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 STSB
       type: glue
       config: stsb
       split: validation
@@ -21,7 +23,7 @@ model-index:
     metrics:
     - name: Spearmanr
       type: spearmanr
-      value: 0.14974645018360452
+      value: 0.008260352697674129
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,12 +31,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_stsb_256
 
-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 STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3938
-- Pearson: 0.1605
-- Spearmanr: 0.1497
-- Combined Score: 0.1551
+- Loss: 2.2966
+- Pearson: 0.0077
+- Spearmanr: 0.0083
+- Combined Score: 0.0080
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_combined_score": 0.00795730392793844,
+    "eval_loss": 2.296581506729126,
+    "eval_pearson": 0.00765425515820275,
+    "eval_runtime": 3.4215,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 438.399,
+    "eval_spearmanr": 0.008260352697674129,
+    "eval_steps_per_second": 3.507,
+    "train_loss": 2.354518410011574,
+    "train_runtime": 330.4759,
+    "train_samples": 5749,
+    "train_samples_per_second": 869.806,
+    "train_steps_per_second": 6.808
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_combined_score": 0.00795730392793844,
+    "eval_loss": 2.296581506729126,
+    "eval_pearson": 0.00765425515820275,
+    "eval_runtime": 3.4215,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 438.399,
+    "eval_spearmanr": 0.008260352697674129,
+    "eval_steps_per_second": 3.507
+}

logs/events.out.tfevents.1674663936.garda.1292005.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ff25a73568bc94908ebf3915dd7dd85fbc93274b96748bfd6d81a4d2c99847
+size 473

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 2.354518410011574,
+    "train_runtime": 330.4759,
+    "train_samples": 5749,
+    "train_samples_per_second": 869.806,
+    "train_steps_per_second": 6.808
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 2.296581506729126,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_stsb_256/checkpoint-45",
+  "epoch": 6.0,
+  "global_step": 270,
+  "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": 4.155,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.00795730392793844,
+      "eval_loss": 2.296581506729126,
+      "eval_pearson": 0.00765425515820275,
+      "eval_runtime": 3.3999,
+      "eval_samples_per_second": 441.189,
+      "eval_spearmanr": 0.008260352697674129,
+      "eval_steps_per_second": 3.53,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 2.1654,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.0616449353759356,
+      "eval_loss": 2.3384053707122803,
+      "eval_pearson": 0.059981702507068475,
+      "eval_runtime": 3.3969,
+      "eval_samples_per_second": 441.585,
+      "eval_spearmanr": 0.06330816824480273,
+      "eval_steps_per_second": 3.533,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 2.0822,
+      "step": 135
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.06713068116052827,
+      "eval_loss": 2.3582634925842285,
+      "eval_pearson": 0.06248450146298008,
+      "eval_runtime": 3.3974,
+      "eval_samples_per_second": 441.509,
+      "eval_spearmanr": 0.07177686085807645,
+      "eval_steps_per_second": 3.532,
+      "step": 135
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 2.0017,
+      "step": 180
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.07367586673239779,
+      "eval_loss": 2.7680296897888184,
+      "eval_pearson": 0.07205633459447747,
+      "eval_runtime": 3.3957,
+      "eval_samples_per_second": 441.735,
+      "eval_spearmanr": 0.07529539887031811,
+      "eval_steps_per_second": 3.534,
+      "step": 180
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 1.9379,
+      "step": 225
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.0941042781764054,
+      "eval_loss": 2.732980251312256,
+      "eval_pearson": 0.09627236123406349,
+      "eval_runtime": 3.3972,
+      "eval_samples_per_second": 441.546,
+      "eval_spearmanr": 0.09193619511874733,
+      "eval_steps_per_second": 3.532,
+      "step": 225
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.785,
+      "step": 270
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.15511313724328826,
+      "eval_loss": 2.3938400745391846,
+      "eval_pearson": 0.160479824302972,
+      "eval_runtime": 3.3962,
+      "eval_samples_per_second": 441.677,
+      "eval_spearmanr": 0.14974645018360452,
+      "eval_steps_per_second": 3.533,
+      "step": 270
+    },
+    {
+      "epoch": 6.0,
+      "step": 270,
+      "total_flos": 908597982658560.0,
+      "train_loss": 2.354518410011574,
+      "train_runtime": 330.4759,
+      "train_samples_per_second": 869.806,
+      "train_steps_per_second": 6.808
+    }
+  ],
+  "max_steps": 2250,
+  "num_train_epochs": 50,
+  "total_flos": 908597982658560.0,
+  "trial_name": null,
+  "trial_params": null
+}