knowgen/ManuBERT-SequenceClassification

README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: mDeBERTa
+  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. -->
+
+# mDeBERTa
+
+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: 0.0347
+- Accuracy: 0.9921
+
+## 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: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9921333333333333,
+    "eval_loss": 0.03474695608019829,
+    "eval_runtime": 410.5726,
+    "eval_samples": 60000,
+    "eval_samples_per_second": 146.137,
+    "eval_steps_per_second": 4.567,
+    "train_loss": 0.020007819811503093,
+    "train_runtime": 9507.2866,
+    "train_samples": 480000,
+    "train_samples_per_second": 100.975,
+    "train_steps_per_second": 1.578
+}

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": "4.38.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9921333333333333,
+    "eval_loss": 0.03474695608019829,
+    "eval_runtime": 410.5726,
+    "eval_samples": 60000,
+    "eval_samples_per_second": 146.137,
+    "eval_steps_per_second": 4.567
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a84401d5ebf15b9bd0610a1a07447b87d9af5086e8c882f8a7417d063c71f4
+size 737719272

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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
+    }
+  },
+  "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": 2.0,
+    "train_loss": 0.020007819811503093,
+    "train_runtime": 9507.2866,
+    "train_samples": 480000,
+    "train_samples_per_second": 100.975,
+    "train_steps_per_second": 1.578
+}

trainer_state.json

@@ -0,0 +1,210 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 0.0827,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.0397,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8e-05,
+      "loss": 0.0337,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.0327,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0313,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.0272,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 0.0236,
+      "step": 3500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.0263,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.4e-05,
+      "loss": 0.0233,
+      "step": 4500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.0229,
+      "step": 5000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.2666666666666667e-05,
+      "loss": 0.022,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2e-05,
+      "loss": 0.0215,
+      "step": 6000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1333333333333334e-05,
+      "loss": 0.0194,
+      "step": 6500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.0234,
+      "step": 7000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0182,
+      "step": 7500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.0136,
+      "step": 8000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.0104,
+      "step": 8500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.0121,
+      "step": 9000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.0122,
+      "step": 9500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0108,
+      "step": 10000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 6e-06,
+      "loss": 0.0107,
+      "step": 10500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.0121,
+      "step": 11000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.0085,
+      "step": 11500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0079,
+      "step": 12000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0086,
+      "step": 12500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.0095,
+      "step": 13000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0092,
+      "step": 13500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.0103,
+      "step": 14000
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.0077,
+      "step": 14500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.009,
+      "step": 15000
+    },
+    {
+      "epoch": 2.0,
+      "step": 15000,
+      "total_flos": 1.2629557149696e+17,
+      "train_loss": 0.020007819811503093,
+      "train_runtime": 9507.2866,
+      "train_samples_per_second": 100.975,
+      "train_steps_per_second": 1.578
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.2629557149696e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7401efe3d3c5e93ce21e6db161b08470a4eede364cc4ea93cd79288a998f8de8
+size 4728