Model save

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+final/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: Snowflake/snowflake-arctic-embed-m-v1.5
+license: mit
+base_model: intfloat/multilingual-e5-base
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # alignment-score-model
 
-This model is a fine-tuned version of [Snowflake/snowflake-arctic-embed-m-v1.5](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v1.5) on the None dataset.
+This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1019
-- Precision: 0.9234
-- Recall: 0.9136
-- F1 Macro: 0.9143
-- Accuracy: 0.9149
+- Loss: 0.0969
+- Precision: 0.9388
+- Recall: 0.9275
+- F1 Macro: 0.9283
+- Accuracy: 0.9289
 
 ## Model description
 
@@ -47,23 +47,30 @@ The following hyperparameters were used during training:
 - train_batch_size: 256
 - eval_batch_size: 128
 - seed: 0
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 2048
+- total_eval_batch_size: 1024
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
-| No log        | 0     | 0    | 0.5032          | 0.2550    | 0.5    | 0.3377   | 0.5100   |
-| No log        | 1.0   | 31   | 0.1634          | 0.8494    | 0.7842 | 0.7770   | 0.7884   |
-| No log        | 2.0   | 62   | 0.1102          | 0.9267    | 0.9185 | 0.9193   | 0.9198   |
-| No log        | 3.0   | 93   | 0.1019          | 0.9234    | 0.9136 | 0.9143   | 0.9149   |
+| No log        | 0     | 0    | 0.4846          | 0.2550    | 0.5    | 0.3377   | 0.5100   |
+| No log        | 1.0   | 4    | 0.2132          | 0.7608    | 0.6895 | 0.6704   | 0.6947   |
+| No log        | 2.0   | 8    | 0.1678          | 0.8813    | 0.8469 | 0.8458   | 0.8498   |
+| No log        | 3.0   | 12   | 0.1488          | 0.8297    | 0.7313 | 0.7137   | 0.7367   |
+| No log        | 4.0   | 16   | 0.1257          | 0.8693    | 0.8159 | 0.8121   | 0.8196   |
+| No log        | 5.0   | 20   | 0.1047          | 0.9183    | 0.8984 | 0.8989   | 0.9004   |
+| No log        | 6.0   | 24   | 0.0969          | 0.9388    | 0.9275 | 0.9283   | 0.9289   |
 
 
 ### Framework versions
 
 - Transformers 4.56.1
-- Pytorch 2.7.1+cu126
+- Pytorch 2.6.0a0+ecf3bae40a.nv25.01
 - Datasets 4.0.0
 - Tokenizers 0.22.0

final/config.json

@@ -1,11 +1,12 @@
 {
   "architectures": [
-    "BertForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": 0.0,
   "dtype": "float32",
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
@@ -17,19 +18,17 @@
   "label2id": {
     "LABEL_0": 0
   },
-  "layer_norm_eps": 1e-12,
-  "matryoshka_dimensions": [
-    256
-  ],
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "regression",
   "transformers_version": "4.56.1",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 250002
 }

final/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d78a7f400e135cc29992a8a458b1c6468ef1e41314bf9f7a2bd0bf40c2dbfb
-size 437955572
+oid sha256:f2d871c1c9db3bf703b69015678e7daae94d8a6464b6fe788cc481f9665748a2
+size 1112201932

final/special_tokens_map.json

@@ -1,34 +1,48 @@
 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "[MASK]",
+  "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
-    "content": "[PAD]",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "[UNK]",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

final/tokenizer_config.json

@@ -1,63 +1,55 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "max_length": 512,
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "[SEP]",
-  "stride": 0,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

final/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e5f6d5af216d17edfe1467da470e957780b3ac40160bc38ba9df9956fa7f181
-size 5841
+oid sha256:5685c8d944a8138d54ea8d9ac9bd7d9f7858cfa5fba16bf86c8fb5115d681ebd
+size 5432

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faca50eebc292cd4b2ba5c0e8868f3dc759f1fa3aafbcd8ff46da3d945f12ef
+oid sha256:f2d871c1c9db3bf703b69015678e7daae94d8a6464b6fe788cc481f9665748a2
 size 1112201932

runs/Sep14_16-45-42_fs-cai-002/events.out.tfevents.1757868347.fs-cai-002.3596035.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d927eb9933e4cb7f123aa3be027ce63758e0da4d9c757fde5cf1e782588a56f
-size 7920
+oid sha256:804be0591084ad58dd747c4f662291c0b1f1bce9f94fd6eab7070a41ea9858d1
+size 8737