Upload 11 files

README.md

@@ -1,3 +1,34 @@
 ---
-license: cc-by-sa-4.0
+library_name: peft
 ---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+- PEFT 0.5.0
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "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": 16,
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813a0d452dc50f5945b3110658315f82ebccefb5d0de3e7498c03fd583c2d875
+size 92867533

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315915ed1ec06967ba58e01db849faaf05028f4bc1c6d8d411783b1d53473971
+size 185759493

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c75173d3879db635fd595ebff71b7e567970628e6d2806de9b253b3052fce3
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec75d0ea72b9443721912e1add368f17afed290ed2e66c3bde40d5a43b441ac2
+size 627

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9993906154783668,
+  "eval_steps": 100,
+  "global_step": 615,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0004,
+      "loss": 1.3292,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 1.264318823814392,
+      "eval_runtime": 84.6316,
+      "eval_samples_per_second": 6.121,
+      "eval_steps_per_second": 1.536,
+      "step": 100
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00036392754225221053,
+      "loss": 1.2472,
+      "step": 200
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 1.2486543655395508,
+      "eval_runtime": 84.6693,
+      "eval_samples_per_second": 6.118,
+      "eval_steps_per_second": 1.535,
+      "step": 200
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00026872239108850267,
+      "loss": 1.2331,
+      "step": 300
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 1.2404521703720093,
+      "eval_runtime": 84.6623,
+      "eval_samples_per_second": 6.118,
+      "eval_steps_per_second": 1.536,
+      "step": 300
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00014872738443612402,
+      "loss": 1.2188,
+      "step": 400
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 1.2340422868728638,
+      "eval_runtime": 84.6101,
+      "eval_samples_per_second": 6.122,
+      "eval_steps_per_second": 1.536,
+      "step": 400
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.722767036921105e-05,
+      "loss": 1.2173,
+      "step": 500
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 1.2294026613235474,
+      "eval_runtime": 84.6649,
+      "eval_samples_per_second": 6.118,
+      "eval_steps_per_second": 1.535,
+      "step": 500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.366903586781493e-07,
+      "loss": 1.2025,
+      "step": 600
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 1.2282078266143799,
+      "eval_runtime": 84.629,
+      "eval_samples_per_second": 6.121,
+      "eval_steps_per_second": 1.536,
+      "step": 600
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 615,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 8.660077507682304e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20469e100d2886c495c7cccfe2d1fc3156b74c166ccdd9a494eaa45d776cd255
+size 4027