End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: tiny_bert_rand_5_v1_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.09519669889219669
+    - name: Accuracy
+      type: accuracy
+      value: 0.6960690021514893
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_5_v1_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7742
-- Matthews Correlation: 0.1153
-- Accuracy: 0.6405
+- Loss: 0.6064
+- Matthews Correlation: 0.0952
+- Accuracy: 0.6961
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.6960690021514893,
+    "eval_loss": 0.6063849329948425,
+    "eval_matthews_correlation": 0.09519669889219669,
+    "eval_runtime": 0.3421,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3048.896,
+    "eval_steps_per_second": 14.616,
+    "total_flos": 1793902531485696.0,
+    "train_loss": 0.505933586288901,
+    "train_runtime": 46.78,
+    "train_samples": 8551,
+    "train_samples_per_second": 9139.594,
+    "train_steps_per_second": 36.34
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.6960690021514893,
+    "eval_loss": 0.6063849329948425,
+    "eval_matthews_correlation": 0.09519669889219669,
+    "eval_runtime": 0.3421,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3048.896,
+    "eval_steps_per_second": 14.616
+}

logs/events.out.tfevents.1744642918.s_005_m.2701049.55

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468efd64c94ea0c764a5d2136ea28f37190120462df9b38f4491544a78f9c087
+size 427

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1793902531485696.0,
+    "train_loss": 0.505933586288901,
+    "train_runtime": 46.78,
+    "train_samples": 8551,
+    "train_samples_per_second": 9139.594,
+    "train_steps_per_second": 36.34
+}

trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_global_step": 102,
+  "best_metric": 0.6063849329948425,
+  "best_model_checkpoint": "tiny_bert_rand_5_v1_cola/checkpoint-102",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6819305419921875,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6164,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6149048209190369,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3251,
+      "eval_samples_per_second": 3208.519,
+      "eval_steps_per_second": 15.381,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9399971961975098,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5989,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.690316379070282,
+      "eval_loss": 0.6078919172286987,
+      "eval_matthews_correlation": -0.020702674026557004,
+      "eval_runtime": 0.3619,
+      "eval_samples_per_second": 2881.667,
+      "eval_steps_per_second": 13.814,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3664435148239136,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5773,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6960690021514893,
+      "eval_loss": 0.6063849329948425,
+      "eval_matthews_correlation": 0.09519669889219669,
+      "eval_runtime": 0.3433,
+      "eval_samples_per_second": 3038.365,
+      "eval_steps_per_second": 14.566,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.886993646621704,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5337,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6586769223213196,
+      "eval_loss": 0.6350516676902771,
+      "eval_matthews_correlation": 0.09572663020444179,
+      "eval_runtime": 0.3458,
+      "eval_samples_per_second": 3015.779,
+      "eval_steps_per_second": 14.457,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.374640941619873,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4901,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.668264627456665,
+      "eval_loss": 0.6574270725250244,
+      "eval_matthews_correlation": 0.11042882140267563,
+      "eval_runtime": 0.328,
+      "eval_samples_per_second": 3180.358,
+      "eval_steps_per_second": 15.246,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.690762519836426,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4479,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6500479578971863,
+      "eval_loss": 0.7044727206230164,
+      "eval_matthews_correlation": 0.10229268006391969,
+      "eval_runtime": 0.347,
+      "eval_samples_per_second": 3005.988,
+      "eval_steps_per_second": 14.41,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.9503836631774902,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4082,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.638542652130127,
+      "eval_loss": 0.7738865613937378,
+      "eval_matthews_correlation": 0.09957638832100865,
+      "eval_runtime": 0.3283,
+      "eval_samples_per_second": 3177.048,
+      "eval_steps_per_second": 15.23,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.268338203430176,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3751,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.640460193157196,
+      "eval_loss": 0.7742392420768738,
+      "eval_matthews_correlation": 0.11531200369997101,
+      "eval_runtime": 0.3792,
+      "eval_samples_per_second": 2750.304,
+      "eval_steps_per_second": 13.185,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "step": 272,
+      "total_flos": 1793902531485696.0,
+      "train_loss": 0.505933586288901,
+      "train_runtime": 46.78,
+      "train_samples_per_second": 9139.594,
+      "train_steps_per_second": 36.34
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1700,
+  "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": 1793902531485696.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}