Upload 6 files

README.md

@@ -0,0 +1,32 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: True
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: True
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+- PEFT 0.5.0.dev0
+
+- PEFT 0.5.0.dev0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "models\\komt13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "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 sha256:7ae5e1fc448ef6272d1432e89cd0ac664d7b60b995f6bc485ef060986ef0c868
+size 209772877

training_log.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name": "komt13b",
+  "base_model_class": "LlamaForCausalLM",
+  "base_loaded_in_4bit": false,
+  "base_loaded_in_8bit": true,
+  "projections": "q, v",
+  "loss": 1.9479,
+  "learning_rate": 0.0,
+  "epoch": 4.64,
+  "current_steps": 3795,
+  "train_runtime": 35642.0848,
+  "train_samples_per_second": 1.855,
+  "train_steps_per_second": 0.001,
+  "total_flos": 1.2168655656085094e+18,
+  "train_loss": 2.010098671913147
+}

training_parameters.json

@@ -0,0 +1,30 @@
+{
+  "lora_name": "wwpp v1",
+  "always_override": true,
+  "save_steps": 0.0,
+  "micro_batch_size": 8,
+  "batch_size": 768,
+  "epochs": 5.0,
+  "learning_rate": "2e-5",
+  "lr_scheduler_type": "linear",
+  "lora_rank": 64,
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "cutoff_len": 256,
+  "dataset": "None",
+  "eval_dataset": "None",
+  "format": "None",
+  "eval_steps": 100.0,
+  "raw_text_file": "gumi",
+  "overlap_len": 128,
+  "newline_favor_len": 128,
+  "higher_rank_limit": false,
+  "warmup_steps": 300.0,
+  "optimizer": "adamw_torch",
+  "hard_cut_string": "\\f",
+  "train_only_after": "",
+  "stop_at_loss": 0,
+  "add_eos_token": true,
+  "min_chars": 1.0,
+  "report_to": "tensorboard"
+}

training_prompt.json

@@ -0,0 +1,3 @@
+{
+  "template_type": "raw_text"
+}