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_96
-  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_96
 
-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: 1.4578
-- Accuracy: 0.5662
+- Loss: 0.9096
+- Accuracy: 0.5702
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5701995240710233,
+    "eval_loss": 0.9095715880393982,
+    "eval_runtime": 1.9364,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2821.157,
+    "eval_steps_per_second": 11.361,
+    "train_loss": 0.28817050351509177,
+    "train_runtime": 14652.0321,
+    "train_samples": 4250511,
+    "train_samples_per_second": 14504.851,
+    "train_steps_per_second": 56.661
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5701995240710233,
+    "eval_loss": 0.9095715880393982,
+    "eval_runtime": 1.9364,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2821.157,
+    "eval_steps_per_second": 11.361
+}

logs/events.out.tfevents.1675314170.serv-3331.4030209.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48603bc2a9ba1fb1c6c48293735a3fc7189f599b789686ee10f764d962af8b1
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.28817050351509177,
+    "train_runtime": 14652.0321,
+    "train_samples": 4250511,
+    "train_samples_per_second": 14504.851,
+    "train_steps_per_second": 56.661
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.9095715880393982,
+  "best_model_checkpoint": "distilbert_sa_GLUE_Experiment_data_aug_qnli_96/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": 0.5397,
+      "step": 16604
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5701995240710233,
+      "eval_loss": 0.9095715880393982,
+      "eval_runtime": 1.8571,
+      "eval_samples_per_second": 2941.626,
+      "eval_steps_per_second": 11.846,
+      "step": 16604
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.800078294386895e-05,
+      "loss": 0.3675,
+      "step": 33208
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5595826468973092,
+      "eval_loss": 1.0680475234985352,
+      "eval_runtime": 1.9538,
+      "eval_samples_per_second": 2796.058,
+      "eval_steps_per_second": 11.26,
+      "step": 33208
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7001264755480614e-05,
+      "loss": 0.2735,
+      "step": 49812
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5652571846970529,
+      "eval_loss": 1.1893354654312134,
+      "eval_runtime": 1.8852,
+      "eval_samples_per_second": 2897.785,
+      "eval_steps_per_second": 11.67,
+      "step": 49812
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600162611418935e-05,
+      "loss": 0.2174,
+      "step": 66416
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5643419366648361,
+      "eval_loss": 1.2806222438812256,
+      "eval_runtime": 1.8586,
+      "eval_samples_per_second": 2939.371,
+      "eval_steps_per_second": 11.837,
+      "step": 66416
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.500204769934956e-05,
+      "loss": 0.1795,
+      "step": 83020
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5648910854841662,
+      "eval_loss": 1.411848783493042,
+      "eval_runtime": 1.8614,
+      "eval_samples_per_second": 2934.843,
+      "eval_steps_per_second": 11.819,
+      "step": 83020
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4002469284509754e-05,
+      "loss": 0.1514,
+      "step": 99624
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5661724327292696,
+      "eval_loss": 1.4577802419662476,
+      "eval_runtime": 1.8504,
+      "eval_samples_per_second": 2952.272,
+      "eval_steps_per_second": 11.889,
+      "step": 99624
+    },
+    {
+      "epoch": 6.0,
+      "step": 99624,
+      "total_flos": 1.4859939592588493e+17,
+      "train_loss": 0.28817050351509177,
+      "train_runtime": 14652.0321,
+      "train_samples_per_second": 14504.851,
+      "train_steps_per_second": 56.661
+    }
+  ],
+  "max_steps": 830200,
+  "num_train_epochs": 50,
+  "total_flos": 1.4859939592588493e+17,
+  "trial_name": null,
+  "trial_params": null
+}