End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 model-index:
 - name: bert-base-uncased-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: 0.5577353353156735
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-uncased-finetuned-cola
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6564
 - Matthews Correlation: 0.5577

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6564142107963562,
+    "eval_matthews_correlation": 0.5577353353156735,
+    "eval_runtime": 4.4814,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 232.741,
+    "eval_steps_per_second": 29.232,
+    "total_flos": 6749587903150080.0,
+    "train_loss": 0.31938580189167154,
+    "train_runtime": 346.8226,
+    "train_samples": 8551,
+    "train_samples_per_second": 73.966,
+    "train_steps_per_second": 4.628
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6564142107963562,
+    "eval_matthews_correlation": 0.5577353353156735,
+    "eval_runtime": 4.4814,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 232.741,
+    "eval_steps_per_second": 29.232
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 6749587903150080.0,
+    "train_loss": 0.31938580189167154,
+    "train_runtime": 346.8226,
+    "train_samples": 8551,
+    "train_samples_per_second": 73.966,
+    "train_steps_per_second": 4.628
+}

trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1605,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 14.7899808883667,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.4866,
+      "step": 535
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.42115479707717896,
+      "eval_matthews_correlation": 0.5497032501894998,
+      "eval_runtime": 4.7251,
+      "eval_samples_per_second": 220.738,
+      "eval_steps_per_second": 27.724,
+      "step": 535
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 33.17850112915039,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.2848,
+      "step": 1070
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5097023844718933,
+      "eval_matthews_correlation": 0.5726999708077573,
+      "eval_runtime": 4.4553,
+      "eval_samples_per_second": 234.104,
+      "eval_steps_per_second": 29.403,
+      "step": 1070
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3264881372451782,
+      "learning_rate": 0.0,
+      "loss": 0.1867,
+      "step": 1605
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6564142107963562,
+      "eval_matthews_correlation": 0.5577353353156735,
+      "eval_runtime": 4.4818,
+      "eval_samples_per_second": 232.721,
+      "eval_steps_per_second": 29.23,
+      "step": 1605
+    },
+    {
+      "epoch": 3.0,
+      "step": 1605,
+      "total_flos": 6749587903150080.0,
+      "train_loss": 0.31938580189167154,
+      "train_runtime": 346.8226,
+      "train_samples_per_second": 73.966,
+      "train_steps_per_second": 4.628
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6749587903150080.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}