Upload folder using huggingface_hub

README.md

@@ -1,13 +1,28 @@
 ---
+language:
+- en
 license: apache-2.0
 base_model: bert-large-cased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert-large-sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9254587155963303
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-large-sst2
 
-This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on an unknown dataset.
+This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2122
-- Accuracy: 0.9278
+- Loss: 0.3748
+- Accuracy: 0.9255
 
 ## Model description
 
@@ -37,24 +52,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-05
 - train_batch_size: 16
-- eval_batch_size: 32
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 5.0
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3476        | 1.0   | 526  | 0.3028          | 0.8945   |
-| 0.1646        | 2.0   | 1052 | 0.2425          | 0.9117   |
-| 0.1098        | 3.0   | 1578 | 0.2053          | 0.9278   |
-| 0.0767        | 4.0   | 2104 | 0.2122          | 0.9278   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.9277522935779816,
-    "eval_loss": 0.2121734321117401,
-    "eval_runtime": 5.1507,
+    "epoch": 5.0,
+    "eval_accuracy": 0.9254587155963303,
+    "eval_loss": 0.374822735786438,
+    "eval_runtime": 2.241,
     "eval_samples": 872,
-    "eval_samples_per_second": 169.297,
-    "eval_steps_per_second": 5.436,
-    "train_loss": 0.16908984673793778,
-    "train_runtime": 4642.5497,
+    "eval_samples_per_second": 389.107,
+    "eval_steps_per_second": 48.638,
+    "train_loss": 0.1226784371989923,
+    "train_runtime": 1894.6082,
     "train_samples": 67349,
-    "train_samples_per_second": 58.028,
-    "train_steps_per_second": 0.453
+    "train_samples_per_second": 177.739,
+    "train_steps_per_second": 11.11
 }

config.json

@@ -6,20 +6,20 @@
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
   "directionality": "bidi",
-  "finetuning_task": "text-classification",
+  "finetuning_task": "sst2",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
   "id2label": {
-    "0": "0",
-    "1": "1"
+    "0": "negative",
+    "1": "positive"
   },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "label2id": {
-    "0": 0,
-    "1": 1
+    "negative": 0,
+    "positive": 1
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.9277522935779816,
-    "eval_loss": 0.2121734321117401,
-    "eval_runtime": 5.1507,
+    "epoch": 5.0,
+    "eval_accuracy": 0.9254587155963303,
+    "eval_loss": 0.374822735786438,
+    "eval_runtime": 2.241,
     "eval_samples": 872,
-    "eval_samples_per_second": 169.297,
-    "eval_steps_per_second": 5.436
+    "eval_samples_per_second": 389.107,
+    "eval_steps_per_second": 48.638
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74cbcc1c4be762e57a9262f746ba160437a3096c3176f4ad01675e20e6f9bd0a
+oid sha256:992f71a410b5155d4244cdd74eb958fca18d8f03b9796f7a675da60aa0a2e807
 size 1334459697

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.0,
-    "train_loss": 0.16908984673793778,
-    "train_runtime": 4642.5497,
+    "epoch": 5.0,
+    "train_loss": 0.1226784371989923,
+    "train_runtime": 1894.6082,
     "train_samples": 67349,
-    "train_samples_per_second": 58.028,
-    "train_steps_per_second": 0.453
+    "train_samples_per_second": 177.739,
+    "train_steps_per_second": 11.11
 }

trainer_state.json

@@ -1,85 +1,277 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.998099762470309,
-  "global_step": 2104,
+  "epoch": 5.0,
+  "global_step": 21050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.95,
-      "learning_rate": 3.8236692015209125e-05,
-      "loss": 0.3476,
+      "epoch": 0.12,
+      "learning_rate": 1.952969121140143e-05,
+      "loss": 0.3269,
       "step": 500
     },
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.8944954128440367,
-      "eval_loss": 0.3027590811252594,
-      "eval_runtime": 5.1932,
-      "eval_samples_per_second": 167.912,
-      "eval_steps_per_second": 5.392,
-      "step": 526
+      "epoch": 0.24,
+      "learning_rate": 1.9054631828978623e-05,
+      "loss": 0.275,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.857957244655582e-05,
+      "loss": 0.2457,
+      "step": 1500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8104513064133016e-05,
+      "loss": 0.2285,
+      "step": 2000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7629453681710215e-05,
+      "loss": 0.2181,
+      "step": 2500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7154394299287413e-05,
+      "loss": 0.2131,
+      "step": 3000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6679334916864608e-05,
+      "loss": 0.2115,
+      "step": 3500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6204275534441806e-05,
+      "loss": 0.2013,
+      "step": 4000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5730166270783847e-05,
+      "loss": 0.174,
+      "step": 4500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.5255106888361047e-05,
+      "loss": 0.1483,
+      "step": 5000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4780997624703088e-05,
+      "loss": 0.157,
+      "step": 5500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.4305938242280287e-05,
+      "loss": 0.1516,
+      "step": 6000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.3830878859857483e-05,
+      "loss": 0.1509,
+      "step": 6500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.335581947743468e-05,
+      "loss": 0.1455,
+      "step": 7000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.2880760095011876e-05,
+      "loss": 0.1481,
+      "step": 7500
     },
     {
       "epoch": 1.9,
-      "learning_rate": 2.6354562737642585e-05,
-      "loss": 0.1646,
-      "step": 1000
+      "learning_rate": 1.2405700712589075e-05,
+      "loss": 0.1469,
+      "step": 8000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.1930641330166273e-05,
+      "loss": 0.1406,
+      "step": 8500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.1455581947743468e-05,
+      "loss": 0.1038,
+      "step": 9000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.0980522565320666e-05,
+      "loss": 0.0981,
+      "step": 9500
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.911697247706422,
-      "eval_loss": 0.2424829751253128,
-      "eval_runtime": 5.1979,
-      "eval_samples_per_second": 167.759,
-      "eval_steps_per_second": 5.387,
-      "step": 1052
+      "epoch": 2.38,
+      "learning_rate": 1.0505463182897864e-05,
+      "loss": 0.1033,
+      "step": 10000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.003040380047506e-05,
+      "loss": 0.1123,
+      "step": 10500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 9.555344418052257e-06,
+      "loss": 0.1069,
+      "step": 11000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 9.0812351543943e-06,
+      "loss": 0.1074,
+      "step": 11500
     },
     {
       "epoch": 2.85,
-      "learning_rate": 1.4472433460076046e-05,
-      "loss": 0.1098,
-      "step": 1500
+      "learning_rate": 8.606175771971497e-06,
+      "loss": 0.115,
+      "step": 12000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 8.13206650831354e-06,
+      "loss": 0.1136,
+      "step": 12500
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 7.657007125890738e-06,
+      "loss": 0.0729,
+      "step": 13000
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 7.181947743467934e-06,
+      "loss": 0.0719,
+      "step": 13500
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 6.7068883610451305e-06,
+      "loss": 0.0751,
+      "step": 14000
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 6.231828978622329e-06,
+      "loss": 0.0675,
+      "step": 14500
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 5.757719714964372e-06,
+      "loss": 0.0771,
+      "step": 15000
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.9277522935779816,
-      "eval_loss": 0.2052551656961441,
-      "eval_runtime": 5.1738,
-      "eval_samples_per_second": 168.542,
-      "eval_steps_per_second": 5.412,
-      "step": 1578
+      "epoch": 3.68,
+      "learning_rate": 5.282660332541568e-06,
+      "loss": 0.0739,
+      "step": 15500
     },
     {
       "epoch": 3.8,
-      "learning_rate": 2.5903041825095057e-06,
-      "loss": 0.0767,
-      "step": 2000
+      "learning_rate": 4.807600950118766e-06,
+      "loss": 0.0699,
+      "step": 16000
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 4.332541567695962e-06,
+      "loss": 0.0749,
+      "step": 16500
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 3.857482185273159e-06,
+      "loss": 0.0638,
+      "step": 17000
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 3.383372921615202e-06,
+      "loss": 0.0382,
+      "step": 17500
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 2.9083135391923996e-06,
+      "loss": 0.0474,
+      "step": 18000
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 2.4332541567695966e-06,
+      "loss": 0.0527,
+      "step": 18500
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.9581947743467935e-06,
+      "loss": 0.0457,
+      "step": 19000
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 1.4831353919239907e-06,
+      "loss": 0.0448,
+      "step": 19500
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 1.0080760095011877e-06,
+      "loss": 0.0417,
+      "step": 20000
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 5.330166270783848e-07,
+      "loss": 0.0457,
+      "step": 20500
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.9277522935779816,
-      "eval_loss": 0.2121734321117401,
-      "eval_runtime": 5.1753,
-      "eval_samples_per_second": 168.492,
-      "eval_steps_per_second": 5.41,
-      "step": 2104
+      "epoch": 4.99,
+      "learning_rate": 5.8907363420427555e-08,
+      "loss": 0.0509,
+      "step": 21000
     },
     {
-      "epoch": 4.0,
-      "step": 2104,
-      "total_flos": 2.509495455856005e+17,
-      "train_loss": 0.16908984673793778,
-      "train_runtime": 4642.5497,
-      "train_samples_per_second": 58.028,
-      "train_steps_per_second": 0.453
+      "epoch": 5.0,
+      "step": 21050,
+      "total_flos": 7.845580673597184e+16,
+      "train_loss": 0.1226784371989923,
+      "train_runtime": 1894.6082,
+      "train_samples_per_second": 177.739,
+      "train_steps_per_second": 11.11
     }
   ],
-  "max_steps": 2104,
-  "num_train_epochs": 4,
-  "total_flos": 2.509495455856005e+17,
+  "max_steps": 21050,
+  "num_train_epochs": 5,
+  "total_flos": 7.845580673597184e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c3c538814698c75e5d72b38c6a4bd84b676496e77011365d1a46c481839af0
-size 4155
+oid sha256:506c4bb3faa4a7f22c174fd15b2af7d038fd5408b4b43271e6c75828eeb575fe
+size 3963