End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: tiny_bert_rand_5_v1_stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.28550740239161837
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,12 +30,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_5_v1_stsb
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v1](https://huggingface.co/Hartunka/tiny_bert_rand_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v1](https://huggingface.co/Hartunka/tiny_bert_rand_5_v1) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6687
-- Pearson: 0.3171
-- Spearmanr: 0.3124
-- Combined Score: 0.3148
+- Loss: 2.3876
+- Pearson: 0.2931
+- Spearmanr: 0.2855
+- Combined Score: 0.2893
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 9.0,
+    "eval_combined_score": 0.28932191146728636,
+    "eval_loss": 2.387584686279297,
+    "eval_pearson": 0.2931364205429543,
+    "eval_runtime": 0.4536,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 3306.985,
+    "eval_spearmanr": 0.28550740239161837,
+    "eval_steps_per_second": 13.228,
+    "total_flos": 1356793384840704.0,
+    "train_loss": 1.486379623413086,
+    "train_runtime": 39.6567,
+    "train_samples": 5749,
+    "train_samples_per_second": 7248.454,
+    "train_steps_per_second": 28.999
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 9.0,
+    "eval_combined_score": 0.28932191146728636,
+    "eval_loss": 2.387584686279297,
+    "eval_pearson": 0.2931364205429543,
+    "eval_runtime": 0.4536,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 3306.985,
+    "eval_spearmanr": 0.28550740239161837,
+    "eval_steps_per_second": 13.228
+}

logs/events.out.tfevents.1744645506.s_005_m.2701049.67

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc73ec707cd1033a52491c8818ea82ceabf4d058513fd3c15a789fae20c5023
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 1356793384840704.0,
+    "train_loss": 1.486379623413086,
+    "train_runtime": 39.6567,
+    "train_samples": 5749,
+    "train_samples_per_second": 7248.454,
+    "train_steps_per_second": 28.999
+}

trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_global_step": 92,
+  "best_metric": 2.387584686279297,
+  "best_model_checkpoint": "tiny_bert_rand_5_v1_stsb/checkpoint-92",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 207,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.732455253601074,
+      "learning_rate": 4.9e-05,
+      "loss": 3.4897,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.06359102083043883,
+      "eval_loss": 2.4595422744750977,
+      "eval_pearson": 0.06898776371218468,
+      "eval_runtime": 0.4536,
+      "eval_samples_per_second": 3307.129,
+      "eval_spearmanr": 0.05819427794869299,
+      "eval_steps_per_second": 13.229,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.954559803009033,
+      "learning_rate": 4.8e-05,
+      "loss": 2.0096,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.11660029861389498,
+      "eval_loss": 2.6146180629730225,
+      "eval_pearson": 0.12482784591355002,
+      "eval_runtime": 0.5009,
+      "eval_samples_per_second": 2994.648,
+      "eval_spearmanr": 0.10837275131423994,
+      "eval_steps_per_second": 11.979,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.8552021980285645,
+      "learning_rate": 4.7e-05,
+      "loss": 1.8479,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.18696176467663445,
+      "eval_loss": 2.3950836658477783,
+      "eval_pearson": 0.19475826748422084,
+      "eval_runtime": 0.5063,
+      "eval_samples_per_second": 2962.428,
+      "eval_spearmanr": 0.17916526186904802,
+      "eval_steps_per_second": 11.85,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.263176918029785,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.6023,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.28932191146728636,
+      "eval_loss": 2.387584686279297,
+      "eval_pearson": 0.2931364205429543,
+      "eval_runtime": 0.4705,
+      "eval_samples_per_second": 3188.372,
+      "eval_spearmanr": 0.28550740239161837,
+      "eval_steps_per_second": 12.753,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 12.205520629882812,
+      "learning_rate": 4.5e-05,
+      "loss": 1.3085,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.27613789995817917,
+      "eval_loss": 2.4777557849884033,
+      "eval_pearson": 0.2810773671653918,
+      "eval_runtime": 0.4755,
+      "eval_samples_per_second": 3154.54,
+      "eval_spearmanr": 0.2711984327509666,
+      "eval_steps_per_second": 12.618,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 16.09912109375,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.0396,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.31198315746046257,
+      "eval_loss": 2.449542999267578,
+      "eval_pearson": 0.3128501024896465,
+      "eval_runtime": 0.4966,
+      "eval_samples_per_second": 3020.566,
+      "eval_spearmanr": 0.3111162124312787,
+      "eval_steps_per_second": 12.082,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 16.89310646057129,
+      "learning_rate": 4.3e-05,
+      "loss": 0.8308,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.3389701896462223,
+      "eval_loss": 2.475055694580078,
+      "eval_pearson": 0.33859114529684625,
+      "eval_runtime": 0.4836,
+      "eval_samples_per_second": 3101.759,
+      "eval_spearmanr": 0.3393492339955983,
+      "eval_steps_per_second": 12.407,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 13.597253799438477,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6749,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.3236788646982196,
+      "eval_loss": 2.54538631439209,
+      "eval_pearson": 0.32561739277468726,
+      "eval_runtime": 0.5142,
+      "eval_samples_per_second": 2917.382,
+      "eval_spearmanr": 0.32174033662175194,
+      "eval_steps_per_second": 11.67,
+      "step": 184
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 8.104729652404785,
+      "learning_rate": 4.1e-05,
+      "loss": 0.574,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": 0.3147812326804367,
+      "eval_loss": 2.6686761379241943,
+      "eval_pearson": 0.31714032142045084,
+      "eval_runtime": 0.4508,
+      "eval_samples_per_second": 3327.367,
+      "eval_spearmanr": 0.31242214394042245,
+      "eval_steps_per_second": 13.309,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "step": 207,
+      "total_flos": 1356793384840704.0,
+      "train_loss": 1.486379623413086,
+      "train_runtime": 39.6567,
+      "train_samples_per_second": 7248.454,
+      "train_steps_per_second": 28.999
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1356793384840704.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}