frank098 commited on
Commit
223534a
1 Parent(s): d99e5ba
README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/garage-bAInd_Stable-Platypus2-13B",
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": 256,
10
+ "lora_dropout": 0.05,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 128,
14
+ "revision": null,
15
+ "target_modules": [
16
+ "q_proj",
17
+ "v_proj"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aac00a416756d22ff9e257e47eb69cacf088b4e7f0ecab615f00f031f01007f
3
+ size 419488077
training_log.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name": "garage-bAInd_Stable-Platypus2-13B",
3
+ "base_model_class": "LlamaForCausalLM",
4
+ "base_loaded_in_4bit": false,
5
+ "base_loaded_in_8bit": false,
6
+ "loss": 0.1798,
7
+ "learning_rate": 0.0,
8
+ "epoch": 9.39,
9
+ "current_steps": 9553,
10
+ "train_runtime": 26187.7583,
11
+ "train_samples_per_second": 0.781,
12
+ "train_steps_per_second": 0.006,
13
+ "total_flos": 3.056911968632832e+18,
14
+ "train_loss": 0.3285474260648092
15
+ }
training_parameters.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "lora_name": "2k_planner",
3
+ "always_override": true,
4
+ "save_steps": 500.0,
5
+ "micro_batch_size": 2,
6
+ "batch_size": 128,
7
+ "epochs": 10.0,
8
+ "learning_rate": "1e-4",
9
+ "lr_scheduler_type": "cosine",
10
+ "lora_rank": 128,
11
+ "lora_alpha": 256,
12
+ "lora_dropout": 0.05,
13
+ "cutoff_len": 2048,
14
+ "dataset": "2k_planner",
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_torch",
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
+ }