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 SST2
       type: glue
       config: sst2
       split: validation
@@ -28,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_no_pretrain_sst2
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6970
+- Loss: 0.6954
 - Accuracy: 0.5092
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5091743119266054,
+    "eval_loss": 0.6953763365745544,
+    "eval_runtime": 1.5195,
+    "eval_samples": 872,
+    "eval_samples_per_second": 573.888,
+    "eval_steps_per_second": 4.607,
+    "train_loss": 0.6925539640787011,
+    "train_runtime": 2513.0909,
+    "train_samples": 67349,
+    "train_samples_per_second": 1339.963,
+    "train_steps_per_second": 10.485
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5091743119266054,
+    "eval_loss": 0.6953763365745544,
+    "eval_runtime": 1.5195,
+    "eval_samples": 872,
+    "eval_samples_per_second": 573.888,
+    "eval_steps_per_second": 4.607
+}

logs/events.out.tfevents.1685358970.serv-9225.2840720.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99511b28e13470eecc87061379d583aab36fbab50ee19a7bf510599e3ddaea3
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.6925539640787011,
+    "train_runtime": 2513.0909,
+    "train_samples": 67349,
+    "train_samples_per_second": 1339.963,
+    "train_steps_per_second": 10.485
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.6953763365745544,
+  "best_model_checkpoint": "hBERTv1_no_pretrain_sst2/checkpoint-1054",
+  "epoch": 7.0,
+  "global_step": 3689,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0004900379506641366,
+      "loss": 0.7262,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6957851052284241,
+      "eval_runtime": 1.5307,
+      "eval_samples_per_second": 569.664,
+      "eval_steps_per_second": 4.573,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00048003795066413666,
+      "loss": 0.6878,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6953763365745544,
+      "eval_runtime": 1.5334,
+      "eval_samples_per_second": 568.671,
+      "eval_steps_per_second": 4.565,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00047003795066413663,
+      "loss": 0.687,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.7005088925361633,
+      "eval_runtime": 1.5295,
+      "eval_samples_per_second": 570.132,
+      "eval_steps_per_second": 4.577,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0004600379506641366,
+      "loss": 0.6868,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6974157094955444,
+      "eval_runtime": 1.531,
+      "eval_samples_per_second": 569.563,
+      "eval_steps_per_second": 4.572,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00045003795066413663,
+      "loss": 0.6868,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6966003775596619,
+      "eval_runtime": 1.5282,
+      "eval_samples_per_second": 570.611,
+      "eval_steps_per_second": 4.581,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00044003795066413666,
+      "loss": 0.6868,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6974246501922607,
+      "eval_runtime": 1.5339,
+      "eval_samples_per_second": 568.489,
+      "eval_steps_per_second": 4.564,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00043003795066413663,
+      "loss": 0.6865,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6969632506370544,
+      "eval_runtime": 1.532,
+      "eval_samples_per_second": 569.18,
+      "eval_steps_per_second": 4.569,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "step": 3689,
+      "total_flos": 6.981918485852979e+16,
+      "train_loss": 0.6925539640787011,
+      "train_runtime": 2513.0909,
+      "train_samples_per_second": 1339.963,
+      "train_steps_per_second": 10.485
+    }
+  ],
+  "max_steps": 26350,
+  "num_train_epochs": 50,
+  "total_flos": 6.981918485852979e+16,
+  "trial_name": null,
+  "trial_params": null
+}