Initial commit from mrm8488

README.md

@@ -0,0 +1,78 @@
+---
+language:
+- en
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- matthews_correlation
+model-index:
+- name: deberta-v3-small
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.6333205721749096
+---
+
+<!-- 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. -->
+
+# deberta-v3-small
+
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the GLUE COLA dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4051
+- Matthews Correlation: 0.6333
+
+## 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-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
+| No log        | 1.0   | 535  | 0.4051          | 0.6333               |
+| 0.3371        | 2.0   | 1070 | 0.4455          | 0.6531               |
+| 0.3371        | 3.0   | 1605 | 0.5755          | 0.6499               |
+| 0.1305        | 4.0   | 2140 | 0.7188          | 0.6553               |
+| 0.1305        | 5.0   | 2675 | 0.8047          | 0.6700               |
+
+
+### Framework versions
+
+- Transformers 4.13.0.dev0
+- Pytorch 1.10.0+cu111
+- Datasets 1.16.1
+- Tokenizers 0.10.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.4050879180431366,
+    "eval_matthews_correlation": 0.6333205721749096,
+    "eval_runtime": 2.0441,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 510.242,
+    "eval_steps_per_second": 64.086,
+    "train_loss": 0.19247490570923992,
+    "train_runtime": 168.1314,
+    "train_samples": 8551,
+    "train_samples_per_second": 254.295,
+    "train_steps_per_second": 15.91
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "cola",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "unacceptable",
+    "1": "acceptable"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 12,
+  "num_hidden_layers": 6,
+  "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,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.4050879180431366,
+    "eval_matthews_correlation": 0.6333205721749096,
+    "eval_runtime": 2.0441,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 510.242,
+    "eval_steps_per_second": 64.086
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a2eb48f8a23e0b06964e87aec6ef4b1dc985814839082748c064456481e213
+size 567632875

runs/events.out.tfevents.1638896689.fbe054181d38.464.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ea8fd2b61c6a32468a4a0e2d7e652f377160ab9113da34a720766d09d4fecb
+size 5893

runs/events.out.tfevents.1638896860.fbe054181d38.464.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4182510f029363fdf0b3afec212accd36114402b15864ab31458246483d6537
+size 375

special_tokens_map.json

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

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.19247490570923992,
+    "train_runtime": 168.1314,
+    "train_samples": 8551,
+    "train_samples_per_second": 254.295,
+    "train_steps_per_second": 15.91
+}

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": 0.4050879180431366,
+  "best_model_checkpoint": "/content/deberta-v3-small/checkpoint-535",
+  "epoch": 5.0,
+  "global_step": 2675,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4050879180431366,
+      "eval_matthews_correlation": 0.6333205721749096,
+      "eval_runtime": 2.031,
+      "eval_samples_per_second": 513.528,
+      "eval_steps_per_second": 64.499,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.8785046728971963e-05,
+      "loss": 0.3371,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4455100893974304,
+      "eval_matthews_correlation": 0.6530734183134956,
+      "eval_runtime": 2.0334,
+      "eval_samples_per_second": 512.931,
+      "eval_steps_per_second": 64.424,
+      "step": 1070
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5754692554473877,
+      "eval_matthews_correlation": 0.6499333084534608,
+      "eval_runtime": 2.0345,
+      "eval_samples_per_second": 512.647,
+      "eval_steps_per_second": 64.388,
+      "step": 1605
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 7.570093457943924e-06,
+      "loss": 0.1305,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7188061475753784,
+      "eval_matthews_correlation": 0.6553451139053764,
+      "eval_runtime": 2.0152,
+      "eval_samples_per_second": 517.554,
+      "eval_steps_per_second": 65.004,
+      "step": 2140
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.8047384023666382,
+      "eval_matthews_correlation": 0.6700089525749314,
+      "eval_runtime": 2.0026,
+      "eval_samples_per_second": 520.818,
+      "eval_steps_per_second": 65.414,
+      "step": 2675
+    },
+    {
+      "epoch": 5.0,
+      "step": 2675,
+      "total_flos": 1415961343234560.0,
+      "train_loss": 0.19247490570923992,
+      "train_runtime": 168.1314,
+      "train_samples_per_second": 254.295,
+      "train_steps_per_second": 15.91
+    }
+  ],
+  "max_steps": 2675,
+  "num_train_epochs": 5,
+  "total_flos": 1415961343234560.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a4cd8abdc7501e9f667c3605f9282b8e62a2fe1ba2844b1934d379173a587e
+size 2927