Training in progress, step 500
Browse files
adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bigscience/bloom-1b1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": "loftq",
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {
|
| 12 |
+
"loftq_bits": 4,
|
| 13 |
+
"loftq_iter": 1
|
| 14 |
+
},
|
| 15 |
+
"lora_alpha": 8,
|
| 16 |
+
"lora_dropout": 0.05,
|
| 17 |
+
"megatron_config": null,
|
| 18 |
+
"megatron_core": "megatron.core",
|
| 19 |
+
"modules_to_save": null,
|
| 20 |
+
"peft_type": "LORA",
|
| 21 |
+
"r": 16,
|
| 22 |
+
"rank_pattern": {},
|
| 23 |
+
"revision": null,
|
| 24 |
+
"target_modules": [
|
| 25 |
+
"query_key_value"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_dora": false,
|
| 29 |
+
"use_rslora": false
|
| 30 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8809e685cf60f89290b8cfcf8ba4c8cd7680658087038b3c92c43ffc6befa0c
|
| 3 |
+
size 9444296
|
runs/Mar09_10-38-39_1fa0acbe9796/events.out.tfevents.1709980720.1fa0acbe9796.628.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34238abc7430e3835cc0992bacd6f9e8d6f4f73f0ebd85fc6ee5adfd54c136d2
|
| 3 |
+
size 4891
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70984629b68a96aa1441a48eb59ea11277d143e94aec21e4e9dced86b3f5a0f5
|
| 3 |
+
size 4920
|