_10.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:98298c09628a5370836fdab430191117c3386c78337f9f2c62f101aa17d7e4f8
-size 27789
diff --git a/checkpoint-3100/rng_state_11.pth b/checkpoint-3100/rng_state_11.pth
deleted file mode 100644
index 69bf391e000763718374f273648faea4493154e2..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_11.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:68ae9f8a2401b67aa57f50c34841e07a3dc51f9b81e0436c33e2b67fe7c4baee
-size 27789
diff --git a/checkpoint-3100/rng_state_12.pth b/checkpoint-3100/rng_state_12.pth
deleted file mode 100644
index 38ecccc69861fd0c6e9e0892ce1c94f08e46c7ee..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_12.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:22848d56d849bc600e823fc9cfb270dd9494429c7f77cf79dbfbdf4a72efaba0
-size 27789
diff --git a/checkpoint-3100/rng_state_13.pth b/checkpoint-3100/rng_state_13.pth
deleted file mode 100644
index 60986aa8681df4bdf8579fd6208c5af5a417bdc7..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_13.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f3076b14a53ecb3520119317b5b2e50278e91bfa176e1f3b4d62a09a55b10c15
-size 27789
diff --git a/checkpoint-3100/rng_state_2.pth b/checkpoint-3100/rng_state_2.pth
deleted file mode 100644
index 60462776d902cf64a63733935612b4801f264554..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_2.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8502ae4ad065d02b5651b21e8f626b0f0ba70cb25fc8fff417ceacffff2c0af9
-size 27772
diff --git a/checkpoint-3100/rng_state_3.pth b/checkpoint-3100/rng_state_3.pth
deleted file mode 100644
index a819389f95a1df3ef7c9232918172c745277d8e2..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_3.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e560e73955af90e58da7fd5613f914bc880456d4e233dfb371f9de5f68da2f65
-size 27772
diff --git a/checkpoint-3100/rng_state_4.pth b/checkpoint-3100/rng_state_4.pth
deleted file mode 100644
index d622001df7cc09dd4608f228212d19f9dbbd48ac..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_4.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c1325c064dbe9b4b47234209edc5ce58860efd7b44e31e1e367cc65157805fb5
-size 27772
diff --git a/checkpoint-3100/rng_state_5.pth b/checkpoint-3100/rng_state_5.pth
deleted file mode 100644
index 96bff79b8a079f3b367eb6f8413531fb5bff0ecd..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_5.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dae1ede6bf5b2686c0a3e858c74f1ad7c53f73bff27db97fa9e477440f52c571
-size 27772
diff --git a/checkpoint-3100/rng_state_6.pth b/checkpoint-3100/rng_state_6.pth
deleted file mode 100644
index 0f377ee3865769ca7390e478c192919ac370e5d3..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_6.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:181f86e82ddf8a60f98f38e3eb3e9daea0f03767e98f46ac40b43f04100a7cc7
-size 27772
diff --git a/checkpoint-3100/rng_state_7.pth b/checkpoint-3100/rng_state_7.pth
deleted file mode 100644
index 2ecd97daa65fc10ea67f18705f827aa7c0168804..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_7.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6dba2bbc40ef363764a30227e3decb70eb10e50a3e97241431a928d011805fbe
-size 27772
diff --git a/checkpoint-3100/rng_state_8.pth b/checkpoint-3100/rng_state_8.pth
deleted file mode 100644
index 53a0bd7dabed2ef1ddcb2a4ea7869e6a28c93cb5..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_8.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d1bae03f64a7771751c64781fb44b1c9744351929cb10e9281c9f741f3eea0d3
-size 27772
diff --git a/checkpoint-3100/rng_state_9.pth b/checkpoint-3100/rng_state_9.pth
deleted file mode 100644
index 095f3cd91372639f120a8f39eaf40d3bc942a640..0000000000000000000000000000000000000000
--- a/checkpoint-3100/rng_state_9.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9135a97bdad98c9b172d205cb6e8826f379e19e767179271dbc08babc1c3dd01
-size 27772
diff --git a/checkpoint-3100/scheduler.pt b/checkpoint-3100/scheduler.pt
deleted file mode 100644
index a5454ac32b2919846d4817be960479ffed2e9e89..0000000000000000000000000000000000000000
--- a/checkpoint-3100/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d5a1153b6ecad2aef39ef54d264602f1ef058c1cd82ac7533e0298d295685be1
-size 627
diff --git a/checkpoint-3100/trainer_state.json b/checkpoint-3100/trainer_state.json
deleted file mode 100644
index ff116b5ea24bf2e784481775f4d5435463907505..0000000000000000000000000000000000000000
--- a/checkpoint-3100/trainer_state.json
+++ /dev/null
@@ -1,760 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.202016285381931,
-  "global_step": 3100,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.02,
-      "learning_rate": 0.0001999867761371633,
-      "loss": 1.0435,
-      "step": 50
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 0.00019993306018843102,
-      "loss": 0.8918,
-      "step": 100
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 0.00019983804784290833,
-      "loss": 0.8874,
-      "step": 150
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 0.00019970177836355307,
-      "loss": 0.8839,
-      "step": 200
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 0.00019961818913082012,
-      "loss": 0.8801,
-      "step": 225
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 0.00019952430806244534,
-      "loss": 0.8753,
-      "step": 250
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 0.00019942014485754635,
-      "loss": 0.8754,
-      "step": 275
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 0.00019930571027751713,
-      "loss": 0.8751,
-      "step": 300
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 0.0001991810161449164,
-      "loss": 0.8819,
-      "step": 325
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 0.00019904607534224612,
-      "loss": 0.8744,
-      "step": 350
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 0.00019890090181062063,
-      "loss": 0.8735,
-      "step": 375
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019874551054832625,
-      "loss": 0.8703,
-      "step": 400
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019857991760927193,
-      "loss": 0.8715,
-      "step": 425
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 0.00019840414010133045,
-      "loss": 0.8714,
-      "step": 450
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 0.00019821819618457114,
-      "loss": 0.8653,
-      "step": 475
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 0.0001980221050693837,
-      "loss": 0.8716,
-      "step": 500
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 0.00019781588701449338,
-      "loss": 0.8695,
-      "step": 525
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 0.0001975995633248682,
-      "loss": 0.8746,
-      "step": 550
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 0.00019737315634951762,
-      "loss": 0.8731,
-      "step": 575
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 0.00019713668947918386,
-      "loss": 0.867,
-      "step": 600
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 0.0001968901871439252,
-      "loss": 0.8706,
-      "step": 625
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 0.000196633674810592,
-      "loss": 0.8595,
-      "step": 650
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 0.0001963671789801958,
-      "loss": 0.8627,
-      "step": 675
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 0.0001960907271851712,
-      "loss": 0.8607,
-      "step": 700
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 0.00019580434798653173,
-      "loss": 0.858,
-      "step": 725
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 0.00019550807097091876,
-      "loss": 0.8589,
-      "step": 750
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 0.00019520192674754515,
-      "loss": 0.8561,
-      "step": 775
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 0.00019488594694503264,
-      "loss": 0.8576,
-      "step": 800
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 0.00019456016420814446,
-      "loss": 0.8597,
-      "step": 825
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 0.00019422461219441254,
-      "loss": 0.862,
-      "step": 850
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 0.00019387932557066035,
-      "loss": 0.8577,
-      "step": 875
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 0.00019352434000942127,
-      "loss": 0.8632,
-      "step": 900
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 0.00019315969218525333,
-      "loss": 0.8567,
-      "step": 925
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 0.00019278541977095005,
-      "loss": 0.8501,
-      "step": 950
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 0.00019240156143364844,
-      "loss": 0.8596,
-      "step": 975
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 0.00019200815683083434,
-      "loss": 0.8556,
-      "step": 1000
-    },
-    {
-      "epoch": 0.39,
-      "eval_loss": 0.8521950244903564,
-      "eval_runtime": 59.8838,
-      "eval_samples_per_second": 12.19,
-      "eval_steps_per_second": 0.885,
-      "step": 1000
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 0.00019160524660624505,
-      "loss": 0.8531,
-      "step": 1025
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 0.00019119287238567045,
-      "loss": 0.8513,
-      "step": 1050
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 0.00019077107677265253,
-      "loss": 0.8502,
-      "step": 1075
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 0.00019033990334408384,
-      "loss": 0.8469,
-      "step": 1100
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 0.00018989939664570545,
-      "loss": 0.8495,
-      "step": 1125
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 0.00018944960218750484,
-      "loss": 0.8485,
-      "step": 1150
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 0.00018899056643901404,
-      "loss": 0.8534,
-      "step": 1175
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018852233682450893,
-      "loss": 0.8531,
-      "step": 1200
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018804496171810948,
-      "loss": 0.8509,
-      "step": 1225
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 0.00018755849043878222,
-      "loss": 0.8445,
-      "step": 1250
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 0.0001870629732452449,
-      "loss": 0.8548,
-      "step": 1275
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 0.00018655846133077417,
-      "loss": 0.8441,
-      "step": 1300
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 0.00018604500681791656,
-      "loss": 0.8533,
-      "step": 1325
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 0.00018552266275310373,
-      "loss": 0.8505,
-      "step": 1350
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 0.0001849914831011719,
-      "loss": 0.8544,
-      "step": 1375
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 0.00018445152273978668,
-      "loss": 0.845,
-      "step": 1400
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 0.00018390283745377354,
-      "loss": 0.8376,
-      "step": 1425
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 0.0001833454839293545,
-      "loss": 0.847,
-      "step": 1450
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 0.00018277951974829163,
-      "loss": 0.8473,
-      "step": 1475
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.0001822050033819382,
-      "loss": 0.8438,
-      "step": 1500
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 0.00018162199418519785,
-      "loss": 0.8418,
-      "step": 1525
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 0.00018103055239039243,
-      "loss": 0.842,
-      "step": 1550
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 0.0001804307391010393,
-      "loss": 0.8435,
-      "step": 1575
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 0.00017982261628553842,
-      "loss": 0.8349,
-      "step": 1600
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 0.0001792062467707703,
-      "loss": 0.8483,
-      "step": 1625
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 0.0001785816942356052,
-      "loss": 0.8387,
-      "step": 1650
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 0.00017794902320432429,
-      "loss": 0.843,
-      "step": 1675
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 0.00017730829903995333,
-      "loss": 0.8424,
-      "step": 1700
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 0.00017665958793751006,
-      "loss": 0.8418,
-      "step": 1725
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 0.00017600295691716522,
-      "loss": 0.8384,
-      "step": 1750
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 0.00017533847381731856,
-      "loss": 0.8445,
-      "step": 1775
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.00017466620728759033,
-      "loss": 0.8446,
-      "step": 1800
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 0.00017398622678172878,
-      "loss": 0.838,
-      "step": 1825
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0001732986025504348,
-      "loss": 0.8415,
-      "step": 1850
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 0.000172603405634104,
-      "loss": 0.8357,
-      "step": 1875
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 0.00017190070785548755,
-      "loss": 0.8311,
-      "step": 1900
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 0.0001711905818122717,
-      "loss": 0.8333,
-      "step": 1925
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 0.0001704731008695777,
-      "loss": 0.8387,
-      "step": 1950
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 0.0001697483391523821,
-      "loss": 0.8442,
-      "step": 1975
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.00016901637153785885,
-      "loss": 0.8399,
-      "step": 2000
-    },
-    {
-      "epoch": 0.78,
-      "eval_loss": 0.8339959383010864,
-      "eval_runtime": 58.5829,
-      "eval_samples_per_second": 12.461,
-      "eval_steps_per_second": 0.905,
-      "step": 2000
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001682772736476434,
-      "loss": 0.8334,
-      "step": 2025
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001675311218400201,
-      "loss": 0.835,
-      "step": 2050
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.00016677799320203332,
-      "loss": 0.8368,
-      "step": 2075
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 0.00016601796554152344,
-      "loss": 0.8278,
-      "step": 2100
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 0.00016525111737908827,
-      "loss": 0.8334,
-      "step": 2125
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 0.00016447752793997096,
-      "loss": 0.8416,
-      "step": 2150
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.00016369727714587483,
-      "loss": 0.8297,
-      "step": 2175
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 0.0001629104456067066,
-      "loss": 0.8327,
-      "step": 2200
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.00016211711461224825,
-      "loss": 0.8324,
-      "step": 2225
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 0.0001613173661237589,
-      "loss": 0.8313,
-      "step": 2250
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 0.0001605112827655069,
-      "loss": 0.8292,
-      "step": 2275
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0001596989478162339,
-      "loss": 0.8334,
-      "step": 2300
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 0.00015888044520055106,
-      "loss": 0.8352,
-      "step": 2325
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.00015805585948026852,
-      "loss": 0.823,
-      "step": 2350
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 0.000157225275845659,
-      "loss": 0.8293,
-      "step": 2375
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 0.00015638878010665672,
-      "loss": 0.8289,
-      "step": 2400
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 0.00015554645868399205,
-      "loss": 0.832,
-      "step": 2425
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.00015469839860026308,
-      "loss": 0.8294,
-      "step": 2450
-    },
-    {
-      "epoch": 0.96,
-      "learning_rate": 0.0001538446874709452,
-      "loss": 0.8281,
-      "step": 2475
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 0.00015298541349533925,
-      "loss": 0.8314,
-      "step": 2500
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.00015212066544745926,
-      "loss": 0.831,
-      "step": 2525
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 0.00015125053266686124,
-      "loss": 0.8319,
-      "step": 2550
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 0.00015037510504941303,
-      "loss": 0.8259,
-      "step": 2575
-    },
-    {
-      "epoch": 1.01,
-      "learning_rate": 0.00014949447303800695,
-      "loss": 0.8133,
-      "step": 2600
-    },
-    {
-      "epoch": 1.02,
-      "learning_rate": 0.00014860872761321593,
-      "loss": 0.8139,
-      "step": 2625
-    },
-    {
-      "epoch": 1.03,
-      "learning_rate": 0.00014771796028389405,
-      "loss": 0.804,
-      "step": 2650
-    },
-    {
-      "epoch": 1.04,
-      "learning_rate": 0.0001468222630777225,
-      "loss": 0.8011,
-      "step": 2675
-    },
-    {
-      "epoch": 1.05,
-      "learning_rate": 0.00014592172853170193,
-      "loss": 0.8037,
-      "step": 2700
-    },
-    {
-      "epoch": 1.06,
-      "learning_rate": 0.00014501644968259212,
-      "loss": 0.8063,
-      "step": 2725
-    },
-    {
-      "epoch": 1.07,
-      "learning_rate": 0.00014410652005730025,
-      "loss": 0.8155,
-      "step": 2750
-    },
-    {
-      "epoch": 1.08,
-      "learning_rate": 0.00014319203366321826,
-      "loss": 0.8066,
-      "step": 2775
-    },
-    {
-      "epoch": 1.09,
-      "learning_rate": 0.0001422730849785107,
-      "loss": 0.8091,
-      "step": 2800
-    },
-    {
-      "epoch": 1.1,
-      "learning_rate": 0.0001413497689423539,
-      "loss": 0.8067,
-      "step": 2825
-    },
-    {
-      "epoch": 1.11,
-      "learning_rate": 0.00014042218094512755,
-      "loss": 0.8046,
-      "step": 2850
-    },
-    {
-      "epoch": 1.11,
-      "learning_rate": 0.00013949041681855985,
-      "loss": 0.8053,
-      "step": 2875
-    },
-    {
-      "epoch": 1.12,
-      "learning_rate": 0.0001385545728258264,
-      "loss": 0.8075,
-      "step": 2900
-    },
-    {
-      "epoch": 1.13,
-      "learning_rate": 0.0001376147456516055,
-      "loss": 0.8015,
-      "step": 2925
-    },
-    {
-      "epoch": 1.14,
-      "learning_rate": 0.00013667103239208903,
-      "loss": 0.8016,
-      "step": 2950
-    },
-    {
-      "epoch": 1.15,
-      "learning_rate": 0.00013572353054495126,
-      "loss": 0.8029,
-      "step": 2975
-    },
-    {
-      "epoch": 1.16,
-      "learning_rate": 0.0001347723379992762,
-      "loss": 0.8017,
-      "step": 3000
-    },
-    {
-      "epoch": 1.16,
-      "eval_loss": 0.8229297995567322,
-      "eval_runtime": 59.3398,
-      "eval_samples_per_second": 12.302,
-      "eval_steps_per_second": 0.893,
-      "step": 3000
-    },
-    {
-      "epoch": 1.17,
-      "learning_rate": 0.0001338175530254443,
-      "loss": 0.8049,
-      "step": 3025
-    },
-    {
-      "epoch": 1.18,
-      "learning_rate": 0.00013285927426497985,
-      "loss": 0.8027,
-      "step": 3050
-    },
-    {
-      "epoch": 1.19,
-      "learning_rate": 0.00013189760072036008,
-      "loss": 0.8028,
-      "step": 3075
-    },
-    {
-      "epoch": 1.2,
-      "learning_rate": 0.0001309326317447869,
-      "loss": 0.8021,
-      "step": 3100
-    }
-  ],
-  "max_steps": 7737,
-  "num_train_epochs": 3,
-  "total_flos": 1.3349988348702228e+19,
-  "trial_name": null,
-  "trial_params": null
-}
diff --git a/checkpoint-3100/training_args.bin b/checkpoint-3100/training_args.bin
deleted file mode 100644
index 89b6f6487f3e8cc200589fafc4378937a3fadf66..0000000000000000000000000000000000000000
--- a/checkpoint-3100/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7292138fecd854f5f17371c439bbd450ee3c48e738b75818b778a55f4e26ef57
-size 4027
diff --git a/checkpoint-3200/README.md b/checkpoint-3200/README.md
deleted file mode 100644
index f2208b0ded6c10ed47b2ea9df5ab7c8dd721a53c..0000000000000000000000000000000000000000
--- a/checkpoint-3200/README.md
+++ /dev/null
@@ -1,20 +0,0 @@
----
-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: bfloat16
-### Framework versions
-
-
-- PEFT 0.5.0.dev0
diff --git a/checkpoint-3200/adapter_config.json b/checkpoint-3200/adapter_config.json
deleted file mode 100644
index 6984f5fd4bab99ec956ebe3bf12d7b823649c936..0000000000000000000000000000000000000000
--- a/checkpoint-3200/adapter_config.json
+++ /dev/null
@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
-  "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": [
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}
\ No newline at end of file
diff --git a/checkpoint-3200/adapter_model.bin b/checkpoint-3200/adapter_model.bin
deleted file mode 100644
index 9983417f84d25dbcb0ce2f5f4845d2e07f37baac..0000000000000000000000000000000000000000
--- a/checkpoint-3200/adapter_model.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:db5a92be0cd5f8b38b328e0f82e62452a3fa7b5052a0a1f93fd8c4b1dd18b7a7
-size 500897101
diff --git a/checkpoint-3200/optimizer.pt b/checkpoint-3200/optimizer.pt
deleted file mode 100644
index 226452e1d09e64d212b48ac55c6172578c2af053..0000000000000000000000000000000000000000
--- a/checkpoint-3200/optimizer.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:734792a711547c325f20f564fba3fc1dafb5a5e2eb00a8e88a628060b50ad4e0
-size 1001752701
diff --git a/checkpoint-3200/rng_state_0.pth b/checkpoint-3200/rng_state_0.pth
deleted file mode 100644
index f1227112a055b9edb5eeb329533f5aed76e67d80..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_0.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:47493f691983492eb548e89c4bc00a908f9336311a3cdb9b6d4d0436862a7afe
-size 27772
diff --git a/checkpoint-3200/rng_state_1.pth b/checkpoint-3200/rng_state_1.pth
deleted file mode 100644
index 634b8df2811de99580c787bd77a406df7d6a5509..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_1.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7fd2d4258cdbe26a4276e6adf71ed40f5fb449eeb7efadbcb60ee6c3eb243b4a
-size 27772
diff --git a/checkpoint-3200/rng_state_10.pth b/checkpoint-3200/rng_state_10.pth
deleted file mode 100644
index 67bbbcdf71e1616cf3652e62ce0bf9646740465b..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_10.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a1a66a04d36cd4ced3163ee7de7c3f532444837ca748b2c7402468c7cf9ac0cc
-size 27789
diff --git a/checkpoint-3200/rng_state_11.pth b/checkpoint-3200/rng_state_11.pth
deleted file mode 100644
index b3a1d0f07d52d1e00fc37067477a0fded1f4137e..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_11.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6fd816f782b7158df45bbb3a0847b7e567cbc8246b73c484a51cea72f837a615
-size 27789
diff --git a/checkpoint-3200/rng_state_12.pth b/checkpoint-3200/rng_state_12.pth
deleted file mode 100644
index fc0ca9f711bacbbbae129702028db9b98da142de..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_12.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a5c0e7d21944297ce2889bf41e83eaf69e29b09934c6e5396b81f21c8d554008
-size 27789
diff --git a/checkpoint-3200/rng_state_13.pth b/checkpoint-3200/rng_state_13.pth
deleted file mode 100644
index c2edd1b9466db9c5e305a5e0456176a22be139ce..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_13.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a4a856ae9cc1a21a8770367e26ba40b6eb42e788a7f1046e05e030a2571733a3
-size 27789
diff --git a/checkpoint-3200/rng_state_2.pth b/checkpoint-3200/rng_state_2.pth
deleted file mode 100644
index 3adb767352c06c044f2f114dd6c52eb83db232f3..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_2.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:21fe838aa7244c39844b0cc17fda41f0bf30a92e8c365cbf60e9909dc9539b7a
-size 27772
diff --git a/checkpoint-3200/rng_state_3.pth b/checkpoint-3200/rng_state_3.pth
deleted file mode 100644
index ad285df37a770b7a13cd51599d010197b3fb9772..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_3.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c73d64b42d450cb0cd9d780bb5d76b4532c040febbd3e57c1a7e507f307c6919
-size 27772
diff --git a/checkpoint-3200/rng_state_4.pth b/checkpoint-3200/rng_state_4.pth
deleted file mode 100644
index 1ffcead5c4feafbc420a89b58372a0c00df964d5..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_4.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dd75d438f8c213a76df48ea475d4e8d725ef60a192611b3a3b5156b54d9bd3aa
-size 27772
diff --git a/checkpoint-3200/rng_state_5.pth b/checkpoint-3200/rng_state_5.pth
deleted file mode 100644
index 57c81481a57ac9811e8813fdfcf9f35248637e65..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_5.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a92b4282b70600e8661d984a46aae33c95db7e5a45a98aa75d1ab7fe809f0e87
-size 27772
diff --git a/checkpoint-3200/rng_state_6.pth b/checkpoint-3200/rng_state_6.pth
deleted file mode 100644
index 3dbeee076e2fd6d7449c24e95f3c71a242fe4aa5..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_6.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:60a6277ffeade78c02a3c80e695be2609d9c03891fa74c239da9236a5d8a411f
-size 27772
diff --git a/checkpoint-3200/rng_state_7.pth b/checkpoint-3200/rng_state_7.pth
deleted file mode 100644
index 6902be9c4287b3c7d011a62201d86ca18cb84de8..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_7.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:04ceb85b25ddf1ff875502c31946bedfdea45ff9b753957a01149a9fc85fe4aa
-size 27772
diff --git a/checkpoint-3200/rng_state_8.pth b/checkpoint-3200/rng_state_8.pth
deleted file mode 100644
index a3f4fa192010aaaaba4e5c479c145ece5ec0d660..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_8.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7647a4e90848b95f8b12db8456e13797e34b5cb91f94f229dfe860ef88396c11
-size 27772
diff --git a/checkpoint-3200/rng_state_9.pth b/checkpoint-3200/rng_state_9.pth
deleted file mode 100644
index 119154421bf9b73bef8d5b5ac45cc6432215fa7d..0000000000000000000000000000000000000000
--- a/checkpoint-3200/rng_state_9.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f4297218a6c8fddf475d7093a33dde8e1024bb348b2eacb353ad76d4cb02c652
-size 27772
diff --git a/checkpoint-3200/scheduler.pt b/checkpoint-3200/scheduler.pt
deleted file mode 100644
index 7bff1a8e664b7b0d992cbf63b72d3c26a103d7f8..0000000000000000000000000000000000000000
--- a/checkpoint-3200/scheduler.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c684e0d6e24a062502c981434add298c33b176147f87f977608afcf00cc005c3
-size 627
diff --git a/checkpoint-3200/trainer_state.json b/checkpoint-3200/trainer_state.json
deleted file mode 100644
index bd1f8246bdf2d7cc608063f44e0a61d07ba85f46..0000000000000000000000000000000000000000
--- a/checkpoint-3200/trainer_state.json
+++ /dev/null
@@ -1,784 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.240791004265219,
-  "global_step": 3200,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.02,
-      "learning_rate": 0.0001999867761371633,
-      "loss": 1.0435,
-      "step": 50
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 0.00019993306018843102,
-      "loss": 0.8918,
-      "step": 100
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 0.00019983804784290833,
-      "loss": 0.8874,
-      "step": 150
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 0.00019970177836355307,
-      "loss": 0.8839,
-      "step": 200
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 0.00019961818913082012,
-      "loss": 0.8801,
-      "step": 225
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 0.00019952430806244534,
-      "loss": 0.8753,
-      "step": 250
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 0.00019942014485754635,
-      "loss": 0.8754,
-      "step": 275
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 0.00019930571027751713,
-      "loss": 0.8751,
-      "step": 300
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 0.0001991810161449164,
-      "loss": 0.8819,
-      "step": 325
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 0.00019904607534224612,
-      "loss": 0.8744,
-      "step": 350
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 0.00019890090181062063,
-      "loss": 0.8735,
-      "step": 375
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019874551054832625,
-      "loss": 0.8703,
-      "step": 400
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019857991760927193,
-      "loss": 0.8715,
-      "step": 425
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 0.00019840414010133045,
-      "loss": 0.8714,
-      "step": 450
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 0.00019821819618457114,
-      "loss": 0.8653,
-      "step": 475
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 0.0001980221050693837,
-      "loss": 0.8716,
-      "step": 500
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 0.00019781588701449338,
-      "loss": 0.8695,
-      "step": 525
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 0.0001975995633248682,
-      "loss": 0.8746,
-      "step": 550
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 0.00019737315634951762,
-      "loss": 0.8731,
-      "step": 575
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 0.00019713668947918386,
-      "loss": 0.867,
-      "step": 600
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 0.0001968901871439252,
-      "loss": 0.8706,
-      "step": 625
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 0.000196633674810592,
-      "loss": 0.8595,
-      "step": 650
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 0.0001963671789801958,
-      "loss": 0.8627,
-      "step": 675
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 0.0001960907271851712,
-      "loss": 0.8607,
-      "step": 700
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 0.00019580434798653173,
-      "loss": 0.858,
-      "step": 725
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 0.00019550807097091876,
-      "loss": 0.8589,
-      "step": 750
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 0.00019520192674754515,
-      "loss": 0.8561,
-      "step": 775
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 0.00019488594694503264,
-      "loss": 0.8576,
-      "step": 800
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 0.00019456016420814446,
-      "loss": 0.8597,
-      "step": 825
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 0.00019422461219441254,
-      "loss": 0.862,
-      "step": 850
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 0.00019387932557066035,
-      "loss": 0.8577,
-      "step": 875
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 0.00019352434000942127,
-      "loss": 0.8632,
-      "step": 900
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 0.00019315969218525333,
-      "loss": 0.8567,
-      "step": 925
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 0.00019278541977095005,
-      "loss": 0.8501,
-      "step": 950
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 0.00019240156143364844,
-      "loss": 0.8596,
-      "step": 975
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 0.00019200815683083434,
-      "loss": 0.8556,
-      "step": 1000
-    },
-    {
-      "epoch": 0.39,
-      "eval_loss": 0.8521950244903564,
-      "eval_runtime": 59.8838,
-      "eval_samples_per_second": 12.19,
-      "eval_steps_per_second": 0.885,
-      "step": 1000
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 0.00019160524660624505,
-      "loss": 0.8531,
-      "step": 1025
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 0.00019119287238567045,
-      "loss": 0.8513,
-      "step": 1050
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 0.00019077107677265253,
-      "loss": 0.8502,
-      "step": 1075
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 0.00019033990334408384,
-      "loss": 0.8469,
-      "step": 1100
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 0.00018989939664570545,
-      "loss": 0.8495,
-      "step": 1125
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 0.00018944960218750484,
-      "loss": 0.8485,
-      "step": 1150
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 0.00018899056643901404,
-      "loss": 0.8534,
-      "step": 1175
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018852233682450893,
-      "loss": 0.8531,
-      "step": 1200
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018804496171810948,
-      "loss": 0.8509,
-      "step": 1225
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 0.00018755849043878222,
-      "loss": 0.8445,
-      "step": 1250
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 0.0001870629732452449,
-      "loss": 0.8548,
-      "step": 1275
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 0.00018655846133077417,
-      "loss": 0.8441,
-      "step": 1300
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 0.00018604500681791656,
-      "loss": 0.8533,
-      "step": 1325
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 0.00018552266275310373,
-      "loss": 0.8505,
-      "step": 1350
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 0.0001849914831011719,
-      "loss": 0.8544,
-      "step": 1375
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 0.00018445152273978668,
-      "loss": 0.845,
-      "step": 1400
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 0.00018390283745377354,
-      "loss": 0.8376,
-      "step": 1425
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 0.0001833454839293545,
-      "loss": 0.847,
-      "step": 1450
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 0.00018277951974829163,
-      "loss": 0.8473,
-      "step": 1475
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.0001822050033819382,
-      "loss": 0.8438,
-      "step": 1500
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 0.00018162199418519785,
-      "loss": 0.8418,
-      "step": 1525
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 0.00018103055239039243,
-      "loss": 0.842,
-      "step": 1550
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 0.0001804307391010393,
-      "loss": 0.8435,
-      "step": 1575
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 0.00017982261628553842,
-      "loss": 0.8349,
-      "step": 1600
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 0.0001792062467707703,
-      "loss": 0.8483,
-      "step": 1625
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 0.0001785816942356052,
-      "loss": 0.8387,
-      "step": 1650
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 0.00017794902320432429,
-      "loss": 0.843,
-      "step": 1675
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 0.00017730829903995333,
-      "loss": 0.8424,
-      "step": 1700
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 0.00017665958793751006,
-      "loss": 0.8418,
-      "step": 1725
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 0.00017600295691716522,
-      "loss": 0.8384,
-      "step": 1750
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 0.00017533847381731856,
-      "loss": 0.8445,
-      "step": 1775
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.00017466620728759033,
-      "loss": 0.8446,
-      "step": 1800
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 0.00017398622678172878,
-      "loss": 0.838,
-      "step": 1825
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0001732986025504348,
-      "loss": 0.8415,
-      "step": 1850
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 0.000172603405634104,
-      "loss": 0.8357,
-      "step": 1875
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 0.00017190070785548755,
-      "loss": 0.8311,
-      "step": 1900
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 0.0001711905818122717,
-      "loss": 0.8333,
-      "step": 1925
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 0.0001704731008695777,
-      "loss": 0.8387,
-      "step": 1950
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 0.0001697483391523821,
-      "loss": 0.8442,
-      "step": 1975
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.00016901637153785885,
-      "loss": 0.8399,
-      "step": 2000
-    },
-    {
-      "epoch": 0.78,
-      "eval_loss": 0.8339959383010864,
-      "eval_runtime": 58.5829,
-      "eval_samples_per_second": 12.461,
-      "eval_steps_per_second": 0.905,
-      "step": 2000
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001682772736476434,
-      "loss": 0.8334,
-      "step": 2025
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001675311218400201,
-      "loss": 0.835,
-      "step": 2050
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.00016677799320203332,
-      "loss": 0.8368,
-      "step": 2075
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 0.00016601796554152344,
-      "loss": 0.8278,
-      "step": 2100
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 0.00016525111737908827,
-      "loss": 0.8334,
-      "step": 2125
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 0.00016447752793997096,
-      "loss": 0.8416,
-      "step": 2150
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.00016369727714587483,
-      "loss": 0.8297,
-      "step": 2175
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 0.0001629104456067066,
-      "loss": 0.8327,
-      "step": 2200
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.00016211711461224825,
-      "loss": 0.8324,
-      "step": 2225
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 0.0001613173661237589,
-      "loss": 0.8313,
-      "step": 2250
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 0.0001605112827655069,
-      "loss": 0.8292,
-      "step": 2275
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0001596989478162339,
-      "loss": 0.8334,
-      "step": 2300
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 0.00015888044520055106,
-      "loss": 0.8352,
-      "step": 2325
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.00015805585948026852,
-      "loss": 0.823,
-      "step": 2350
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 0.000157225275845659,
-      "loss": 0.8293,
-      "step": 2375
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 0.00015638878010665672,
-      "loss": 0.8289,
-      "step": 2400
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 0.00015554645868399205,
-      "loss": 0.832,
-      "step": 2425
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.00015469839860026308,
-      "loss": 0.8294,
-      "step": 2450
-    },
-    {
-      "epoch": 0.96,
-      "learning_rate": 0.0001538446874709452,
-      "loss": 0.8281,
-      "step": 2475
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 0.00015298541349533925,
-      "loss": 0.8314,
-      "step": 2500
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.00015212066544745926,
-      "loss": 0.831,
-      "step": 2525
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 0.00015125053266686124,
-      "loss": 0.8319,
-      "step": 2550
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 0.00015037510504941303,
-      "loss": 0.8259,
-      "step": 2575
-    },
-    {
-      "epoch": 1.01,
-      "learning_rate": 0.00014949447303800695,
-      "loss": 0.8133,
-      "step": 2600
-    },
-    {
-      "epoch": 1.02,
-      "learning_rate": 0.00014860872761321593,
-      "loss": 0.8139,
-      "step": 2625
-    },
-    {
-      "epoch": 1.03,
-      "learning_rate": 0.00014771796028389405,
-      "loss": 0.804,
-      "step": 2650
-    },
-    {
-      "epoch": 1.04,
-      "learning_rate": 0.0001468222630777225,
-      "loss": 0.8011,
-      "step": 2675
-    },
-    {
-      "epoch": 1.05,
-      "learning_rate": 0.00014592172853170193,
-      "loss": 0.8037,
-      "step": 2700
-    },
-    {
-      "epoch": 1.06,
-      "learning_rate": 0.00014501644968259212,
-      "loss": 0.8063,
-      "step": 2725
-    },
-    {
-      "epoch": 1.07,
-      "learning_rate": 0.00014410652005730025,
-      "loss": 0.8155,
-      "step": 2750
-    },
-    {
-      "epoch": 1.08,
-      "learning_rate": 0.00014319203366321826,
-      "loss": 0.8066,
-      "step": 2775
-    },
-    {
-      "epoch": 1.09,
-      "learning_rate": 0.0001422730849785107,
-      "loss": 0.8091,
-      "step": 2800
-    },
-    {
-      "epoch": 1.1,
-      "learning_rate": 0.0001413497689423539,
-      "loss": 0.8067,
-      "step": 2825
-    },
-    {
-      "epoch": 1.11,
-      "learning_rate": 0.00014042218094512755,
-      "loss": 0.8046,
-      "step": 2850
-    },
-    {
-      "epoch": 1.11,
-      "learning_rate": 0.00013949041681855985,
-      "loss": 0.8053,
-      "step": 2875
-    },
-    {
-      "epoch": 1.12,
-      "learning_rate": 0.0001385545728258264,
-      "loss": 0.8075,
-      "step": 2900
-    },
-    {
-      "epoch": 1.13,
-      "learning_rate": 0.0001376147456516055,
-      "loss": 0.8015,
-      "step": 2925
-    },
-    {
-      "epoch": 1.14,
-      "learning_rate": 0.00013667103239208903,
-      "loss": 0.8016,
-      "step": 2950
-    },
-    {
-      "epoch": 1.15,
-      "learning_rate": 0.00013572353054495126,
-      "loss": 0.8029,
-      "step": 2975
-    },
-    {
-      "epoch": 1.16,
-      "learning_rate": 0.0001347723379992762,
-      "loss": 0.8017,
-      "step": 3000
-    },
-    {
-      "epoch": 1.16,
-      "eval_loss": 0.8229297995567322,
-      "eval_runtime": 59.3398,
-      "eval_samples_per_second": 12.302,
-      "eval_steps_per_second": 0.893,
-      "step": 3000
-    },
-    {
-      "epoch": 1.17,
-      "learning_rate": 0.0001338175530254443,
-      "loss": 0.8049,
-      "step": 3025
-    },
-    {
-      "epoch": 1.18,
-      "learning_rate": 0.00013285927426497985,
-      "loss": 0.8027,
-      "step": 3050
-    },
-    {
-      "epoch": 1.19,
-      "learning_rate": 0.00013189760072036008,
-      "loss": 0.8028,
-      "step": 3075
-    },
-    {
-      "epoch": 1.2,
-      "learning_rate": 0.0001309326317447869,
-      "loss": 0.8021,
-      "step": 3100
-    },
-    {
-      "epoch": 1.21,
-      "learning_rate": 0.00012996446703192257,
-      "loss": 0.8033,
-      "step": 3125
-    },
-    {
-      "epoch": 1.22,
-      "learning_rate": 0.00012899320660558986,
-      "loss": 0.8016,
-      "step": 3150
-    },
-    {
-      "epoch": 1.23,
-      "learning_rate": 0.00012801895080943846,
-      "loss": 0.7995,
-      "step": 3175
-    },
-    {
-      "epoch": 1.24,
-      "learning_rate": 0.0001270418002965782,
-      "loss": 0.799,
-      "step": 3200
-    }
-  ],
-  "max_steps": 7737,
-  "num_train_epochs": 3,
-  "total_flos": 1.3780535807691457e+19,
-  "trial_name": null,
-  "trial_params": null
-}
diff --git a/checkpoint-3200/training_args.bin b/checkpoint-3200/training_args.bin
deleted file mode 100644
index 89b6f6487f3e8cc200589fafc4378937a3fadf66..0000000000000000000000000000000000000000
--- a/checkpoint-3200/training_args.bin
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7292138fecd854f5f17371c439bbd450ee3c48e738b75818b778a55f4e26ef57
-size 4027
diff --git a/training_args.bin b/training_args.bin
index 89b6f6487f3e8cc200589fafc4378937a3fadf66..fb0f561b69fb593b0412efd616e76bb2ca52ed7b 100644
--- a/training_args.bin
+++ b/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7292138fecd854f5f17371c439bbd450ee3c48e738b75818b778a55f4e26ef57
+oid sha256:4458bf553277b063d908ed9668b95abc04892c52d8d793f6b007433394d06f17
 size 4027