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:
 - accuracy
 model-index:
 - name: bert-base-uncased-finetuned-mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8474369406021155
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-uncased-finetuned-mnli
 
-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 MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5565
-- Accuracy: 0.8469
+- Loss: 0.5520
+- Accuracy: 0.8474
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 3.0,
+    "epoch_mm": 3.0,
+    "eval_accuracy": 0.8468670402445236,
+    "eval_accuracy_mm": 0.8474369406021155,
+    "eval_loss": 0.5565051436424255,
+    "eval_loss_mm": 0.5519542098045349,
+    "eval_runtime": 41.7413,
+    "eval_runtime_mm": 41.6975,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 235.139,
+    "eval_samples_per_second_mm": 235.793,
+    "eval_steps_per_second": 29.395,
+    "eval_steps_per_second_mm": 29.474,
+    "total_flos": 3.099754961058632e+17,
+    "train_loss": 0.3580092687494907,
+    "train_runtime": 14713.385,
+    "train_samples": 392702,
+    "train_samples_per_second": 80.07,
+    "train_steps_per_second": 5.004
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "epoch_mm": 3.0,
+    "eval_accuracy": 0.8468670402445236,
+    "eval_accuracy_mm": 0.8474369406021155,
+    "eval_loss": 0.5565051436424255,
+    "eval_loss_mm": 0.5519542098045349,
+    "eval_runtime": 41.7413,
+    "eval_runtime_mm": 41.6975,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 235.139,
+    "eval_samples_per_second_mm": 235.793,
+    "eval_steps_per_second": 29.395,
+    "eval_steps_per_second_mm": 29.474
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3.099754961058632e+17,
+    "train_loss": 0.3580092687494907,
+    "train_runtime": 14713.385,
+    "train_samples": 392702,
+    "train_samples_per_second": 80.07,
+    "train_steps_per_second": 5.004
+}

trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 73632,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.612536430358887,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.5193,
+      "step": 24544
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8372898624554254,
+      "eval_loss": 0.4270987808704376,
+      "eval_runtime": 41.8372,
+      "eval_samples_per_second": 234.6,
+      "eval_steps_per_second": 29.328,
+      "step": 24544
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.1507811546325684,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3333,
+      "step": 49088
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8451349974528782,
+      "eval_loss": 0.4371325969696045,
+      "eval_runtime": 41.4112,
+      "eval_samples_per_second": 237.013,
+      "eval_steps_per_second": 29.63,
+      "step": 49088
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 17.64081573486328,
+      "learning_rate": 0.0,
+      "loss": 0.2214,
+      "step": 73632
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8468670402445236,
+      "eval_loss": 0.5565051436424255,
+      "eval_runtime": 41.8267,
+      "eval_samples_per_second": 234.659,
+      "eval_steps_per_second": 29.335,
+      "step": 73632
+    },
+    {
+      "epoch": 3.0,
+      "step": 73632,
+      "total_flos": 3.099754961058632e+17,
+      "train_loss": 0.3580092687494907,
+      "train_runtime": 14713.385,
+      "train_samples_per_second": 80.07,
+      "train_steps_per_second": 5.004
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 73632,
+  "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": 3.099754961058632e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}