End of training

.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

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: mpnet-multi-agri-classifier
+  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. -->
+
+# mpnet-multi-agri-classifier
+
+This model is a fine-tuned version of [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3444
+- Precision Macro: 0.8402
+- Precision Weighted: 0.9196
+- Recall Macro: 0.9042
+- Recall Weighted: 0.9046
+- F1-score: 0.8655
+- Accuracy: 0.9046
+
+## 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: 6.9e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision Macro | Precision Weighted | Recall Macro | Recall Weighted | F1-score | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------------:|:------------------:|:------------:|:---------------:|:--------:|:--------:|
+| 0.393         | 1.0   | 334  | 0.2938          | 0.8528          | 0.9132             | 0.8773       | 0.9092          | 0.8641   | 0.9092   |
+| 0.3213        | 2.0   | 668  | 0.3049          | 0.8299          | 0.9110             | 0.8885       | 0.8966          | 0.8534   | 0.8966   |
+| 0.2591        | 3.0   | 1002 | 0.2561          | 0.8654          | 0.9226             | 0.8937       | 0.9184          | 0.8784   | 0.9184   |
+| 0.1853        | 4.0   | 1336 | 0.3254          | 0.8386          | 0.9190             | 0.9034       | 0.9034          | 0.8641   | 0.9034   |
+| 0.1119        | 5.0   | 1670 | 0.3444          | 0.8402          | 0.9196             | 0.9042       | 0.9046          | 0.8655   | 0.9046   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 1.12.0+cu102
+- Datasets 2.3.2
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Other",
+    "1": "Agriculture"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Agriculture": 1,
+    "Other": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92db5ec3aa955baf7cfacef696cc5e8aedef2d3ab51843d13151d7092350cc8b
+size 1112205008

runs/Dec11_12-40-34_prashant-t4-core4/events.out.tfevents.1702298483.prashant-t4-core4.4196.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2258667544b9a359aebf6a62350fdb5c202257083595264f6d446cab5f88c43e
+size 8691

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa685fc160bbdbab64058d4fc91b60e62d207e8dc60b9af5c002c5ab946ded00
+size 17083009

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "problem_type": "single_label_classification",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78562f32c0578383d4e947415b7849780aed317d42b8d88be6602561dbb825ad
+size 4143