Upload folder using huggingface_hub

.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 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: Snowflake/snowflake-arctic-embed-l-v2.0
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.244761124253273
+
+f1_macro: 0.9768339768339769
+
+f1_micro: 0.9760765550239234
+
+f1_weighted: 0.9760457655194498
+
+precision_macro: 0.978448275862069
+
+precision_micro: 0.9760765550239234
+
+precision_weighted: 0.978138920970137
+
+recall_macro: 0.9772727272727273
+
+recall_micro: 0.9760765550239234
+
+recall_weighted: 0.9760765550239234
+
+accuracy: 0.9760765550239234

checkpoint-803/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Snowflake/snowflake-arctic-embed-l-v2.0",
+  "_num_labels": 4,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "coding",
+    "1": "question_answering",
+    "2": "searching_for_information",
+    "3": "summarization"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "coding": 0,
+    "question_answering": 1,
+    "searching_for_information": 2,
+    "summarization": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-803/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ddfe5660324c067939f702dd0c891e7b0fa5ab419814ff8527cace7d85ff34
+size 2271084152

checkpoint-803/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2f851090f59f0f76332270270cc38d1a0396fd6c7daf2c4ac85c9b0a5187ff
+size 4542405205

checkpoint-803/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a9d1b1c2a35a9941ea6e9bd8462c2e18221983c7406a6aaeeae85db6b01035
+size 14244

checkpoint-803/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d755a2018e4826fdcc89fa667833156a2954bad472d3a793dc893be909e4615a
+size 1064

checkpoint-803/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09cad0fb1148af34ae47c649e5647cdb30f4a05d13dcfff4be36f777a3d8ac6b
+size 5368

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Snowflake/snowflake-arctic-embed-l-v2.0",
+  "_num_labels": 4,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "coding",
+    "1": "question_answering",
+    "2": "searching_for_information",
+    "3": "summarization"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "coding": 0,
+    "question_answering": 1,
+    "searching_for_information": 2,
+    "summarization": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "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 sha256:78ddfe5660324c067939f702dd0c891e7b0fa5ab419814ff8527cace7d85ff34
+size 2271084152

runs/Dec16_02-21-48_r-claudiomello-bookclassifier-od72w12h-ae4df-qtkw7/events.out.tfevents.1734315710.r-claudiomello-bookclassifier-od72w12h-ae4df-qtkw7.124.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef685452f036c832ad25e070bf36c7ac416a6a706fbacddebd29a588587c5f9
-size 1032694
+oid sha256:5765370a90a2a011aab9d287cc8c18fc0b09a5c09b15c23fd91247b2c3ad7fd9
+size 1037679

runs/Dec16_02-21-48_r-claudiomello-bookclassifier-od72w12h-ae4df-qtkw7/events.out.tfevents.1734322417.r-claudiomello-bookclassifier-od72w12h-ae4df-qtkw7.124.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35705715c5ec26d2160be03de6089207c1a04182dcf79dda031a91cee609e0f8
+size 921

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": true,
+    "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 sha256:901bd4b40a8c8307455742bb500cd5d6a1491ab313b2e3755f38502e9951cecf
+size 17083066

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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": 512,
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "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 sha256:09cad0fb1148af34ae47c649e5647cdb30f4a05d13dcfff4be36f777a3d8ac6b
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "Classifier-Intent-snowflake/autotrain-data",
+    "model": "Snowflake/snowflake-arctic-embed-l-v2.0",
+    "lr": 5e-05,
+    "epochs": 20,
+    "max_seq_length": 8192,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": 1,
+    "project_name": "Classifier-Intent-snowflake",
+    "auto_find_batch_size": true,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "claudiomello",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}