Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,55 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: solon-large-06-BIG
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# solon-large-06-BIG
+
+This model was trained from scratch on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.3.2
+- Tokenizers 0.15.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "solon-large-06-BIG/checkpoint-6000",
+  "_name_or_path": "solon-large-06-BIG",
   "architectures": [
     "XLMRobertaModel"
   ],

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.35.2",
+    "pytorch": "2.1.1+cu121"
+  }
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebecd3087208e74c7922e0efbc734f910e366b06634a005df4fe40dab3d3a4c8
+oid sha256:e08b024ee2b4cf4e2364ba1c4f9ea763764d6ea7081e303b836dc19bd5a3a8b1
 size 2239607176

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

runs/Dec09_10-01-38_ordalie-8x-a100/events.out.tfevents.1702116183.ordalie-8x-a100.19338.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea7262b5033052bffb5cf143752328eeca21fbe977580fc218cc6629ab5f449
-size 99692
+oid sha256:bc0838a43d400c2e752b1129f2122e3468a21ba5a04d049d069187621f3e8d6e
+size 147303

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6710678b12670bc442b99edc952c4d996ae309a7020c1fa0096dd245c2faf790
+size 17082821