End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -12,7 +14,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE QNLI
       type: glue
       config: qnli
       split: validation
@@ -28,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # add_BERT_no_pretrain_qnli
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the glue dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6933
+- Loss: 0.6930
 - Accuracy: 0.5054
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930387616157532,
+    "eval_runtime": 8.4832,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 643.979,
+    "eval_steps_per_second": 5.069,
+    "train_loss": 0.697838950555015,
+    "train_runtime": 2914.3249,
+    "train_samples": 104743,
+    "train_samples_per_second": 1797.037,
+    "train_steps_per_second": 14.051
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930387616157532,
+    "eval_runtime": 8.4832,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 643.979,
+    "eval_steps_per_second": 5.069
+}

logs/events.out.tfevents.1685340641.serv-9215.1440072.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c461ef7d9da38ee4e1b42ce41d4049f940ca99bfdef7b25adf8eeda1594549
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.697838950555015,
+    "train_runtime": 2914.3249,
+    "train_samples": 104743,
+    "train_samples_per_second": 1797.037,
+    "train_steps_per_second": 14.051
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6930387616157532,
+  "best_model_checkpoint": "add_BERT_no_pretrain_qnli/checkpoint-819",
+  "epoch": 6.0,
+  "global_step": 4914,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0004900366300366301,
+      "loss": 0.7205,
+      "step": 819
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930387616157532,
+      "eval_runtime": 8.5235,
+      "eval_samples_per_second": 640.931,
+      "eval_steps_per_second": 5.045,
+      "step": 819
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00048003663003663005,
+      "loss": 0.6935,
+      "step": 1638
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930967569351196,
+      "eval_runtime": 8.519,
+      "eval_samples_per_second": 641.274,
+      "eval_steps_per_second": 5.048,
+      "step": 1638
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00047003663003663003,
+      "loss": 0.6932,
+      "step": 2457
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930704116821289,
+      "eval_runtime": 8.5483,
+      "eval_samples_per_second": 639.078,
+      "eval_steps_per_second": 5.03,
+      "step": 2457
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00046003663003663006,
+      "loss": 0.6932,
+      "step": 3276
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6931969523429871,
+      "eval_runtime": 8.5019,
+      "eval_samples_per_second": 642.559,
+      "eval_steps_per_second": 5.058,
+      "step": 3276
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00045003663003663003,
+      "loss": 0.6932,
+      "step": 4095
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931020617485046,
+      "eval_runtime": 8.5439,
+      "eval_samples_per_second": 639.401,
+      "eval_steps_per_second": 5.033,
+      "step": 4095
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00044003663003663,
+      "loss": 0.6935,
+      "step": 4914
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6933435797691345,
+      "eval_runtime": 8.5341,
+      "eval_samples_per_second": 640.137,
+      "eval_steps_per_second": 5.039,
+      "step": 4914
+    },
+    {
+      "epoch": 6.0,
+      "step": 4914,
+      "total_flos": 8.975886795669504e+16,
+      "train_loss": 0.697838950555015,
+      "train_runtime": 2914.3249,
+      "train_samples_per_second": 1797.037,
+      "train_steps_per_second": 14.051
+    }
+  ],
+  "max_steps": 40950,
+  "num_train_epochs": 50,
+  "total_flos": 8.975886795669504e+16,
+  "trial_name": null,
+  "trial_params": null
+}