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-rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.703971119133574
 ---
 
 <!-- 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-rte
 
-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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6921
-- Accuracy: 0.5307
+- Loss: 0.7109
+- Accuracy: 0.7040
 
 ## Model description
 
@@ -37,24 +52,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 32
+- learning_rate: 2e-05
+- train_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: 3.0
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.97  | 19   | 0.6876          | 0.5162   |
-| No log        | 2.0   | 39   | 0.6919          | 0.5054   |
-| No log        | 2.97  | 58   | 0.6949          | 0.5126   |
-| No log        | 3.9   | 76   | 0.6921          | 0.5307   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.9,
-    "eval_accuracy": 0.5306859205776173,
-    "eval_loss": 0.6921272277832031,
-    "eval_runtime": 1.84,
+    "epoch": 3.0,
+    "eval_accuracy": 0.703971119133574,
+    "eval_loss": 0.7108999490737915,
+    "eval_runtime": 1.628,
     "eval_samples": 277,
-    "eval_samples_per_second": 150.543,
-    "eval_steps_per_second": 4.891,
-    "train_loss": 0.7039596658003958,
-    "train_runtime": 185.7529,
+    "eval_samples_per_second": 170.149,
+    "eval_steps_per_second": 21.499,
+    "train_loss": 0.4925964877136752,
+    "train_runtime": 120.7223,
     "train_samples": 2490,
-    "train_samples_per_second": 53.62,
-    "train_steps_per_second": 0.409
+    "train_samples_per_second": 61.878,
+    "train_steps_per_second": 1.938
 }

config.json

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

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.9,
-    "eval_accuracy": 0.5306859205776173,
-    "eval_loss": 0.6921272277832031,
-    "eval_runtime": 1.84,
+    "epoch": 3.0,
+    "eval_accuracy": 0.703971119133574,
+    "eval_loss": 0.7108999490737915,
+    "eval_runtime": 1.628,
     "eval_samples": 277,
-    "eval_samples_per_second": 150.543,
-    "eval_steps_per_second": 4.891
+    "eval_samples_per_second": 170.149,
+    "eval_steps_per_second": 21.499
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f962d8019acbb96f9b187c15af21271b488974f767a5dbe1269615d01af6f7df
+oid sha256:8ad0b31d43a528f235b2d0a53058a6d07df9d46ea4b8bf48a275a4580cd660c9
 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": 3.9,
-    "train_loss": 0.7039596658003958,
-    "train_runtime": 185.7529,
+    "epoch": 3.0,
+    "train_loss": 0.4925964877136752,
+    "train_runtime": 120.7223,
     "train_samples": 2490,
-    "train_samples_per_second": 53.62,
-    "train_steps_per_second": 0.409
+    "train_samples_per_second": 61.878,
+    "train_steps_per_second": 1.938
 }

trainer_state.json

@@ -1,61 +1,25 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.8974358974358974,
-  "global_step": 76,
+  "epoch": 3.0,
+  "global_step": 234,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.97,
-      "eval_accuracy": 0.516245487364621,
-      "eval_loss": 0.6875916719436646,
-      "eval_runtime": 1.8174,
-      "eval_samples_per_second": 152.416,
-      "eval_steps_per_second": 4.952,
-      "step": 19
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5054151624548736,
-      "eval_loss": 0.6918654441833496,
-      "eval_runtime": 1.809,
-      "eval_samples_per_second": 153.125,
-      "eval_steps_per_second": 4.975,
-      "step": 39
-    },
-    {
-      "epoch": 2.97,
-      "eval_accuracy": 0.5126353790613718,
-      "eval_loss": 0.6949273347854614,
-      "eval_runtime": 1.8221,
-      "eval_samples_per_second": 152.019,
-      "eval_steps_per_second": 4.939,
-      "step": 58
-    },
-    {
-      "epoch": 3.9,
-      "eval_accuracy": 0.5306859205776173,
-      "eval_loss": 0.6921272277832031,
-      "eval_runtime": 1.8199,
-      "eval_samples_per_second": 152.207,
-      "eval_steps_per_second": 4.945,
-      "step": 76
-    },
-    {
-      "epoch": 3.9,
-      "step": 76,
-      "total_flos": 9049053537914880.0,
-      "train_loss": 0.7039596658003958,
-      "train_runtime": 185.7529,
-      "train_samples_per_second": 53.62,
-      "train_steps_per_second": 0.409
+      "epoch": 3.0,
+      "step": 234,
+      "total_flos": 1740381821015040.0,
+      "train_loss": 0.4925964877136752,
+      "train_runtime": 120.7223,
+      "train_samples_per_second": 61.878,
+      "train_steps_per_second": 1.938
     }
   ],
-  "max_steps": 76,
-  "num_train_epochs": 4,
-  "total_flos": 9049053537914880.0,
+  "max_steps": 234,
+  "num_train_epochs": 3,
+  "total_flos": 1740381821015040.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858f7c0aafe56df454bb01f63122dbdf4b1eb9fa3bfb6d2c897479a64adc5260
-size 4155
+oid sha256:e4399aaeb798913062f8219ace308d12474eafbe83a8cc2e0ee9fb2296004ef7
+size 3963