Upload folder using huggingface_hub

README.md

@@ -0,0 +1,21 @@
+---
+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: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/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": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "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 sha256:014c44b49d87f1d9eded01347909227f923b7f3693b96f96839fae7ea76523b7
+size 134264202

checkpoint-100/README.md

@@ -0,0 +1,34 @@
+---
+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: False
+- 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: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+- PEFT 0.5.0
+
+- PEFT 0.5.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/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": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "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 sha256:615e4cdf956b551f9f61dbd0275af73de7492fbd59b2678ca529f5fb9ee99d69
+size 134264202

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9050a3d265ce5779463efc8a32eb6bd741735cb709982ffe41f8f827482788aa
+size 268514874

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4196c310679c3b5b5cccaf12f78b316e65ef31ceb19d2208292c18a27b6c72
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf17cf57a2c7ada30c068bda10f9471324026e43a9481dd681eee7940fc506d
+size 1064

checkpoint-100/special_tokens_map.json

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2518891687657431,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 7.8137,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0002,
+      "loss": 2.5574,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0002,
+      "loss": 2.3516,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002,
+      "loss": 2.0521,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0002,
+      "loss": 1.5531,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002,
+      "loss": 2.0324,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0002,
+      "loss": 1.704,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0002,
+      "loss": 1.8253,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0002,
+      "loss": 2.1076,
+      "step": 90
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0002,
+      "loss": 1.8701,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1507829183594496.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e89503efa45e7df5f867ecf175c0c724821a0add1cd513005c95cba03217b95
+size 4536

runs/Oct24_17-46-05_0d087949e2b4/events.out.tfevents.1698169594.0d087949e2b4.279.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87fc5e1f9b20cfb1f36276c0408bb337a540ab9bd39d55557d54fc0c3ec0386
+size 6464