Upload 6 files

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: True
+- bnb_4bit_compute_dtype: bfloat16
+
+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: bfloat16
+### Framework versions
+
+- PEFT 0.5.0
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/grimpep_L2-MythoMax22b-instruct-Falseblock",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "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:d16629ea18728fa24526d62da7938acf496e25e8dbc17ef3d8fb5724d20cf174
+size 136372557

training_log.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name": "grimpep_L2-MythoMax22b-instruct-Falseblock",
+  "base_model_class": "LlamaForCausalLM",
+  "base_loaded_in_4bit": true,
+  "base_loaded_in_8bit": false,
+  "projections": "q, v",
+  "loss": 1.3766,
+  "learning_rate": 0.0,
+  "epoch": 2.53,
+  "current_steps": 451,
+  "train_runtime": 998.8868,
+  "train_samples_per_second": 2.274,
+  "train_steps_per_second": 0.015,
+  "total_flos": 3.2187033092358144e+16,
+  "train_loss": 1.9135538736979167
+}

training_parameters.json

@@ -0,0 +1,30 @@
+{
+  "lora_name": "aichan-22B",
+  "always_override": false,
+  "save_steps": 0.0,
+  "micro_batch_size": 4,
+  "batch_size": 128,
+  "epochs": 3.0,
+  "learning_rate": "3e-4",
+  "lr_scheduler_type": "linear",
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "cutoff_len": 256,
+  "dataset": "aichan-public-v3.1",
+  "eval_dataset": "None",
+  "format": "alpaca-format",
+  "eval_steps": 100.0,
+  "raw_text_file": "None",
+  "overlap_len": 128,
+  "newline_favor_len": 128,
+  "higher_rank_limit": false,
+  "warmup_steps": 100.0,
+  "optimizer": "adamw_torch",
+  "hard_cut_string": "\\n\\n\\n",
+  "train_only_after": "",
+  "stop_at_loss": 0,
+  "add_eos_token": false,
+  "min_chars": 0.0,
+  "report_to": "None"
+}

training_prompt.json

@@ -0,0 +1,5 @@
+{
+  "template_type": "dataset",
+  "template_1": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n%instruction%\n\n### Response:\n%output%",
+  "template_2": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n%instruction%\n\n### Input:\n%input%\n\n### Response:\n%output%"
+}