Training in progress, step 198000
Browse files
adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Alibaba-NLP/gte-modernbert-base",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": false,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 128,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.1,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"qalora_group_size": 16,
|
24 |
+
"r": 64,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"Wo",
|
29 |
+
"Wqkv"
|
30 |
+
],
|
31 |
+
"target_parameters": null,
|
32 |
+
"task_type": "FEATURE_EXTRACTION",
|
33 |
+
"trainable_token_indices": null,
|
34 |
+
"use_dora": false,
|
35 |
+
"use_qalora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea6fa2cb394a5f34052164c01d3f18f394fb0d8f0f5d46001c34e1d0b410ddfd
|
3 |
+
size 36781392
|
eval/binary_classification_evaluation_test_results.csv
CHANGED
@@ -352,3 +352,4 @@ epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision
|
|
352 |
51.58730158730159,195000,0.7674013640541107,0.7569075923028534,0.667567644464677,0.873854748603352,0.7774184322776321,0.541592140132882
|
353 |
51.851851851851855,196000,0.7670627690620919,0.756264829200117,0.6708568792526813,0.8665921787709497,0.7771932300429866,0.5409150302582091
|
354 |
52.116402116402114,197000,0.7670627690620919,0.7557872986149227,0.6669990882151812,0.8718435754189944,0.7775947397511751,0.5393761775866834
|
|
|
|
352 |
51.58730158730159,195000,0.7674013640541107,0.7569075923028534,0.667567644464677,0.873854748603352,0.7774184322776321,0.541592140132882
|
353 |
51.851851851851855,196000,0.7670627690620919,0.756264829200117,0.6708568792526813,0.8665921787709497,0.7771932300429866,0.5409150302582091
|
354 |
52.116402116402114,197000,0.7670627690620919,0.7557872986149227,0.6669990882151812,0.8718435754189944,0.7775947397511751,0.5393761775866834
|
355 |
+
52.38095238095238,198000,0.7667725447832185,0.7553963798277031,0.6663251366120219,0.8719553072625699,0.777431193404544,0.5385298107291973
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 298041696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8a189e39af9414e52d52a06b9edeb6adf2e30467a2798c5869ff74660904786
|
3 |
size 298041696
|