End of training

README.md

@@ -1,13 +1,28 @@
 ---
+language:
+- en
 license: apache-2.0
 base_model: google/fnet-base
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 model-index:
 - name: fnet-base-finetuned-cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.3934207280665654
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fnet-base-finetuned-cola
 
-This model is a fine-tuned version of [google/fnet-base](https://huggingface.co/google/fnet-base) on an unknown dataset.
+This model is a fine-tuned version of [google/fnet-base](https://huggingface.co/google/fnet-base) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6476
 - Matthews Correlation: 0.3934

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 0.5648320913314819,
-    "eval_matthews_correlation": 0.3262988329908328,
-    "eval_runtime": 8.5449,
+    "epoch": 5.0,
+    "eval_loss": 0.6475589275360107,
+    "eval_matthews_correlation": 0.3934207280665654,
+    "eval_runtime": 8.5348,
     "eval_samples": 1043,
-    "eval_samples_per_second": 122.062,
-    "eval_steps_per_second": 7.724,
-    "total_flos": 4562104380880896.0,
-    "train_loss": 0.5235365682573461,
-    "train_runtime": 487.6856,
+    "eval_samples_per_second": 122.206,
+    "eval_steps_per_second": 7.733,
+    "total_flos": 7603507301468160.0,
+    "train_loss": 0.4301326410094304,
+    "train_runtime": 814.307,
     "train_samples": 8551,
-    "train_samples_per_second": 52.602,
-    "train_steps_per_second": 1.649
+    "train_samples_per_second": 52.505,
+    "train_steps_per_second": 1.646
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 0.5648320913314819,
-    "eval_matthews_correlation": 0.3262988329908328,
-    "eval_runtime": 8.5449,
+    "epoch": 5.0,
+    "eval_loss": 0.6475589275360107,
+    "eval_matthews_correlation": 0.3934207280665654,
+    "eval_runtime": 8.5348,
     "eval_samples": 1043,
-    "eval_samples_per_second": 122.062,
-    "eval_steps_per_second": 7.724
+    "eval_samples_per_second": 122.206,
+    "eval_steps_per_second": 7.733
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
-    "total_flos": 4562104380880896.0,
-    "train_loss": 0.5235365682573461,
-    "train_runtime": 487.6856,
+    "epoch": 5.0,
+    "total_flos": 7603507301468160.0,
+    "train_loss": 0.4301326410094304,
+    "train_runtime": 814.307,
     "train_samples": 8551,
-    "train_samples_per_second": 52.602,
-    "train_steps_per_second": 1.649
+    "train_samples_per_second": 52.505,
+    "train_steps_per_second": 1.646
 }

trainer_state.json

@@ -1,75 +1,107 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 804,
+  "global_step": 1340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 6.508703708648682,
-      "learning_rate": 1.3333333333333333e-05,
-      "loss": 0.6101,
+      "grad_norm": 9.199758529663086,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.61,
       "step": 268
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.6032158732414246,
-      "eval_matthews_correlation": 0.1345503796973939,
-      "eval_runtime": 8.5318,
-      "eval_samples_per_second": 122.249,
-      "eval_steps_per_second": 7.736,
+      "eval_loss": 0.581834614276886,
+      "eval_matthews_correlation": 0.1605505486389139,
+      "eval_runtime": 8.5337,
+      "eval_samples_per_second": 122.221,
+      "eval_steps_per_second": 7.734,
       "step": 268
     },
     {
       "epoch": 2.0,
-      "grad_norm": 11.809653282165527,
-      "learning_rate": 6.666666666666667e-06,
-      "loss": 0.5325,
+      "grad_norm": 7.077225685119629,
+      "learning_rate": 1.2e-05,
+      "loss": 0.5265,
       "step": 536
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5451133251190186,
-      "eval_matthews_correlation": 0.3134805838230471,
-      "eval_runtime": 8.5009,
-      "eval_samples_per_second": 122.693,
-      "eval_steps_per_second": 7.764,
+      "eval_loss": 0.5488986968994141,
+      "eval_matthews_correlation": 0.3414642281150747,
+      "eval_runtime": 8.5064,
+      "eval_samples_per_second": 122.614,
+      "eval_steps_per_second": 7.759,
       "step": 536
     },
     {
       "epoch": 3.0,
-      "grad_norm": 9.861120223999023,
-      "learning_rate": 0.0,
-      "loss": 0.428,
+      "grad_norm": 9.864019393920898,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4161,
       "step": 804
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.5648320913314819,
-      "eval_matthews_correlation": 0.3262988329908328,
-      "eval_runtime": 8.5202,
-      "eval_samples_per_second": 122.414,
-      "eval_steps_per_second": 7.746,
+      "eval_loss": 0.5453676581382751,
+      "eval_matthews_correlation": 0.3451229816764349,
+      "eval_runtime": 8.5021,
+      "eval_samples_per_second": 122.676,
+      "eval_steps_per_second": 7.763,
       "step": 804
     },
     {
-      "epoch": 3.0,
-      "step": 804,
-      "total_flos": 4562104380880896.0,
-      "train_loss": 0.5235365682573461,
-      "train_runtime": 487.6856,
-      "train_samples_per_second": 52.602,
-      "train_steps_per_second": 1.649
+      "epoch": 4.0,
+      "grad_norm": 5.3014726638793945,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3324,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.574592113494873,
+      "eval_matthews_correlation": 0.3868717129142223,
+      "eval_runtime": 8.4987,
+      "eval_samples_per_second": 122.724,
+      "eval_steps_per_second": 7.766,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 17.219274520874023,
+      "learning_rate": 0.0,
+      "loss": 0.2657,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6475589275360107,
+      "eval_matthews_correlation": 0.3934207280665654,
+      "eval_runtime": 8.5544,
+      "eval_samples_per_second": 121.926,
+      "eval_steps_per_second": 7.715,
+      "step": 1340
+    },
+    {
+      "epoch": 5.0,
+      "step": 1340,
+      "total_flos": 7603507301468160.0,
+      "train_loss": 0.4301326410094304,
+      "train_runtime": 814.307,
+      "train_samples_per_second": 52.505,
+      "train_steps_per_second": 1.646
     }
   ],
   "logging_steps": 500,
-  "max_steps": 804,
+  "max_steps": 1340,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -83,7 +115,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4562104380880896.0,
+  "total_flos": 7603507301468160.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null