upload fp32 model

README.md

@@ -1,3 +1,77 @@
 ---
+language:
+- en
 license: mit
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+- f1
+model-index:
+- name: roberta-base-mrpc
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8774509803921569
+    - name: F1
+      type: f1
+      value: 0.9137931034482758
 ---
+
+<!-- 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. -->
+
+# roberta-base-mrpc
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the GLUE MRPC dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5565
+- Accuracy: 0.8775
+- F1: 0.9138
+- Combined Score: 0.8956
+
+## 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": 0.8774509803921569,
+    "eval_combined_score": 0.8956220419202163,
+    "eval_f1": 0.9137931034482758,
+    "eval_loss": 0.5565009117126465,
+    "eval_runtime": 10.3375,
+    "eval_samples": 408,
+    "eval_samples_per_second": 39.468,
+    "eval_steps_per_second": 4.933,
+    "train_loss": 0.2803073907935101,
+    "train_runtime": 6011.5008,
+    "train_samples": 3668,
+    "train_samples_per_second": 3.051,
+    "train_steps_per_second": 0.191
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "mrpc",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8774509803921569,
+    "eval_combined_score": 0.8956220419202163,
+    "eval_f1": 0.9137931034482758,
+    "eval_loss": 0.5565009117126465,
+    "eval_runtime": 10.3375,
+    "eval_samples": 408,
+    "eval_samples_per_second": 39.468,
+    "eval_steps_per_second": 4.933
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7938b88f6f408a2414fdc41230f990c06ac16e1025575f14c629d5246bcaab7
+size 498657517

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.2803073907935101,
+    "train_runtime": 6011.5008,
+    "train_samples": 3668,
+    "train_samples_per_second": 3.051,
+    "train_steps_per_second": 0.191
+}

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": 0.4267,
+      "step": 500
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.1886,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "step": 1150,
+      "total_flos": 2412728377651200.0,
+      "train_loss": 0.2803073907935101,
+      "train_runtime": 6011.5008,
+      "train_samples_per_second": 3.051,
+      "train_steps_per_second": 0.191
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 5,
+  "total_flos": 2412728377651200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d97d89295ed50c09704af46bdabf4d6482fd899dbc66951d064f4d225c8f688
+size 3055