Upload 13 files

add deberta-v3-large-cola files

README.md

@@ -1,3 +1,71 @@
 ---
+language:
+- en
 license: mit
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- matthews_correlation
+model-index:
+- name: debv3base
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.7193201130196331
 ---
+
+<!-- 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. -->
+
+# debv3base
+
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the GLUE COLA dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5335
+- Matthews Correlation: 0.7193
+
+## 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: 3e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.21.2
+- Pytorch 1.12.1+cu113
+- Datasets 2.1.0
+- Tokenizers 0.12.1

added_tokens.json

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

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.5334528088569641,
+    "eval_matthews_correlation": 0.7193201130196331,
+    "eval_runtime": 10.2963,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 101.299,
+    "eval_steps_per_second": 12.723,
+    "train_loss": 0.27882336008983644,
+    "train_runtime": 1049.1554,
+    "train_samples": 8551,
+    "train_samples_per_second": 24.451,
+    "train_steps_per_second": 3.057
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "cola",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "unacceptable",
+    "1": "acceptable"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "acceptable": 1,
+    "unacceptable": 0
+  },
+  "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": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.5334528088569641,
+    "eval_matthews_correlation": 0.7193201130196331,
+    "eval_runtime": 10.2963,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 101.299,
+    "eval_steps_per_second": 12.723
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b878984a61288c3c77d2f54d456e08bdcbf7a39373b28ec3e30860e3071b86a
+size 1740393387

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 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "name_or_path": "microsoft/deberta-v3-large",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.27882336008983644,
+    "train_runtime": 1049.1554,
+    "train_samples": 8551,
+    "train_samples_per_second": 24.451,
+    "train_steps_per_second": 3.057
+}

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 3207,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.532273152478952e-06,
+      "loss": 0.4213,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0645463049579046e-06,
+      "loss": 0.3452,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.5968194574368567e-06,
+      "loss": 0.2744,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.1290926099158092e-06,
+      "loss": 0.2548,
+      "step": 2000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 6.613657623947614e-07,
+      "loss": 0.2152,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.9363891487371378e-07,
+      "loss": 0.1992,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "step": 3207,
+      "total_flos": 5976749164543488.0,
+      "train_loss": 0.27882336008983644,
+      "train_runtime": 1049.1554,
+      "train_samples_per_second": 24.451,
+      "train_steps_per_second": 3.057
+    }
+  ],
+  "max_steps": 3207,
+  "num_train_epochs": 3,
+  "total_flos": 5976749164543488.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759df80c4447973a26ebd65c3f96e3fa94fdfb86acb2edad589367219947e001
+size 3375