Training in progress, step 34000
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": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 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": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"Wqkv",
|
| 29 |
+
"Wo"
|
| 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 sha256:85b0b9b432bd96a6792c736d2a6d015059e411ff8e63ef314ee0da01899a94bd
|
| 3 |
+
size 9207032
|
eval/Information-Retrieval_evaluation_train_predictions_cosine.jsonl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e01b16cb42331d8606f8010aead2c005986c3526491c050da9703bf9e9db2b20
|
| 3 |
+
size 107799810
|
eval/Information-Retrieval_evaluation_train_results.csv
CHANGED
|
@@ -34,3 +34,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Precision@1,cosine-Recall@1,cosine-MRR@1,co
|
|
| 34 |
4.1005291005291005,31000,0.5646243775709028,0.5646243775709028,0.5422409703428321,0.5646243775709028,0.7609398479986418,0.705476302742608
|
| 35 |
4.232804232804233,32000,0.5651872699718554,0.5651872699718554,0.5430923450992731,0.5651872699718554,0.7615643244364297,0.7065930051850824
|
| 36 |
4.365079365079365,33000,0.5648841740636501,0.5648841740636501,0.5424479054658747,0.5648841740636501,0.7601369995161581,0.7051462327425166
|
|
|
|
|
|
| 34 |
4.1005291005291005,31000,0.5646243775709028,0.5646243775709028,0.5422409703428321,0.5646243775709028,0.7609398479986418,0.705476302742608
|
| 35 |
4.232804232804233,32000,0.5651872699718554,0.5651872699718554,0.5430923450992731,0.5651872699718554,0.7615643244364297,0.7065930051850824
|
| 36 |
4.365079365079365,33000,0.5648841740636501,0.5648841740636501,0.5424479054658747,0.5648841740636501,0.7601369995161581,0.7051462327425166
|
| 37 |
+
4.497354497354498,34000,0.5642779822472397,0.5642779822472397,0.5425173649448385,0.5642779822472397,0.7603799152427771,0.7054019396213604
|
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 sha256:2c3f6189e20ff274e531655df423b1c8619191bb160f780c34e2566e287d84be
|
| 3 |
size 298041696
|