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: xlnet-base-cased-mrpc
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8455882352941176
+    - name: F1
+      type: f1
+      value: 0.8896672504378283
 ---
+
+<!-- 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. -->
+
+# xlnet-base-cased-mrpc
+
+This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the GLUE MRPC dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7156
+- Accuracy: 0.8456
+- F1: 0.8897
+- Combined Score: 0.8676
+
+## 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": 0.8455882352941176,
+    "eval_combined_score": 0.867627742865973,
+    "eval_f1": 0.8896672504378283,
+    "eval_loss": 0.7156228423118591,
+    "eval_runtime": 28.4059,
+    "eval_samples": 408,
+    "eval_samples_per_second": 14.363,
+    "eval_steps_per_second": 1.795,
+    "train_loss": 0.2684407242484715,
+    "train_runtime": 5649.8451,
+    "train_samples": 3668,
+    "train_samples_per_second": 3.246,
+    "train_steps_per_second": 0.204
+}

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "xlnet-base-cased",
+  "architectures": [
+    "XLNetForSequenceClassification"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "finetuning_task": "mrpc",
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "problem_type": "single_label_classification",
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8455882352941176,
+    "eval_combined_score": 0.867627742865973,
+    "eval_f1": 0.8896672504378283,
+    "eval_loss": 0.7156228423118591,
+    "eval_runtime": 28.4059,
+    "eval_samples": 408,
+    "eval_samples_per_second": 14.363,
+    "eval_steps_per_second": 1.795
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647ba3eec5026c3900f003c4a3b58fa45e4a9b39a2233f2ba4e0e7210a267cee
+size 469306973

special_tokens_map.json

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

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<eop>", "<eod>"], "special_tokens_map_file": null, "name_or_path": "xlnet-base-cased", "tokenizer_class": "XLNetTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.2684407242484715,
+    "train_runtime": 5649.8451,
+    "train_samples": 3668,
+    "train_samples_per_second": 3.246,
+    "train_steps_per_second": 0.204
+}

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": 0.4261,
+      "step": 500
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.1647,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "step": 1150,
+      "total_flos": 2612352163491840.0,
+      "train_loss": 0.2684407242484715,
+      "train_runtime": 5649.8451,
+      "train_samples_per_second": 3.246,
+      "train_steps_per_second": 0.204
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 5,
+  "total_flos": 2612352163491840.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62e5a671aa2a65b27140fbb487c094a58ebe69c2d6d73c0f07e2938b7dd7c1e
+size 3055