End of training

README.md

@@ -1,12 +1,27 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_sa_GLUE_Experiment_data_aug_qnli_384
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5701995240710233
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_sa_GLUE_Experiment_data_aug_qnli_384
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1939
-- Accuracy: 0.5821
+- Loss: 1.0828
+- Accuracy: 0.5702
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5701995240710233,
+    "eval_loss": 1.0827983617782593,
+    "eval_runtime": 2.4616,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2219.33,
+    "eval_steps_per_second": 8.937,
+    "train_loss": 0.13183473884020716,
+    "train_runtime": 21219.8278,
+    "train_samples": 4250511,
+    "train_samples_per_second": 10015.423,
+    "train_steps_per_second": 39.124
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5701995240710233,
+    "eval_loss": 1.0827983617782593,
+    "eval_runtime": 2.4616,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2219.33,
+    "eval_steps_per_second": 8.937
+}

logs/events.out.tfevents.1675319858.serv-3331.4023797.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e606accf29cb598aab2745ebcc1c1ad849cf2c5279fb9f5145183295d54180ab
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.13183473884020716,
+    "train_runtime": 21219.8278,
+    "train_samples": 4250511,
+    "train_samples_per_second": 10015.423,
+    "train_steps_per_second": 39.124
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 1.0827983617782593,
+  "best_model_checkpoint": "distilbert_sa_GLUE_Experiment_data_aug_qnli_384/checkpoint-16604",
+  "epoch": 6.0,
+  "global_step": 99624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.900030113225729e-05,
+      "loss": 0.4167,
+      "step": 16604
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5701995240710233,
+      "eval_loss": 1.0827983617782593,
+      "eval_runtime": 2.2923,
+      "eval_samples_per_second": 2383.179,
+      "eval_steps_per_second": 9.597,
+      "step": 16604
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.800072271741749e-05,
+      "loss": 0.1701,
+      "step": 33208
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5731283177741168,
+      "eval_loss": 1.3571923971176147,
+      "eval_runtime": 2.2994,
+      "eval_samples_per_second": 2375.792,
+      "eval_steps_per_second": 9.568,
+      "step": 33208
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.700120452902915e-05,
+      "loss": 0.0922,
+      "step": 49812
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5797181036060772,
+      "eval_loss": 1.7374392747879028,
+      "eval_runtime": 2.351,
+      "eval_samples_per_second": 2323.648,
+      "eval_steps_per_second": 9.358,
+      "step": 49812
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600162611418935e-05,
+      "loss": 0.0536,
+      "step": 66416
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5817316492769541,
+      "eval_loss": 1.6714555025100708,
+      "eval_runtime": 2.3391,
+      "eval_samples_per_second": 2335.546,
+      "eval_steps_per_second": 9.405,
+      "step": 66416
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5002107925801014e-05,
+      "loss": 0.0342,
+      "step": 83020
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5817316492769541,
+      "eval_loss": 1.9659866094589233,
+      "eval_runtime": 2.2977,
+      "eval_samples_per_second": 2377.636,
+      "eval_steps_per_second": 9.575,
+      "step": 83020
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.400252951096122e-05,
+      "loss": 0.0242,
+      "step": 99624
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5820977484898407,
+      "eval_loss": 2.1939027309417725,
+      "eval_runtime": 2.2807,
+      "eval_samples_per_second": 2395.361,
+      "eval_steps_per_second": 9.646,
+      "step": 99624
+    },
+    {
+      "epoch": 6.0,
+      "step": 99624,
+      "total_flos": 7.005359837533962e+17,
+      "train_loss": 0.13183473884020716,
+      "train_runtime": 21219.8278,
+      "train_samples_per_second": 10015.423,
+      "train_steps_per_second": 39.124
+    }
+  ],
+  "max_steps": 830200,
+  "num_train_epochs": 50,
+  "total_flos": 7.005359837533962e+17,
+  "trial_name": null,
+  "trial_params": null
+}