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 sha256:2caaad197530a3965a22162a1a4f134ea47bedb0764e975de78c12c02243c5bb
+size 16821197

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.09018798397804953,
+    "train_runtime": 3518.059,
+    "train_samples_per_second": 17.302,
+    "train_steps_per_second": 0.135
+}

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:fda278e5ace76c536aa3bf1c85fe37dee7c1f6ac6d8437aa7124a5892bd0b5dc
+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:d29bf607d1e1afe671d6ca5da3455e86cdf11d536eef4799cbf210d6b1ba39e3
+size 33661637

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05af7fd19119f832a74957287aac384167fca8c622934e8187e2f1b6ccab763
+size 18679

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e7a3cfb6182f86fd8c287f157dbf17a51e3d41ef4900a9c1d16683de988a06
+size 18679

checkpoint-100/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f739cfd665b8f02ff81eac08273474054f733be834d9f5ad06c198f35c200180
+size 18679

checkpoint-100/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85947e197d907567a060baad9da4201ccb50033e71315bdad2473b6c8a9cdd46
+size 18679

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fc3d581e094b837788a14789aed7dda2dc957371e27a9e11c540ba1d15ff44
+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": 2.0664,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.978160173317438e-05,
+      "loss": 1.2851,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9509499146870236e-05,
+      "loss": 0.6483,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.913022275693372e-05,
+      "loss": 0.2406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.864543104251587e-05,
+      "loss": 0.0239,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.805724387443462e-05,
+      "loss": 0.0034,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.736823324551909e-05,
+      "loss": 0.0016,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6581412023939354e-05,
+      "loss": 0.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.5700220778700504e-05,
+      "loss": 0.0008,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.0007,
+      "step": 100
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 1.437155155991593e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4d4776971676826edc330ee61437e7a54bfe686c560913bd8069abb82f5e49
+size 3233

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 sha256:08e7c8df461492fdbde37f96b850b7e78d1c5e76726aa6d370fbeba1ed1c4929
+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 sha256:26051ca8e1622e381cc98e0223e28fa1c5c7bb748de47545c2ca1eeb809cd71e
+size 33661637

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0203839e375e297c063f0be527508574258a71b3ef7eb8d60f5ceaaf649b3b1e
+size 18679

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dab47960e0999cd4f368eb5a167c3f87d3a411f657152e7b67fa055326ad114
+size 18679

checkpoint-200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0398e0ba30bd59ef210aec509d09e2c236bb6f7ff86f0b3833b3bd95c043974e
+size 18679

checkpoint-200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa99c0e254813c49ef236c5f2d087a2bdaebf52f8a64f426abb81fa5baa3f4d7
+size 18679

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893ca84874bd9c2338ac0a97b3de6e0ec91bb60ea1db89177a64098c99125236
+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": 2.0664,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.978160173317438e-05,
+      "loss": 1.2851,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9509499146870236e-05,
+      "loss": 0.6483,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.913022275693372e-05,
+      "loss": 0.2406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.864543104251587e-05,
+      "loss": 0.0239,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.805724387443462e-05,
+      "loss": 0.0034,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.736823324551909e-05,
+      "loss": 0.0016,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6581412023939354e-05,
+      "loss": 0.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.5700220778700504e-05,
+      "loss": 0.0008,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.0007,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.367053692460385e-05,
+      "loss": 0.0006,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.2530919606812216e-05,
+      "loss": 0.0006,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.131464403810422e-05,
+      "loss": 0.0005,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.002702868207563e-05,
+      "loss": 0.0005,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.867370395306068e-05,
+      "loss": 0.0005,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.726058759576271e-05,
+      "loss": 0.0004,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.579385880846232e-05,
+      "loss": 0.0004,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.427993122295552e-05,
+      "loss": 0.0004,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.0004,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1137137178519985e-05,
+      "loss": 0.0004,
+      "step": 200
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 2.873967036722053e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4d4776971676826edc330ee61437e7a54bfe686c560913bd8069abb82f5e49
+size 3233

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 sha256:67afa29920d2fdd88fc572710616aae99bc119a9b324f0484c8bc24be01ea25c
+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:c6cb61c7e7a6c9212fd13bf186651779365f85b3e4522d49f2cc7080d90909c7
+size 33661637

checkpoint-300/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e119d10ba4d8e22aaa3ad4fba2f801258396c5fc1f35f4d35ff7c67d85d093
+size 18679

checkpoint-300/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006add7f74badc1fcd18e5aa4575f72d37f9ecb8c77edd49ca46735c15e0dcf7
+size 18679

checkpoint-300/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6cd1596b1eac1b4c3cd748cc1ed511cc8aa6aac36df17540c2c1b726ecc75e8
+size 18679

checkpoint-300/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d104156c0b3cb1bfc7442325adf59332e75b57234ca2e3c8e362f1e11d477371
+size 18679

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a611d74221f03f472fa8be6b8d9dcfe898c28b46f2edc8cec83be11539a7887
+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": 2.0664,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.978160173317438e-05,
+      "loss": 1.2851,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9509499146870236e-05,
+      "loss": 0.6483,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.913022275693372e-05,
+      "loss": 0.2406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.864543104251587e-05,
+      "loss": 0.0239,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.805724387443462e-05,
+      "loss": 0.0034,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.736823324551909e-05,
+      "loss": 0.0016,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6581412023939354e-05,
+      "loss": 0.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.5700220778700504e-05,
+      "loss": 0.0008,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.0007,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.367053692460385e-05,
+      "loss": 0.0006,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.2530919606812216e-05,
+      "loss": 0.0006,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.131464403810422e-05,
+      "loss": 0.0005,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.002702868207563e-05,
+      "loss": 0.0005,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.867370395306068e-05,
+      "loss": 0.0005,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.726058759576271e-05,
+      "loss": 0.0004,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.579385880846232e-05,
+      "loss": 0.0004,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.427993122295552e-05,
+      "loss": 0.0004,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.0004,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1137137178519985e-05,
+      "loss": 0.0004,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.952201335830275e-05,
+      "loss": 0.0003,
+      "step": 210
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.788711592423966e-05,
+      "loss": 0.0003,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.623959386683056e-05,
+      "loss": 0.0003,
+      "step": 230
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.458665138084104e-05,
+      "loss": 0.0003,
+      "step": 240
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2935516363191693e-05,
+      "loss": 0.0003,
+      "step": 250
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1293408807203947e-05,
+      "loss": 0.0003,
+      "step": 260
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9667509231406334e-05,
+      "loss": 0.0003,
+      "step": 270
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.806492728095389e-05,
+      "loss": 0.0003,
+      "step": 280
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6492670638958924e-05,
+      "loss": 0.0003,
+      "step": 290
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.495761438367577e-05,
+      "loss": 0.0003,
+      "step": 300
+    }
+  ],
+  "max_steps": 475,
+  "num_train_epochs": 1,
+  "total_flos": 4.311371526302597e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4d4776971676826edc330ee61437e7a54bfe686c560913bd8069abb82f5e49
+size 3233

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:c7fd70b326a6697e1a82379ba9c06b287cc8ee698d808cfa21a7537b857ee605
+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:d8202fda93eab44854c6ddcfa01e34c522af24909fcfa74f06f3e10232e7a7a2
+size 33661637

checkpoint-400/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9339f5ba504bd7e6c3838357145b22a63fe93f3cbda16765783c9f6ca7e88f4d
+size 18679

checkpoint-400/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def61d8ae44359a8cba9c62b9dd81352520cc1a9048bbd8b47b06e3e32262cf5
+size 18679

checkpoint-400/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308b0154faf07284bf01c71c1aaa5284e1186f6ab682693f519f295a98f6ef3f
+size 18679

checkpoint-400/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af9908fa1c4458f08404ed789ea1c784606ac07ca08486673d8f3e3522a2105
+size 18679

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dee0767eaefa25af7080534beb0e2e99f2c8c9364e6b61372d798c11efa0dae
+size 627