add weights

README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b93f8b5bf9d5ad5daa6fb35494a535ada9f8370a39766fc243709362f04d76a
+size 16821197

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.3478317604566875,
+    "train_runtime": 4641.6132,
+    "train_samples_per_second": 13.114,
+    "train_steps_per_second": 0.102
+}

checkpoint-100/README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.4.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-100/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0354676fc0412b2797e2f90d88174804a8c2f0f6c6887a92b0311013533082
+size 16821197

checkpoint-100/finetuning_args.json

@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9fa05b8eb370479a3502e3e9a63152954d7417b77da798fb18905d3fe51b528
+size 33661637

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685ab4b3038810680f88b1d59df769ea68e7d862434955abae0ca497f13e8afe
+size 18679

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87cf45370820610b9f28e800b706764c94c0ff8527bf390c3c5f9fff93afde7e
+size 18679

checkpoint-100/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ebf9800688c38adccc12fa6858378c50e1f7d26a2e5570e8b7e04dff1e70262
+size 18679

checkpoint-100/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2bb7e4e4e8915c52d5b3b47831e6e2e038319baed3305fb634f6fab3b999133
+size 18679

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208fa747ba957a9f6589a9eb1cf3905edf393236e5e918f882719b448f1edfab
+size 627

checkpoint-100/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.21019442984760903,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994534068046937e-05,
+      "loss": 1.8599,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 1.6162,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.965903258506806e-05,
+      "loss": 1.5187,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.95415555523494e-05,
+      "loss": 1.4685,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.929469844930753e-05,
+      "loss": 1.3233,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.885188413200075e-05,
+      "loss": 1.1081,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.830477159419966e-05,
+      "loss": 0.9364,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7655753219826114e-05,
+      "loss": 0.7434,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.5053,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.6063784128704367e-05,
+      "loss": 0.2824,
+      "step": 100
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 1.906252514852864e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0474fbb331a6a8df843475fa87e752177bc451d593d9d453141d5ff0e7d077c9
+size 3230

checkpoint-200/README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.4.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-200/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9589e68864de41dda9c6565f54ffba12fb3e507b01057735af691bd61816d7e9
+size 16821197

checkpoint-200/finetuning_args.json

@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689530c5ed411fab4750761eba5dc1d9ece79c8c9ee5ab1cb62763a15c6460a7
+size 33661637

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ec3a97f0cae79cfabb9169aa5be59177f8e0bfe81f0e4c20223ae5b71d130f
+size 18679

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4add78733002391aed792a12c30bd240f199d144e8cf68bb14a04f4616cb1c
+size 18679

checkpoint-200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9349eae2e3e94545c210ae5d4b2a31c0da779a93963c62394c9a3627d608d546
+size 18679

checkpoint-200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac5028c8e4f410f0ef77e3417211d34afd069e3195852c295664fb9ab37a77f
+size 18679

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5f015cad4cd83d66afff7dcd01e4844b2647942ed23ffebf4a1059172aed00
+size 627

checkpoint-200/trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.42038885969521805,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994534068046937e-05,
+      "loss": 1.8599,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 1.6162,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.965903258506806e-05,
+      "loss": 1.5187,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.95415555523494e-05,
+      "loss": 1.4685,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.929469844930753e-05,
+      "loss": 1.3233,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.885188413200075e-05,
+      "loss": 1.1081,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.830477159419966e-05,
+      "loss": 0.9364,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7655753219826114e-05,
+      "loss": 0.7434,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.5053,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.6063784128704367e-05,
+      "loss": 0.2824,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.512779468773494e-05,
+      "loss": 0.1312,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.4103791521862784e-05,
+      "loss": 0.0681,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.2996252336387414e-05,
+      "loss": 0.0496,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.181002011836737e-05,
+      "loss": 0.0482,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.0550281959470023e-05,
+      "loss": 0.0497,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.9222546374139533e-05,
+      "loss": 0.0523,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.783261921226479e-05,
+      "loss": 0.0561,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.6386578271674984e-05,
+      "loss": 0.0606,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.489074672147621e-05,
+      "loss": 0.0664,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.335166545244178e-05,
+      "loss": 0.0742,
+      "step": 200
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 3.8128239525022925e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0474fbb331a6a8df843475fa87e752177bc451d593d9d453141d5ff0e7d077c9
+size 3230

checkpoint-300/README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.4.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-300/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ffe75cda42fc1f1bf8f72a47ff9c7c2eeab14b9cd3987fa6b00c4f75cf623fd
+size 16821197

checkpoint-300/finetuning_args.json

@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7bf627d9efb82fc4d96784a0bcb7e8a249b9e768b2678c9aaec52021a38cec
+size 33661637

checkpoint-300/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c89e638ed7375ec974a55e3a3c91729e83049337874afec1eb571fdf63379cf
+size 18679

checkpoint-300/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee0899f0aa87a4b654957c6791a8ce0592556287ba9a873cd50e551c39e9322
+size 18679

checkpoint-300/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903e65ab7c1af4e8289a7598d59aea37a64efca8f1f755fb387a7ee8a9f632c5
+size 18679

checkpoint-300/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76da0096c2fae55285370594561055d0b90a35ef08c5fdb801ca5eb7bce8ec2
+size 18679

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3a63edbf6cbe2235680152d6107703acd3337683d4cbf948f62e2c6452d486
+size 627

checkpoint-300/trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6305832895428272,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994534068046937e-05,
+      "loss": 1.8599,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 1.6162,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.965903258506806e-05,
+      "loss": 1.5187,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.95415555523494e-05,
+      "loss": 1.4685,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.929469844930753e-05,
+      "loss": 1.3233,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.885188413200075e-05,
+      "loss": 1.1081,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.830477159419966e-05,
+      "loss": 0.9364,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7655753219826114e-05,
+      "loss": 0.7434,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.5053,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.6063784128704367e-05,
+      "loss": 0.2824,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.512779468773494e-05,
+      "loss": 0.1312,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.4103791521862784e-05,
+      "loss": 0.0681,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.2996252336387414e-05,
+      "loss": 0.0496,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.181002011836737e-05,
+      "loss": 0.0482,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.0550281959470023e-05,
+      "loss": 0.0497,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.9222546374139533e-05,
+      "loss": 0.0523,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.783261921226479e-05,
+      "loss": 0.0561,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.6386578271674984e-05,
+      "loss": 0.0606,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.489074672147621e-05,
+      "loss": 0.0664,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.335166545244178e-05,
+      "loss": 0.0742,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.1776064475361114e-05,
+      "loss": 0.0799,
+      "step": 210
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.017083349241492e-05,
+      "loss": 0.0873,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.8542991770260608e-05,
+      "loss": 0.0952,
+      "step": 230
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.689965744656508e-05,
+      "loss": 0.1036,
+      "step": 240
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.5248016404199908e-05,
+      "loss": 0.1103,
+      "step": 250
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.3595290849203862e-05,
+      "loss": 0.1207,
+      "step": 260
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.19487077299135e-05,
+      "loss": 0.1254,
+      "step": 270
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.031546713535688e-05,
+      "loss": 0.1387,
+      "step": 280
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.87027108110963e-05,
+      "loss": 0.1402,
+      "step": 290
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.7117490930191965e-05,
+      "loss": 0.1518,
+      "step": 300
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 5.7197792313789645e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0474fbb331a6a8df843475fa87e752177bc451d593d9d453141d5ff0e7d077c9
+size 3230

checkpoint-400/README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.4.0

checkpoint-400/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-400/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81dea3d855b2b268a97491ab9a1f036d167f3d7b363ac10a851ebc51bff2b973
+size 16821197

checkpoint-400/finetuning_args.json

@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc502017347738b7045a6d970b4f246523c4efb9d497c845fb2c0c7ab15a2c0b
+size 33661637

checkpoint-400/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3071bdb3d8008d67ade26df133a9de77e9c5511a68bdf006986873b194d0729c
+size 18679

checkpoint-400/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d04dc549b97a70c877112b4ea697c076d6467a073e38aab23a469999e8d895
+size 18679

checkpoint-400/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dbedb16f08f5b1ebbf7626b3dc8d974a9f361b4fc37857836a2365dfb2860db
+size 18679

checkpoint-400/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68913ab66483a1233fba4fda9d86e1328db1962b0d2dcc0be4a9ca8a0498758f
+size 18679

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3336dcfe269fac13b4f189bb47e77778dcb14b26aa3143efeba85141081ece94
+size 627