Upload folder using huggingface_hub

README.md

@@ -1,41 +1,72 @@
 ---
-license: mit
-datasets:
-- nyu-mll/glue
 language:
 - en
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
-library_name: transformers
-pipeline_tag: text-classification
+model-index:
+- name: bert-base-qnli
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9070107999267801
 ---
-# Model
-
-`bert-base-cased` fine-tuned on QNLI.
-
-Eval results:
-
-```json
-{
-    "epoch": 3.0,
-    "eval_accuracy": 0.90591250228812,
-    "eval_loss": 0.32652467489242554,
-    "eval_runtime": 10.899,
-    "eval_samples": 5463,
-    "eval_samples_per_second": 501.238,
-    "eval_steps_per_second": 62.666
-}
-```
-
-Train results
-
-```json
-{
-    "epoch": 3.0,
-    "train_loss": 0.21169122040720828,
-    "train_runtime": 1639.2307,
-    "train_samples": 104743,
-    "train_samples_per_second": 191.693,
-    "train_steps_per_second": 5.992
-}
-```
+
+<!-- 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. -->
+
+# bert-base-qnli
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the GLUE QNLI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5751
+- Accuracy: 0.9070
+
+## 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 4.31.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.18.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9070107999267801,
+    "eval_loss": 0.5751491189002991,
+    "eval_runtime": 14.5154,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 376.358,
+    "eval_steps_per_second": 47.053,
+    "train_loss": 0.1580200532820273,
+    "train_runtime": 2902.672,
+    "train_samples": 104743,
+    "train_samples_per_second": 180.425,
+    "train_steps_per_second": 11.278
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/qnli",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
     "BertForSequenceClassification"
   ],

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9070107999267801,
+    "eval_loss": 0.5751491189002991,
+    "eval_runtime": 14.5154,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 376.358,
+    "eval_steps_per_second": 47.053
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa90ebce31b3283ce4dfe508959ea3367df3800ee5e0ed60cef622c2080cf12
-size 433312817
+oid sha256:4919a9cdb4f4a2f60203c8dff1bad945eb1e1a2dc80ddf147934afb135512294
+size 433315633

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.1580200532820273,
+    "train_runtime": 2902.672,
+    "train_samples": 104743,
+    "train_samples_per_second": 180.425,
+    "train_steps_per_second": 11.278
+}

trainer_state.json

@@ -0,0 +1,415 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 32735,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.969573850618604e-05,
+      "loss": 0.4624,
+      "step": 500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9390255078661985e-05,
+      "loss": 0.3994,
+      "step": 1000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9084771651137928e-05,
+      "loss": 0.3688,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.877928822361387e-05,
+      "loss": 0.3434,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8473804796089814e-05,
+      "loss": 0.3376,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8168321368565758e-05,
+      "loss": 0.3317,
+      "step": 3000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7863448907896747e-05,
+      "loss": 0.3318,
+      "step": 3500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.755796548037269e-05,
+      "loss": 0.3189,
+      "step": 4000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7252482052848634e-05,
+      "loss": 0.3197,
+      "step": 4500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.6946998625324577e-05,
+      "loss": 0.3026,
+      "step": 5000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.664151519780052e-05,
+      "loss": 0.3033,
+      "step": 5500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.633664273713151e-05,
+      "loss": 0.2932,
+      "step": 6000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.6031159309607457e-05,
+      "loss": 0.2955,
+      "step": 6500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5725675882083397e-05,
+      "loss": 0.2112,
+      "step": 7000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.5420192454559343e-05,
+      "loss": 0.189,
+      "step": 7500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.5115319993890332e-05,
+      "loss": 0.2086,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.4809836566366276e-05,
+      "loss": 0.2065,
+      "step": 8500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.450435313884222e-05,
+      "loss": 0.202,
+      "step": 9000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.4198869711318161e-05,
+      "loss": 0.2092,
+      "step": 9500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.3893997250649154e-05,
+      "loss": 0.2003,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.3588513823125096e-05,
+      "loss": 0.2056,
+      "step": 10500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.328303039560104e-05,
+      "loss": 0.2035,
+      "step": 11000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.2977546968076984e-05,
+      "loss": 0.2031,
+      "step": 11500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.2672063540552926e-05,
+      "loss": 0.2093,
+      "step": 12000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.2366580113028869e-05,
+      "loss": 0.2022,
+      "step": 12500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2061096685504812e-05,
+      "loss": 0.2031,
+      "step": 13000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.1755613257980756e-05,
+      "loss": 0.1257,
+      "step": 13500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.1450740797311745e-05,
+      "loss": 0.1238,
+      "step": 14000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.114525736978769e-05,
+      "loss": 0.118,
+      "step": 14500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.0839773942263634e-05,
+      "loss": 0.134,
+      "step": 15000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.0534290514739575e-05,
+      "loss": 0.1275,
+      "step": 15500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.0229418054070568e-05,
+      "loss": 0.1184,
+      "step": 16000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 9.923934626546512e-06,
+      "loss": 0.1221,
+      "step": 16500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.618451199022453e-06,
+      "loss": 0.1259,
+      "step": 17000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 9.312967771498396e-06,
+      "loss": 0.1477,
+      "step": 17500
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 9.008095310829388e-06,
+      "loss": 0.1349,
+      "step": 18000
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 8.70322285016038e-06,
+      "loss": 0.1345,
+      "step": 18500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.397739422636323e-06,
+      "loss": 0.1402,
+      "step": 19000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 8.092255995112266e-06,
+      "loss": 0.1418,
+      "step": 19500
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 7.78677256758821e-06,
+      "loss": 0.0875,
+      "step": 20000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 7.4812891400641516e-06,
+      "loss": 0.0687,
+      "step": 20500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 7.176416679395143e-06,
+      "loss": 0.0787,
+      "step": 21000
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 6.870933251871087e-06,
+      "loss": 0.0672,
+      "step": 21500
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 6.5654498243470296e-06,
+      "loss": 0.0703,
+      "step": 22000
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 6.259966396822973e-06,
+      "loss": 0.0744,
+      "step": 22500
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 5.955093936153964e-06,
+      "loss": 0.0734,
+      "step": 23000
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 5.649610508629907e-06,
+      "loss": 0.0762,
+      "step": 23500
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 5.344127081105851e-06,
+      "loss": 0.0792,
+      "step": 24000
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 5.038643653581794e-06,
+      "loss": 0.0746,
+      "step": 24500
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 4.733160226057737e-06,
+      "loss": 0.0899,
+      "step": 25000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 4.428287765388728e-06,
+      "loss": 0.0892,
+      "step": 25500
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 4.122804337864671e-06,
+      "loss": 0.066,
+      "step": 26000
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 3.8173209103406145e-06,
+      "loss": 0.0535,
+      "step": 26500
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 3.5124484496716056e-06,
+      "loss": 0.0455,
+      "step": 27000
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 3.206965022147549e-06,
+      "loss": 0.0347,
+      "step": 27500
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 2.901481594623492e-06,
+      "loss": 0.0416,
+      "step": 28000
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 2.595998167099435e-06,
+      "loss": 0.0491,
+      "step": 28500
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 2.290514739575378e-06,
+      "loss": 0.0438,
+      "step": 29000
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.9850313120513214e-06,
+      "loss": 0.0392,
+      "step": 29500
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 1.6795478845272645e-06,
+      "loss": 0.0446,
+      "step": 30000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 1.3740644570032077e-06,
+      "loss": 0.0487,
+      "step": 30500
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 1.069191996334199e-06,
+      "loss": 0.0468,
+      "step": 31000
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 7.637085688101422e-07,
+      "loss": 0.0518,
+      "step": 31500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 4.5822514128608527e-07,
+      "loss": 0.0419,
+      "step": 32000
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 1.5274171376202842e-07,
+      "loss": 0.0369,
+      "step": 32500
+    },
+    {
+      "epoch": 5.0,
+      "step": 32735,
+      "total_flos": 3.44488015894656e+16,
+      "train_loss": 0.1580200532820273,
+      "train_runtime": 2902.672,
+      "train_samples_per_second": 180.425,
+      "train_steps_per_second": 11.278
+    }
+  ],
+  "max_steps": 32735,
+  "num_train_epochs": 5,
+  "total_flos": 3.44488015894656e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a58c75e722f3dcc67a625ab40187de81f0321a7211424fe86bfe33eeef0c2efe
+size 3963