Upload 12 files

.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

README.md

@@ -1,3 +1,70 @@
----
-license: mit
----
+---
+library_name: transformers
+license: mit
+base_model: agentlans/multilingual-e5-small-aligned-v2
+tags:
+- generated_from_trainer
+model-index:
+- name: multilingual-e5-small-aligned-v2-text-quality-v3
+  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. -->
+
+# multilingual-e5-small-aligned-v2-text-quality-v3
+
+This model is a fine-tuned version of [agentlans/multilingual-e5-small-aligned-v2](https://huggingface.co/agentlans/multilingual-e5-small-aligned-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0641
+- Mse: 0.0641
+- Combined Score: 0.0641
+- Num Input Tokens Seen: 1109813760
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use 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: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step    | Validation Loss | Mse    | Combined Score | Input Tokens Seen |
+|:-------------:|:-----:|:-------:|:---------------:|:------:|:--------------:|:-----------------:|
+| 0.0725        | 1.0   | 108381  | 0.0727          | 0.0727 | 0.0727         | 110981376         |
+| 0.0603        | 2.0   | 216762  | 0.0675          | 0.0675 | 0.0675         | 221962752         |
+| 0.0559        | 3.0   | 325143  | 0.0703          | 0.0703 | 0.0703         | 332944128         |
+| 0.0387        | 4.0   | 433524  | 0.0675          | 0.0675 | 0.0675         | 443925504         |
+| 0.0325        | 5.0   | 541905  | 0.0704          | 0.0704 | 0.0704         | 554906880         |
+| 0.0276        | 6.0   | 650286  | 0.0672          | 0.0672 | 0.0672         | 665888256         |
+| 0.025         | 7.0   | 758667  | 0.0641          | 0.0641 | 0.0641         | 776869632         |
+| 0.0182        | 8.0   | 867048  | 0.0676          | 0.0676 | 0.0676         | 887851008         |
+| 0.0154        | 9.0   | 975429  | 0.0647          | 0.0647 | 0.0647         | 998832384         |
+| 0.0133        | 10.0  | 1083810 | 0.0643          | 0.0643 | 0.0643         | 1109813760        |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.06412914552577642,
+    "eval_loss": 0.06412914395332336,
+    "eval_mse": 0.06412914709822949,
+    "eval_runtime": 46.1708,
+    "eval_samples": 96338,
+    "eval_samples_per_second": 2086.555,
+    "eval_steps_per_second": 260.836,
+    "num_input_tokens_seen": 1109813760,
+    "total_flos": 1.4278349548463616e+17,
+    "train_loss": 0.035630166295778455,
+    "train_runtime": 37672.0963,
+    "train_samples": 867042,
+    "train_samples_per_second": 230.155,
+    "train_steps_per_second": 28.77,
+    "train_tokens_per_second": 29459.836
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.06412914552577642,
+    "eval_loss": 0.06412914395332336,
+    "eval_mse": 0.06412914709822949,
+    "eval_runtime": 46.1708,
+    "eval_samples": 96338,
+    "eval_samples_per_second": 2086.555,
+    "eval_steps_per_second": 260.836,
+    "num_input_tokens_seen": 1109813760
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee9791385346658d7f82314aa2bc73bdf7b69196b090d8a9787fa81c8937d85
+size 470640124

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e2c4647474659095b757711e8aef0583d58dbb50e3349958ebc460a9cf4977
+size 17083065

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "num_input_tokens_seen": 1109813760,
+    "total_flos": 1.4278349548463616e+17,
+    "train_loss": 0.035630166295778455,
+    "train_runtime": 37672.0963,
+    "train_samples": 867042,
+    "train_samples_per_second": 230.155,
+    "train_steps_per_second": 28.77,
+    "train_tokens_per_second": 29459.836
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee275d046c7e6eeeedbdcf73ded2b0eb67c1c7bf2faa51f26256a896694c678d
+size 5432