Training in progress, epoch 0
Browse files
adapter_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlamaForSequenceClassification",
|
5 |
+
"parent_library": "transformers.models.llama.modeling_llama"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-1B",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
+
"lora_dropout": 0.1,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"classifier"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 16,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"fc_out",
|
29 |
+
"v_proj",
|
30 |
+
"q_proj",
|
31 |
+
"k_proj",
|
32 |
+
"out_proj",
|
33 |
+
"wte",
|
34 |
+
"fc_in"
|
35 |
+
],
|
36 |
+
"task_type": null,
|
37 |
+
"use_dora": false,
|
38 |
+
"use_rslora": false
|
39 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc9c148a04e69a1bc4dd72a47271c0e4159a871d1b52f5263faffa67204ca1df
|
3 |
+
size 9449880
|
runs/Oct01_13-03-48_79dff2c489a8/events.out.tfevents.1727787860.79dff2c489a8.1858.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:466c7ed1f0752e71572f30de019abc272011115c4dd22d8808b55b990066e19f
|
3 |
+
size 38223
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5300f0266164376d02b7ce52c63497bc39572571857a641b4454dec7d4cd833d
|
3 |
+
size 5176
|