Upload 5 files
Browse files- adapter_config.json +19 -0
- adapter_model.bin +3 -0
- training_log.json +15 -0
- training_parameters.json +27 -0
- training_prompt.json +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "models/tiiuae_falcon-7b",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 128,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 64,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"query_key_value"
|
| 17 |
+
],
|
| 18 |
+
"task_type": "CAUSAL_LM"
|
| 19 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e35c4df5bb5c16398d964d74100a76dc17c43b94920904fb7be83f59a6549fdc
|
| 3 |
+
size 75521265
|
training_log.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name": "tiiuae_falcon-7b",
|
| 3 |
+
"base_model_class": "RWForCausalLM",
|
| 4 |
+
"base_loaded_in_4bit": true,
|
| 5 |
+
"base_loaded_in_8bit": false,
|
| 6 |
+
"loss": 2.0208,
|
| 7 |
+
"learning_rate": 0.0002222222222222222,
|
| 8 |
+
"epoch": 0.99,
|
| 9 |
+
"current_steps": 103,
|
| 10 |
+
"train_runtime": 443.7855,
|
| 11 |
+
"train_samples_per_second": 0.946,
|
| 12 |
+
"train_steps_per_second": 0.029,
|
| 13 |
+
"total_flos": 8516655881650176.0,
|
| 14 |
+
"train_loss": 2.0475152272444506
|
| 15 |
+
}
|
training_parameters.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"lora_name": "falc7b_swift_contxt_230703_1",
|
| 3 |
+
"always_override": true,
|
| 4 |
+
"save_steps": 50.0,
|
| 5 |
+
"micro_batch_size": 4,
|
| 6 |
+
"batch_size": 32,
|
| 7 |
+
"epochs": 1.0,
|
| 8 |
+
"learning_rate": "1e-3",
|
| 9 |
+
"lr_scheduler_type": "linear",
|
| 10 |
+
"lora_rank": 64,
|
| 11 |
+
"lora_alpha": 128,
|
| 12 |
+
"lora_dropout": 0.05,
|
| 13 |
+
"cutoff_len": 1024,
|
| 14 |
+
"dataset": "None",
|
| 15 |
+
"eval_dataset": "None",
|
| 16 |
+
"format": "None",
|
| 17 |
+
"eval_steps": 100.0,
|
| 18 |
+
"raw_text_file": "swiftify_context_train",
|
| 19 |
+
"overlap_len": 128,
|
| 20 |
+
"newline_favor_len": 128,
|
| 21 |
+
"higher_rank_limit": false,
|
| 22 |
+
"warmup_steps": 30.0,
|
| 23 |
+
"optimizer": "adamw_torch",
|
| 24 |
+
"hard_cut_string": "\\n\\n\\n",
|
| 25 |
+
"train_only_after": "",
|
| 26 |
+
"stop_at_loss": 1.5
|
| 27 |
+
}
|
training_prompt.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"template_type": "raw_text"
|
| 3 |
+
}
|