Training in progress, step 1000

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Alibaba-NLP/gte-modernbert-base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "Wqkv",
+    "Wo"
+  ],
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b0b9b432bd96a6792c736d2a6d015059e411ff8e63ef314ee0da01899a94bd
+size 9207032

eval/binary_classification_evaluation_test_results.csv

@@ -433,3 +433,8 @@ epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision
 4.232804232804233,32000,0.7223037358314119,0.7253189446248114,0.613902004799133,0.886145251396648,0.690575874692857,0.47146300343005826
 4.365079365079365,33000,0.7158220602699086,0.7182069930921152,0.6071465322082733,0.8789944134078213,0.6817875439897024,0.4556655095651951
 4.497354497354498,34000,0.7213201979974525,0.7271285588186892,0.6076617238878748,0.9050651769087523,0.6862317912116369,0.47517110412821156
+0.13227513227513227,1000,0.7037777526966672,0.7122170715871171,0.5989283084033827,0.8783612662942272,0.6476617871668658,0.44182914870985407
+0.26455026455026454,2000,0.7037777526966672,0.7122170715871171,0.5989283084033827,0.8783612662942272,0.6476617871668658,0.44182914870985407
+0.3968253968253968,3000,0.7037777526966672,0.7122170715871171,0.5989283084033827,0.8783612662942272,0.6476617871668658,0.44182914870985407
+0.5291005291005291,4000,0.7037777526966672,0.7122170715871171,0.5989283084033827,0.8783612662942272,0.6476617871668658,0.44182914870985407
+0.13227513227513227,1000,0.7213201979974525,0.7271285588186892,0.6076617238878748,0.9050651769087523,0.6862317912116369,0.47517110412821156

initial_metrics.json

@@ -1,10 +1,10 @@
 {
-    "test_cosine_accuracy": 0.7037777526966672,
-    "test_cosine_accuracy_threshold": 0.8524033427238464,
-    "test_cosine_f1": 0.7122170715871171,
-    "test_cosine_f1_threshold": 0.8118724822998047,
-    "test_cosine_precision": 0.5989283084033827,
-    "test_cosine_recall": 0.8783612662942272,
-    "test_cosine_ap": 0.6476617871668658,
-    "test_cosine_mcc": 0.44182914870985407
+    "test_cosine_accuracy": 0.7213201979974525,
+    "test_cosine_accuracy_threshold": 0.8022605776786804,
+    "test_cosine_f1": 0.7271285588186892,
+    "test_cosine_f1_threshold": 0.7352645397186279,
+    "test_cosine_precision": 0.6076617238878748,
+    "test_cosine_recall": 0.9050651769087523,
+    "test_cosine_ap": 0.6862317912116369,
+    "test_cosine_mcc": 0.47517110412821156
 }