Upload 5 files
Browse files- adapter_config.json +17 -0
- adapter_model.bin +3 -0
- training_log.json +15 -0
- training_parameters.json +27 -0
- training_prompt.json +5 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "models\\orca_mini_v2_7b",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"lora_alpha": 64,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"modules_to_save": null,
|
| 10 |
+
"peft_type": "LORA",
|
| 11 |
+
"r": 32,
|
| 12 |
+
"target_modules": [
|
| 13 |
+
"q_proj",
|
| 14 |
+
"v_proj"
|
| 15 |
+
],
|
| 16 |
+
"task_type": "CAUSAL_LM"
|
| 17 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73de1e9d111170dd22465a189b4315a0f01d759def74d5dea2b1f0b3590cc470
|
| 3 |
+
size 67154893
|
training_log.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name": "orca_mini_v2_7b",
|
| 3 |
+
"base_model_class": "LlamaForCausalLM",
|
| 4 |
+
"base_loaded_in_4bit": true,
|
| 5 |
+
"base_loaded_in_8bit": false,
|
| 6 |
+
"loss": 0.4249,
|
| 7 |
+
"learning_rate": 9.941095478389733e-06,
|
| 8 |
+
"epoch": 2.02,
|
| 9 |
+
"current_steps": 25922,
|
| 10 |
+
"train_runtime": 336185.1496,
|
| 11 |
+
"train_samples_per_second": 0.612,
|
| 12 |
+
"train_steps_per_second": 0.005,
|
| 13 |
+
"total_flos": 4.318475426973352e+18,
|
| 14 |
+
"train_loss": 0.4772539265729763
|
| 15 |
+
}
|
training_parameters.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"lora_name": "Orcawiz7bloraMini",
|
| 3 |
+
"always_override": false,
|
| 4 |
+
"save_steps": 300.0,
|
| 5 |
+
"micro_batch_size": 4,
|
| 6 |
+
"batch_size": 128,
|
| 7 |
+
"epochs": 4.0,
|
| 8 |
+
"learning_rate": "2e-5",
|
| 9 |
+
"lr_scheduler_type": "cosine",
|
| 10 |
+
"lora_rank": 32,
|
| 11 |
+
"lora_alpha": 64,
|
| 12 |
+
"lora_dropout": 0.05,
|
| 13 |
+
"cutoff_len": 2048,
|
| 14 |
+
"dataset": "FilteredOrcaWizardClean2spaces",
|
| 15 |
+
"eval_dataset": "None",
|
| 16 |
+
"format": "alpaca-format",
|
| 17 |
+
"eval_steps": 100.0,
|
| 18 |
+
"raw_text_file": "None",
|
| 19 |
+
"overlap_len": 128,
|
| 20 |
+
"newline_favor_len": 128,
|
| 21 |
+
"higher_rank_limit": false,
|
| 22 |
+
"warmup_steps": 100.0,
|
| 23 |
+
"optimizer": "adamw_bnb_8bit",
|
| 24 |
+
"hard_cut_string": "\\n\\n\\n",
|
| 25 |
+
"train_only_after": "",
|
| 26 |
+
"stop_at_loss": 0
|
| 27 |
+
}
|
training_prompt.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"template_type": "dataset",
|
| 3 |
+
"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%",
|
| 4 |
+
"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%"
|
| 5 |
+
}
|