fp32 model

README.md

@@ -1,3 +1,77 @@
 ---
-license: mit
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+- f1
+model-index:
+- name: electra-small-discriminator-mrpc
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8529411764705882
+    - name: F1
+      type: f1
+      value: 0.8983050847457628
 ---
+
+<!-- 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. -->
+
+# electra-small-discriminator-mrpc
+
+This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on the GLUE MRPC dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3909
+- Accuracy: 0.8529
+- F1: 0.8983
+- Combined Score: 0.8756
+
+## 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: 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
+
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- Pytorch 1.10.0+cu102
+- Datasets 2.1.0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8529411764705882,
+    "eval_combined_score": 0.8756231306081754,
+    "eval_f1": 0.8983050847457628,
+    "eval_loss": 0.3908618092536926,
+    "eval_runtime": 3.2371,
+    "eval_samples": 408,
+    "eval_samples_per_second": 126.041,
+    "eval_steps_per_second": 15.755,
+    "train_loss": 0.37104834515115487,
+    "train_runtime": 609.8592,
+    "train_samples": 3668,
+    "train_samples_per_second": 30.073,
+    "train_steps_per_second": 1.886
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google/electra-small-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "finetuning_task": "mrpc",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8529411764705882,
+    "eval_combined_score": 0.8756231306081754,
+    "eval_f1": 0.8983050847457628,
+    "eval_loss": 0.3908618092536926,
+    "eval_runtime": 3.2371,
+    "eval_samples": 408,
+    "eval_samples_per_second": 126.041,
+    "eval_steps_per_second": 15.755
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6650367835f290aa8dd6985dac961b74257e04a3183e3ae2ccc36a5de12852ee
+size 54266665

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-small-discriminator", "tokenizer_class": "ElectraTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.37104834515115487,
+    "train_runtime": 609.8592,
+    "train_samples": 3668,
+    "train_samples_per_second": 30.073,
+    "train_steps_per_second": 1.886
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 1150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.4823,
+      "step": 500
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.2987,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "step": 1150,
+      "total_flos": 269778106429440.0,
+      "train_loss": 0.37104834515115487,
+      "train_runtime": 609.8592,
+      "train_samples_per_second": 30.073,
+      "train_steps_per_second": 1.886
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 5,
+  "total_flos": 269778106429440.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba96485012c08898cf9d01e24e84d8721e723c0511a46f50a11951933f034fa6
+size 3119