Upload folder using huggingface_hub

README.md

@@ -0,0 +1,86 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: out_2
+  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. -->
+
+# out_2
+
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6774
+- F1: 0.7444
+
+## 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: 6e-06
+- train_batch_size: 3
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 48
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 5.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Accuracy | Validation Loss |
+|:-------------:|:-----:|:-----:|:--------:|:---------------:|
+| 0.6448        | 0.21  | 500   | 0.6347   | 0.6498          |
+| 0.6401        | 0.41  | 1000  | 0.6442   | 0.6312          |
+| 0.6557        | 0.62  | 1500  | 0.6582   | 0.6314          |
+| 0.5819        | 0.83  | 2000  | 0.6588   | 0.6320          |
+| 0.6086        | 1.04  | 2500  | 0.6563   | 0.6343          |
+| 0.6011        | 1.24  | 3000  | 0.6557   | 0.6165          |
+| 0.5616        | 1.45  | 3500  | 0.6461   | 0.6376          |
+| 0.5885        | 1.66  | 4000  | 0.6468   | 0.6304          |
+| 0.6198        | 1.87  | 4500  | 0.6423   | 0.6448          |
+| 0.5838        | 2.07  | 5000  | 0.6665   | 0.6320          |
+| 0.5564        | 2.28  | 5500  | 0.6684   | 0.6428          |
+| 0.5726        | 2.49  | 6000  | 0.6703   | 0.6401          |
+| 0.5491        | 2.7   | 6500  | 0.6684   | 0.6455          |
+| 0.5303        | 2.9   | 7000  | 0.6703   | 0.6339          |
+| 0.497         | 3.11  | 7500  | 0.6607   | 0.6541          |
+| 0.5041        | 3.32  | 8000  | 0.6760   | 0.6653          |
+| 0.4978        | 3.53  | 8500  | 0.6696   | 0.6627          |
+| 0.5272        | 3.73  | 9000  | 0.6677   | 0.6684          |
+| 0.5487        | 3.94  | 9500  | 0.6760   | 0.6593          |
+| 0.4998        | 4.15  | 10000 | 0.6747   | 0.6738          |
+| 0.4626        | 4.36  | 10500 | 0.6753   | 0.6781          |
+| 0.5202        | 4.56  | 11000 | 0.6722   | 0.6763          |
+| 0.4623        | 4.77  | 11500 | 0.6728   | 0.6778          |
+| 0.4383        | 4.98  | 12000 | 0.6741   | 0.6775          |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.4
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 1,
+  "[MASK]": 128000,
+  "[PAD]": 0,
+  "[SEP]": 2,
+  "[UNK]": 3
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.6740787801778907,
+    "eval_f1": 0.7443946188340808,
+    "eval_loss": 0.6774438619613647,
+    "eval_runtime": 61.2399,
+    "eval_samples": 1574,
+    "eval_samples_per_second": 25.702,
+    "eval_steps_per_second": 3.217,
+    "train_loss": 0.0,
+    "train_runtime": 5.2952,
+    "train_samples": 77152,
+    "train_samples_per_second": 72851.348,
+    "train_steps_per_second": 1517.422
+}

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "single_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_f1": 0.7443946188340808,
+    "eval_loss": 0.6774438619613647,
+    "eval_runtime": 61.2399,
+    "eval_samples": 1574,
+    "eval_samples_per_second": 25.702,
+    "eval_steps_per_second": 3.217
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f022abb7f0098f9177c30d622c0fc3436b280c56fc5c9d72487c73d60792eac7
+size 737764341

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.0,
+    "train_runtime": 5.2952,
+    "train_samples": 77152,
+    "train_samples_per_second": 72851.348,
+    "train_steps_per_second": 1517.422
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab224a6df4956eb33c732d9f454a4a99e9e61aeb5e7b63517ca008495c25aec7
+size 4219