Training in progress, step 20
Browse files
adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-2-27b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"exclude_modules": null,
|
| 7 |
+
"fan_in_fan_out": false,
|
| 8 |
+
"inference_mode": true,
|
| 9 |
+
"init_lora_weights": true,
|
| 10 |
+
"layer_replication": null,
|
| 11 |
+
"layers_pattern": null,
|
| 12 |
+
"layers_to_transform": null,
|
| 13 |
+
"loftq_config": {},
|
| 14 |
+
"lora_alpha": 32,
|
| 15 |
+
"lora_dropout": 0.05,
|
| 16 |
+
"megatron_config": null,
|
| 17 |
+
"megatron_core": "megatron.core",
|
| 18 |
+
"modules_to_save": null,
|
| 19 |
+
"peft_type": "LORA",
|
| 20 |
+
"r": 8,
|
| 21 |
+
"rank_pattern": {},
|
| 22 |
+
"revision": null,
|
| 23 |
+
"target_modules": [
|
| 24 |
+
"q_proj",
|
| 25 |
+
"v_proj"
|
| 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:ff1905781a83a125f37c9a89d86a3bd0edcece5e1eee6e2f78a40029d62072b0
|
| 3 |
+
size 22634392
|
runs/Oct14_17-06-31_f47acc3acfa9/events.out.tfevents.1728925592.f47acc3acfa9.1885.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e209c53b8e78e5bf42ac6c20c49d239bb93fcfab782c2f4274a3375b7671b6e3
|
| 3 |
+
size 10198
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31fd0aa364d0329057067cc0c1d094736715fae943850006b9ae9fd58c154938
|
| 3 |
+
size 5240
|