update

README.md

@@ -1,4 +1,32 @@
 ---
-tags:
-- not-for-all-audiences
----
+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: False
+- 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: False
+- 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

@@ -1,14 +1,18 @@
 {
-  "base_model_name_or_path": "models/TehVenom_Pygmalion-13b-Merged",
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/mythalion-13b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
   "lora_alpha": 256,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 128,
+  "revision": null,
   "target_modules": [
     "q_proj",
     "v_proj"

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a42ec582bb934b176d722fb2ac82c0f4b45ee9a9829da398e0d04eeed92cf03
+oid sha256:9e9252b498460da1e610f4727d892cf5f800e1480964b3df994baabcdf266679
 size 419488077

training_log.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name": "mythalion-13b",
+  "base_model_class": "LlamaForCausalLM",
+  "base_loaded_in_4bit": false,
+  "base_loaded_in_8bit": true,
+  "projections": "q, v",
+  "loss": 0.9646,
+  "learning_rate": 0.00015,
+  "epoch": 1.88,
+  "current_steps": 46,
+  "train_runtime": 87.3735,
+  "train_samples_per_second": 2.232,
+  "train_steps_per_second": 0.034,
+  "total_flos": 2487721328640000.0,
+  "train_loss": 0.9646244049072266
+}

training_parameters.json

@@ -1 +1,30 @@
-{"lora_name": "charluv-lora-v2", "always_override": true, "save_steps": 0.0, "micro_batch_size": 4, "batch_size": 128, "epochs": 3.0, "learning_rate": "3e-4", "lr_scheduler_type": "cosine_with_restarts", "lora_rank": 128, "lora_alpha": 256, "lora_dropout": 0.05, "cutoff_len": 256, "dataset": "None", "eval_dataset": "None", "format": "None", "eval_steps": 100.0, "raw_text_file": "aivo", "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": ""}
+{
+  "lora_name": "charluv-lora",
+  "always_override": false,
+  "save_steps": 0.0,
+  "micro_batch_size": 4,
+  "batch_size": 128,
+  "epochs": 3.0,
+  "learning_rate": "3e-4",
+  "lr_scheduler_type": "cosine_with_restarts",
+  "lora_rank": 128,
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "cutoff_len": 256,
+  "dataset": "None",
+  "eval_dataset": "None",
+  "format": "None",
+  "eval_steps": 100.0,
+  "raw_text_file": "aivo",
+  "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": 1.5,
+  "add_eos_token": false,
+  "min_chars": 0.0,
+  "report_to": "wandb"
+}

training_prompt.json

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