End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE QNLI
       type: glue
       config: qnli
       split: validation
@@ -29,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_add_GLUE_Experiment_qnli_128
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the glue dataset.
+This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6931
 - Accuracy: 0.5054

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930947303771973,
+    "eval_runtime": 9.4077,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 580.693,
+    "eval_steps_per_second": 4.571,
+    "train_loss": 0.6931800702552655,
+    "train_runtime": 4355.0892,
+    "train_samples": 104743,
+    "train_samples_per_second": 1202.536,
+    "train_steps_per_second": 9.403
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930947303771973,
+    "eval_runtime": 9.4077,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 580.693,
+    "eval_steps_per_second": 4.571
+}

logs/events.out.tfevents.1674741429.gera.2822633.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108f4f6a6ff839188d48cd25d5fde5405f62dc9f35993ffe34ce0c515f21c7dc
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 0.6931800702552655,
+    "train_runtime": 4355.0892,
+    "train_samples": 104743,
+    "train_samples_per_second": 1202.536,
+    "train_steps_per_second": 9.403
+}

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": 0.6930947303771973,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_qnli_128/checkpoint-2457",
+  "epoch": 8.0,
+  "global_step": 6552,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6933,
+      "step": 819
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6931872367858887,
+      "eval_runtime": 9.484,
+      "eval_samples_per_second": 576.021,
+      "eval_steps_per_second": 4.534,
+      "step": 819
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6932,
+      "step": 1638
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6932188868522644,
+      "eval_runtime": 9.4261,
+      "eval_samples_per_second": 579.563,
+      "eval_steps_per_second": 4.562,
+      "step": 1638
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6932,
+      "step": 2457
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930947303771973,
+      "eval_runtime": 9.4523,
+      "eval_samples_per_second": 577.956,
+      "eval_steps_per_second": 4.549,
+      "step": 2457
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6932,
+      "step": 3276
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6932775974273682,
+      "eval_runtime": 9.6547,
+      "eval_samples_per_second": 565.836,
+      "eval_steps_per_second": 4.454,
+      "step": 3276
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6932,
+      "step": 4095
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931426525115967,
+      "eval_runtime": 9.4692,
+      "eval_samples_per_second": 576.924,
+      "eval_steps_per_second": 4.541,
+      "step": 4095
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6932,
+      "step": 4914
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931297779083252,
+      "eval_runtime": 9.4468,
+      "eval_samples_per_second": 578.291,
+      "eval_steps_per_second": 4.552,
+      "step": 4914
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6932,
+      "step": 5733
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931160688400269,
+      "eval_runtime": 9.568,
+      "eval_samples_per_second": 570.963,
+      "eval_steps_per_second": 4.494,
+      "step": 5733
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6932,
+      "step": 6552
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931292414665222,
+      "eval_runtime": 9.4706,
+      "eval_samples_per_second": 576.838,
+      "eval_steps_per_second": 4.54,
+      "step": 6552
+    },
+    {
+      "epoch": 8.0,
+      "step": 6552,
+      "total_flos": 2.0003934735171584e+16,
+      "train_loss": 0.6931800702552655,
+      "train_runtime": 4355.0892,
+      "train_samples_per_second": 1202.536,
+      "train_steps_per_second": 9.403
+    }
+  ],
+  "max_steps": 40950,
+  "num_train_epochs": 50,
+  "total_flos": 2.0003934735171584e+16,
+  "trial_name": null,
+  "trial_params": null
+}