End of training

README.md

@@ -1,12 +1,27 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: mobilebert_sa_GLUE_Experiment_data_aug_stsb_256
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.1663132925626873
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,12 +29,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_data_aug_stsb_256
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on an unknown dataset.
+This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.9109
-- Pearson: 0.1632
-- Spearmanr: 0.1691
-- Combined Score: 0.1661
+- Loss: 2.7922
+- Pearson: 0.1559
+- Spearmanr: 0.1663
+- Combined Score: 0.1611
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 7.0,
+    "eval_combined_score": 0.16113036482362375,
+    "eval_loss": 2.7922346591949463,
+    "eval_pearson": 0.15594743708456024,
+    "eval_runtime": 2.2061,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 679.944,
+    "eval_spearmanr": 0.1663132925626873,
+    "eval_steps_per_second": 5.44,
+    "train_loss": 0.4518196766484437,
+    "train_runtime": 11070.8008,
+    "train_samples": 322247,
+    "train_samples_per_second": 1455.392,
+    "train_steps_per_second": 11.372
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_combined_score": 0.16113036482362375,
+    "eval_loss": 2.7922346591949463,
+    "eval_pearson": 0.15594743708456024,
+    "eval_runtime": 2.2061,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 679.944,
+    "eval_spearmanr": 0.1663132925626873,
+    "eval_steps_per_second": 5.44
+}

logs/events.out.tfevents.1675444601.serv-3329.2663131.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e577d31c6d88dbf93523ffefc87bdc56bab32f65977cd33985bb2904eefc497
+size 481

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.4518196766484437,
+    "train_runtime": 11070.8008,
+    "train_samples": 322247,
+    "train_samples_per_second": 1455.392,
+    "train_steps_per_second": 11.372
+}

trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 2.7922346591949463,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_stsb_256/checkpoint-5036",
+  "epoch": 7.0,
+  "global_step": 17626,
+  "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": 1.0735,
+      "step": 2518
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.1758629659576597,
+      "eval_loss": 2.8240866661071777,
+      "eval_pearson": 0.16641833622575744,
+      "eval_runtime": 2.1478,
+      "eval_samples_per_second": 698.375,
+      "eval_spearmanr": 0.18530759568956198,
+      "eval_steps_per_second": 5.587,
+      "step": 2518
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6303,
+      "step": 5036
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.16113036482362375,
+      "eval_loss": 2.7922346591949463,
+      "eval_pearson": 0.15594743708456024,
+      "eval_runtime": 2.1418,
+      "eval_samples_per_second": 700.341,
+      "eval_spearmanr": 0.1663132925626873,
+      "eval_steps_per_second": 5.603,
+      "step": 5036
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.501,
+      "step": 7554
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.16101797610988475,
+      "eval_loss": 3.093930721282959,
+      "eval_pearson": 0.15904807653977932,
+      "eval_runtime": 2.5433,
+      "eval_samples_per_second": 589.782,
+      "eval_spearmanr": 0.16298787567999018,
+      "eval_steps_per_second": 4.718,
+      "step": 7554
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3527,
+      "step": 10072
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.16887284041784573,
+      "eval_loss": 3.228435516357422,
+      "eval_pearson": 0.16622200211961496,
+      "eval_runtime": 2.1395,
+      "eval_samples_per_second": 701.112,
+      "eval_spearmanr": 0.17152367871607652,
+      "eval_steps_per_second": 5.609,
+      "step": 10072
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.255,
+      "step": 12590
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.18048193294363915,
+      "eval_loss": 2.910629987716675,
+      "eval_pearson": 0.17746155791882828,
+      "eval_runtime": 2.1337,
+      "eval_samples_per_second": 703.003,
+      "eval_spearmanr": 0.18350230796845002,
+      "eval_steps_per_second": 5.624,
+      "step": 12590
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.194,
+      "step": 15108
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.1587986190895676,
+      "eval_loss": 3.17031192779541,
+      "eval_pearson": 0.15500351401635443,
+      "eval_runtime": 2.1476,
+      "eval_samples_per_second": 698.466,
+      "eval_spearmanr": 0.16259372416278078,
+      "eval_steps_per_second": 5.588,
+      "step": 15108
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1563,
+      "step": 17626
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.1661386795918801,
+      "eval_loss": 2.910940408706665,
+      "eval_pearson": 0.16316202806265387,
+      "eval_runtime": 2.1393,
+      "eval_samples_per_second": 701.152,
+      "eval_spearmanr": 0.16911533112110635,
+      "eval_steps_per_second": 5.609,
+      "step": 17626
+    },
+    {
+      "epoch": 7.0,
+      "step": 17626,
+      "total_flos": 5.941760460691866e+16,
+      "train_loss": 0.4518196766484437,
+      "train_runtime": 11070.8008,
+      "train_samples_per_second": 1455.392,
+      "train_steps_per_second": 11.372
+    }
+  ],
+  "max_steps": 125900,
+  "num_train_epochs": 50,
+  "total_flos": 5.941760460691866e+16,
+  "trial_name": null,
+  "trial_params": null
+}