End of training

README.md

@@ -1,13 +1,31 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: distilbert_sa_GLUE_Experiment_data_aug_qqp_256
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7887954489240663
+    - name: F1
+      type: f1
+      value: 0.7301115711621732
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,12 +33,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_sa_GLUE_Experiment_data_aug_qqp_256
 
-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 QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8332
-- Accuracy: 0.8044
-- F1: 0.7379
-- Combined Score: 0.7711
+- Loss: 0.5126
+- Accuracy: 0.7888
+- F1: 0.7301
+- Combined Score: 0.7595
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.7887954489240663,
+    "eval_combined_score": 0.7594535100431197,
+    "eval_f1": 0.7301115711621732,
+    "eval_loss": 0.5126270055770874,
+    "eval_runtime": 29.318,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 1379.014,
+    "eval_steps_per_second": 5.389,
+    "train_loss": 0.16987583515715401,
+    "train_runtime": 50655.2686,
+    "train_samples": 7595601,
+    "train_samples_per_second": 7497.346,
+    "train_steps_per_second": 29.287
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.7887954489240663,
+    "eval_combined_score": 0.7594535100431197,
+    "eval_f1": 0.7301115711621732,
+    "eval_loss": 0.5126270055770874,
+    "eval_runtime": 29.318,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 1379.014,
+    "eval_steps_per_second": 5.389
+}

logs/events.out.tfevents.1675712417.serv-3330.104899.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e79f18f45409539e5cfd3c058d93c618d27574aaf7c89e01bcda36b10df834e
+size 475

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.16987583515715401,
+    "train_runtime": 50655.2686,
+    "train_samples": 7595601,
+    "train_samples_per_second": 7497.346,
+    "train_steps_per_second": 29.287
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.5126270055770874,
+  "best_model_checkpoint": "distilbert_sa_GLUE_Experiment_data_aug_qqp_256/checkpoint-29671",
+  "epoch": 6.0,
+  "global_step": 178026,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.900033702942267e-05,
+      "loss": 0.3952,
+      "step": 29671
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7887954489240663,
+      "eval_combined_score": 0.7594535100431197,
+      "eval_f1": 0.7301115711621732,
+      "eval_loss": 0.5126270055770874,
+      "eval_runtime": 29.5581,
+      "eval_samples_per_second": 1367.815,
+      "eval_steps_per_second": 5.345,
+      "step": 29671
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8000808870614404e-05,
+      "loss": 0.2233,
+      "step": 59342
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7960178085580015,
+      "eval_combined_score": 0.7653223515229433,
+      "eval_f1": 0.7346268944878849,
+      "eval_loss": 0.5941275954246521,
+      "eval_runtime": 29.386,
+      "eval_samples_per_second": 1375.825,
+      "eval_steps_per_second": 5.377,
+      "step": 59342
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.700131441474841e-05,
+      "loss": 0.147,
+      "step": 89013
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7996537224833045,
+      "eval_combined_score": 0.7668394047498941,
+      "eval_f1": 0.7340250870164838,
+      "eval_loss": 0.6602815985679626,
+      "eval_runtime": 29.2551,
+      "eval_samples_per_second": 1381.981,
+      "eval_steps_per_second": 5.401,
+      "step": 89013
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.6001786255940145e-05,
+      "loss": 0.1067,
+      "step": 118684
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.801187237200099,
+      "eval_combined_score": 0.7693823877805914,
+      "eval_f1": 0.737577538361084,
+      "eval_loss": 0.7090513110160828,
+      "eval_runtime": 29.4929,
+      "eval_samples_per_second": 1370.841,
+      "eval_steps_per_second": 5.357,
+      "step": 118684
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.500229180007415e-05,
+      "loss": 0.082,
+      "step": 148355
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7999505317833292,
+      "eval_combined_score": 0.7688298514410226,
+      "eval_f1": 0.7377091710987158,
+      "eval_loss": 0.8757410645484924,
+      "eval_runtime": 29.0987,
+      "eval_samples_per_second": 1389.41,
+      "eval_steps_per_second": 5.43,
+      "step": 148355
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.400269623538135e-05,
+      "loss": 0.0652,
+      "step": 178026
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8043779371753649,
+      "eval_combined_score": 0.7711193984706826,
+      "eval_f1": 0.7378608597660004,
+      "eval_loss": 0.8331958055496216,
+      "eval_runtime": 29.279,
+      "eval_samples_per_second": 1380.855,
+      "eval_steps_per_second": 5.396,
+      "step": 178026
+    },
+    {
+      "epoch": 6.0,
+      "step": 178026,
+      "total_flos": 7.776503176668119e+17,
+      "train_loss": 0.16987583515715401,
+      "train_runtime": 50655.2686,
+      "train_samples_per_second": 7497.346,
+      "train_steps_per_second": 29.287
+    }
+  ],
+  "max_steps": 1483550,
+  "num_train_epochs": 50,
+  "total_flos": 7.776503176668119e+17,
+  "trial_name": null,
+  "trial_params": null
+}