Upload folder using huggingface_hub

README.md

@@ -1,13 +1,28 @@
 ---
+language:
+- en
 license: other
 base_model: facebook/opt-350m
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: opt-350m-boolq
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE BOOLQ
+      type: glue
+      args: boolq
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6975535168195719
 ---
 
 <!-- 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-350m-boolq
 
-This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the GLUE BOOLQ dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8184
-- Accuracy: 0.6743
+- Loss: 2.2006
+- Accuracy: 0.6976
 
 ## 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   | 0.7308          | 0.6217   |
-| No log        | 1.99  | 147  | 0.6529          | 0.6159   |
-| No log        | 3.0   | 221  | 0.6295          | 0.6844   |
-| No log        | 3.96  | 292  | 0.8184          | 0.6743   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.96,
-    "eval_accuracy": 0.6743119266055045,
-    "eval_loss": 0.8184447884559631,
-    "eval_runtime": 20.0092,
+    "epoch": 5.0,
+    "eval_accuracy": 0.6975535168195719,
+    "eval_loss": 2.200601100921631,
+    "eval_runtime": 8.7053,
     "eval_samples": 3270,
-    "eval_samples_per_second": 163.425,
-    "eval_steps_per_second": 5.148,
-    "train_loss": 0.5905772692536655,
-    "train_runtime": 808.3468,
+    "eval_samples_per_second": 375.632,
+    "eval_steps_per_second": 46.983,
+    "train_loss": 0.36301778308415816,
+    "train_runtime": 286.6652,
     "train_samples": 9427,
-    "train_samples_per_second": 46.648,
-    "train_steps_per_second": 0.361
+    "train_samples_per_second": 164.425,
+    "train_steps_per_second": 10.291
 }

config.json

@@ -13,16 +13,16 @@
   "enable_bias": true,
   "eos_token_id": 2,
   "ffn_dim": 4096,
-  "finetuning_task": "text-classification",
+  "finetuning_task": "boolq",
   "hidden_size": 1024,
   "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": 0.6743119266055045,
-    "eval_loss": 0.8184447884559631,
-    "eval_runtime": 20.0092,
+    "epoch": 5.0,
+    "eval_accuracy": 0.6975535168195719,
+    "eval_loss": 2.200601100921631,
+    "eval_runtime": 8.7053,
     "eval_samples": 3270,
-    "eval_samples_per_second": 163.425,
-    "eval_steps_per_second": 5.148
+    "eval_samples_per_second": 375.632,
+    "eval_steps_per_second": 46.983
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a6a93adcfcb70e04216e6d803ce1a57eaae3fadb2a34d8bb71b6f7e52a7c15
+oid sha256:5f39da6a4f3fb08f11e4661b20108331dbade5f4549ff096f0c35b1f6737e791
 size 1324921569

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": 0.5905772692536655,
-    "train_runtime": 808.3468,
+    "epoch": 5.0,
+    "train_loss": 0.36301778308415816,
+    "train_runtime": 286.6652,
     "train_samples": 9427,
-    "train_samples_per_second": 46.648,
-    "train_steps_per_second": 0.361
+    "train_samples_per_second": 164.425,
+    "train_steps_per_second": 10.291
 }

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": 0.6217125382262997,
-      "eval_loss": 0.7307831645011902,
-      "eval_runtime": 20.3283,
-      "eval_samples_per_second": 160.859,
-      "eval_steps_per_second": 5.067,
-      "step": 73
+      "epoch": 0.85,
+      "learning_rate": 1.663050847457627e-05,
+      "loss": 0.7248,
+      "step": 500
     },
     {
-      "epoch": 1.99,
-      "eval_accuracy": 0.6159021406727829,
-      "eval_loss": 0.6529456377029419,
-      "eval_runtime": 20.3385,
-      "eval_samples_per_second": 160.779,
-      "eval_steps_per_second": 5.064,
-      "step": 147
+      "epoch": 1.69,
+      "learning_rate": 1.3240677966101696e-05,
+      "loss": 0.5954,
+      "step": 1000
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.6844036697247706,
-      "eval_loss": 0.6294939517974854,
-      "eval_runtime": 20.3517,
-      "eval_samples_per_second": 160.674,
-      "eval_steps_per_second": 5.061,
-      "step": 221
+      "epoch": 2.54,
+      "learning_rate": 9.85084745762712e-06,
+      "loss": 0.4047,
+      "step": 1500
     },
     {
-      "epoch": 3.96,
-      "eval_accuracy": 0.6743119266055045,
-      "eval_loss": 0.8184447884559631,
-      "eval_runtime": 20.3635,
-      "eval_samples_per_second": 160.582,
-      "eval_steps_per_second": 5.058,
-      "step": 292
+      "epoch": 3.39,
+      "learning_rate": 6.461016949152543e-06,
+      "loss": 0.2393,
+      "step": 2000
     },
     {
-      "epoch": 3.96,
-      "step": 292,
-      "total_flos": 3.4795051274993664e+16,
-      "train_loss": 0.5905772692536655,
-      "train_runtime": 808.3468,
-      "train_samples_per_second": 46.648,
-      "train_steps_per_second": 0.361
+      "epoch": 4.24,
+      "learning_rate": 3.0711864406779663e-06,
+      "loss": 0.1266,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "step": 2950,
+      "total_flos": 1.098149785632768e+16,
+      "train_loss": 0.36301778308415816,
+      "train_runtime": 286.6652,
+      "train_samples_per_second": 164.425,
+      "train_steps_per_second": 10.291
     }
   ],
-  "max_steps": 292,
-  "num_train_epochs": 4,
-  "total_flos": 3.4795051274993664e+16,
+  "max_steps": 2950,
+  "num_train_epochs": 5,
+  "total_flos": 1.098149785632768e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b02a1e90c22ba522739491abaa691dae02d224ee51efe1de4f38bb24a7214a28
-size 4155
+oid sha256:d27e70519ec88117f900ccffa31d3ba03a4c990cc12f6fba3abd1a46af73f1ec
+size 3963