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_mnli_96
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.565500406834825
 ---
 
 <!-- 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_mnli_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 MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1396
-- Accuracy: 0.5795
+- Loss: 0.9477
+- Accuracy: 0.5655
 
 ## Model description
 

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 6.0,
+    "epoch_mm": 6.0,
+    "eval_accuracy": 0.5686194600101885,
+    "eval_accuracy_mm": 0.565500406834825,
+    "eval_loss": 0.9328168630599976,
+    "eval_loss_mm": 0.9477424025535583,
+    "eval_runtime": 6.259,
+    "eval_runtime_mm": 6.35,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1568.132,
+    "eval_samples_per_second_mm": 1548.349,
+    "eval_steps_per_second": 6.231,
+    "eval_steps_per_second_mm": 6.142,
+    "train_loss": 0.7230182159139101,
+    "train_runtime": 46377.2172,
+    "train_samples": 8048562,
+    "train_samples_per_second": 8677.28,
+    "train_steps_per_second": 33.896
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "epoch_mm": 6.0,
+    "eval_accuracy": 0.5686194600101885,
+    "eval_accuracy_mm": 0.565500406834825,
+    "eval_loss": 0.9328168630599976,
+    "eval_loss_mm": 0.9477424025535583,
+    "eval_runtime": 6.259,
+    "eval_runtime_mm": 6.35,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1568.132,
+    "eval_samples_per_second_mm": 1548.349,
+    "eval_steps_per_second": 6.231,
+    "eval_steps_per_second_mm": 6.142
+}

logs/events.out.tfevents.1675476950.serv-3332.2907171.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d84c0f56c1f7f0eec5c272b226f36311b0f75a8005a7e8d12da37eff6e41e6
+size 698

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.7230182159139101,
+    "train_runtime": 46377.2172,
+    "train_samples": 8048562,
+    "train_samples_per_second": 8677.28,
+    "train_steps_per_second": 33.896
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.9328168630599976,
+  "best_model_checkpoint": "distilbert_sa_GLUE_Experiment_data_aug_mnli_96/checkpoint-31440",
+  "epoch": 6.0,
+  "global_step": 188640,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.900028625954199e-05,
+      "loss": 0.9142,
+      "step": 31440
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5686194600101885,
+      "eval_loss": 0.9328168630599976,
+      "eval_runtime": 6.4992,
+      "eval_samples_per_second": 1510.195,
+      "eval_steps_per_second": 6.001,
+      "step": 31440
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8000731552162856e-05,
+      "loss": 0.8099,
+      "step": 62880
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5752419765664799,
+      "eval_loss": 0.9523168802261353,
+      "eval_runtime": 6.3789,
+      "eval_samples_per_second": 1538.662,
+      "eval_steps_per_second": 6.114,
+      "step": 62880
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7001145038167944e-05,
+      "loss": 0.7371,
+      "step": 94320
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.573713703515028,
+      "eval_loss": 1.007168173789978,
+      "eval_runtime": 6.2854,
+      "eval_samples_per_second": 1561.551,
+      "eval_steps_per_second": 6.205,
+      "step": 94320
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.6001526717557254e-05,
+      "loss": 0.6756,
+      "step": 125760
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5750382068262863,
+      "eval_loss": 1.060626745223999,
+      "eval_runtime": 6.3969,
+      "eval_samples_per_second": 1534.325,
+      "eval_steps_per_second": 6.097,
+      "step": 125760
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.500194020356234e-05,
+      "loss": 0.6229,
+      "step": 157200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5739174732552216,
+      "eval_loss": 1.111612319946289,
+      "eval_runtime": 6.3646,
+      "eval_samples_per_second": 1542.126,
+      "eval_steps_per_second": 6.128,
+      "step": 157200
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.400232188295166e-05,
+      "loss": 0.5784,
+      "step": 188640
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5795211411105451,
+      "eval_loss": 1.1395729780197144,
+      "eval_runtime": 6.2786,
+      "eval_samples_per_second": 1563.255,
+      "eval_steps_per_second": 6.212,
+      "step": 188640
+    },
+    {
+      "epoch": 6.0,
+      "step": 188640,
+      "total_flos": 2.8138783182422016e+17,
+      "train_loss": 0.7230182159139101,
+      "train_runtime": 46377.2172,
+      "train_samples_per_second": 8677.28,
+      "train_steps_per_second": 33.896
+    }
+  ],
+  "max_steps": 1572000,
+  "num_train_epochs": 50,
+  "total_flos": 2.8138783182422016e+17,
+  "trial_name": null,
+  "trial_params": null
+}