cj
commited on
Commit
•
b080a15
1
Parent(s):
d39e326
first
Browse files- README.md +7 -1
- adapter_config.json +20 -0
- adapter_model.bin +3 -0
- all_results.json +7 -0
- finetuning_args.json +14 -0
- runs/Aug18_12-50-02_autodl-container-82e3118a3c-73e19e11/events.out.tfevents.1692334250.autodl-container-82e3118a3c-73e19e11.5279.0 +3 -0
- train_results.json +7 -0
- trainer_log.jsonl +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -1,3 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: peft
|
| 3 |
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.4.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "baichuan-inc/Baichuan-7B",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32.0,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"W_pack"
|
| 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 sha256:779ba958aac2ea60a6ebb2e9471c21b18064bf26cf29388f86b834e4f4b58d5c
|
| 3 |
+
size 16799153
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.98,
|
| 3 |
+
"train_loss": 0.2642190715797791,
|
| 4 |
+
"train_runtime": 4480.4571,
|
| 5 |
+
"train_samples_per_second": 29.305,
|
| 6 |
+
"train_steps_per_second": 1.83
|
| 7 |
+
}
|
finetuning_args.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dpo_beta": 0.1,
|
| 3 |
+
"finetuning_type": "lora",
|
| 4 |
+
"lora_alpha": 32.0,
|
| 5 |
+
"lora_dropout": 0.1,
|
| 6 |
+
"lora_rank": 8,
|
| 7 |
+
"lora_target": [
|
| 8 |
+
"W_pack"
|
| 9 |
+
],
|
| 10 |
+
"name_module_trainable": "mlp",
|
| 11 |
+
"num_hidden_layers": 32,
|
| 12 |
+
"num_layer_trainable": 3,
|
| 13 |
+
"resume_lora_training": true
|
| 14 |
+
}
|
runs/Aug18_12-50-02_autodl-container-82e3118a3c-73e19e11/events.out.tfevents.1692334250.autodl-container-82e3118a3c-73e19e11.5279.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6d0dead6dea01a32a09a72a9230d92f9bdc5ca9cfa6b9be00382ad6596444e7
|
| 3 |
+
size 133414
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.98,
|
| 3 |
+
"train_loss": 0.2642190715797791,
|
| 4 |
+
"train_runtime": 4480.4571,
|
| 5 |
+
"train_samples_per_second": 29.305,
|
| 6 |
+
"train_steps_per_second": 1.83
|
| 7 |
+
}
|
trainer_log.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a845508e1963b928a33759d29fbd93d72d7a73e63db60f4240c1ac3cad629eab
|
| 3 |
+
size 3357
|
training_loss.png
ADDED
|