Upload folder using huggingface_hub

README.md

@@ -1,13 +1,28 @@
 ---
+language:
+- en
 license: other
 base_model: facebook/opt-125m
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: opt-125m-boolq
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE BOOLQ
+      type: glue
+      args: boolq
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.690519877675841
 ---
 
 <!-- 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. -->
 
 # opt-125m-boolq
 
-This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the GLUE BOOLQ dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7814
-- Accuracy: 0.6639
+- Loss: 2.0177
+- Accuracy: 0.6905
 
 ## 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 |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.99  | 73   | 0.6819          | 0.6220   |
-| No log        | 1.99  | 147  | 0.6106          | 0.6743   |
-| No log        | 3.0   | 221  | 0.6686          | 0.6679   |
-| No log        | 3.96  | 292  | 0.7814          | 0.6639   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.96,
-    "eval_accuracy": 0.6639143730886851,
-    "eval_loss": 0.7814202904701233,
-    "eval_runtime": 7.2459,
+    "epoch": 5.0,
+    "eval_accuracy": 0.690519877675841,
+    "eval_loss": 2.0176548957824707,
+    "eval_runtime": 4.6528,
     "eval_samples": 3270,
-    "eval_samples_per_second": 451.292,
-    "eval_steps_per_second": 14.215,
-    "train_loss": 0.515642035497378,
-    "train_runtime": 299.1283,
+    "eval_samples_per_second": 702.796,
+    "eval_steps_per_second": 87.903,
+    "train_loss": 0.3138986231917042,
+    "train_runtime": 144.264,
     "train_samples": 9427,
-    "train_samples_per_second": 126.06,
-    "train_steps_per_second": 0.976
+    "train_samples_per_second": 326.727,
+    "train_steps_per_second": 20.449
 }

config.json

@@ -13,16 +13,16 @@
   "enable_bias": true,
   "eos_token_id": 2,
   "ffn_dim": 3072,
-  "finetuning_task": "text-classification",
+  "finetuning_task": "boolq",
   "hidden_size": 768,
   "id2label": {
-    "0": "0",
-    "1": "1"
+    "0": "False",
+    "1": "True"
   },
   "init_std": 0.02,
   "label2id": {
-    "0": 0,
-    "1": 1
+    "False": 0,
+    "True": 1
   },
   "layer_norm_elementwise_affine": true,
   "layerdrop": 0.0,

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.96,
-    "eval_accuracy": 0.6639143730886851,
-    "eval_loss": 0.7814202904701233,
-    "eval_runtime": 7.2459,
+    "epoch": 5.0,
+    "eval_accuracy": 0.690519877675841,
+    "eval_loss": 2.0176548957824707,
+    "eval_runtime": 4.6528,
     "eval_samples": 3270,
-    "eval_samples_per_second": 451.292,
-    "eval_steps_per_second": 14.215
+    "eval_samples_per_second": 702.796,
+    "eval_steps_per_second": 87.903
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22cb5a66fe96bdd6361ca4c8161ebfdf6fdc149aff2efeb229e8f33d8352466d
+oid sha256:9873491ef883a28fc7b16c18de013bd4fe14db9305e43e77ac7314a74a28f27a
 size 501029729

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": 3.96,
-    "train_loss": 0.515642035497378,
-    "train_runtime": 299.1283,
+    "epoch": 5.0,
+    "train_loss": 0.3138986231917042,
+    "train_runtime": 144.264,
     "train_samples": 9427,
-    "train_samples_per_second": 126.06,
-    "train_steps_per_second": 0.976
+    "train_samples_per_second": 326.727,
+    "train_steps_per_second": 20.449
 }

trainer_state.json

@@ -1,61 +1,55 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.959322033898305,
-  "global_step": 292,
+  "epoch": 5.0,
+  "global_step": 2950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.99,
-      "eval_accuracy": 0.6220183486238532,
-      "eval_loss": 0.681908905506134,
-      "eval_runtime": 7.2291,
-      "eval_samples_per_second": 452.336,
-      "eval_steps_per_second": 14.248,
-      "step": 73
+      "epoch": 0.85,
+      "learning_rate": 1.6616949152542374e-05,
+      "loss": 0.6614,
+      "step": 500
     },
     {
-      "epoch": 1.99,
-      "eval_accuracy": 0.6743119266055045,
-      "eval_loss": 0.6105863451957703,
-      "eval_runtime": 7.2547,
-      "eval_samples_per_second": 450.742,
-      "eval_steps_per_second": 14.198,
-      "step": 147
+      "epoch": 1.69,
+      "learning_rate": 1.3227118644067798e-05,
+      "loss": 0.5209,
+      "step": 1000
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.6678899082568808,
-      "eval_loss": 0.668644905090332,
-      "eval_runtime": 7.2653,
-      "eval_samples_per_second": 450.085,
-      "eval_steps_per_second": 14.177,
-      "step": 221
+      "epoch": 2.54,
+      "learning_rate": 9.837288135593221e-06,
+      "loss": 0.3374,
+      "step": 1500
     },
     {
-      "epoch": 3.96,
-      "eval_accuracy": 0.6639143730886851,
-      "eval_loss": 0.7814202904701233,
-      "eval_runtime": 7.2598,
-      "eval_samples_per_second": 450.425,
-      "eval_steps_per_second": 14.188,
-      "step": 292
+      "epoch": 3.39,
+      "learning_rate": 6.461016949152543e-06,
+      "loss": 0.1943,
+      "step": 2000
     },
     {
-      "epoch": 3.96,
-      "step": 292,
-      "total_flos": 9756036776853504.0,
-      "train_loss": 0.515642035497378,
-      "train_runtime": 299.1283,
-      "train_samples_per_second": 126.06,
-      "train_steps_per_second": 0.976
+      "epoch": 4.24,
+      "learning_rate": 3.0711864406779663e-06,
+      "loss": 0.0907,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "step": 2950,
+      "total_flos": 3079055584788480.0,
+      "train_loss": 0.3138986231917042,
+      "train_runtime": 144.264,
+      "train_samples_per_second": 326.727,
+      "train_steps_per_second": 20.449
     }
   ],
-  "max_steps": 292,
-  "num_train_epochs": 4,
-  "total_flos": 9756036776853504.0,
+  "max_steps": 2950,
+  "num_train_epochs": 5,
+  "total_flos": 3079055584788480.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a9f7e79cc343c77d44b33fab7c3b2efae6702863648c2a79ab100546bdca04e
-size 4155
+oid sha256:eb2a3944a92defcf466ae4bd4a269b67a3b743465a077db50a7ff77aa2c8e1b8
+size 3963