End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_tiny_lda_20_v1_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6838235294117647
+    - name: F1
+      type: f1
+      value: 0.8122270742358079
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_lda_20_v1_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6249
+- Loss: 0.6233
 - Accuracy: 0.6838
 - F1: 0.8122
 - Combined Score: 0.7480

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6233484745025635,
+    "eval_runtime": 0.1332,
+    "eval_samples": 408,
+    "eval_samples_per_second": 3062.177,
+    "eval_steps_per_second": 15.011,
+    "total_flos": 1058068929662976.0,
+    "train_loss": 0.6397525556159742,
+    "train_runtime": 32.0741,
+    "train_samples": 3668,
+    "train_samples_per_second": 5718.002,
+    "train_steps_per_second": 23.383
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6233484745025635,
+    "eval_runtime": 0.1332,
+    "eval_samples": 408,
+    "eval_samples_per_second": 3062.177,
+    "eval_steps_per_second": 15.011
+}

logs/events.out.tfevents.1732655630.ki-g0008.2136969.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ac90fd6703181ef17bdf192c8ff3e9014d5ed800732937fb48af4c57224f3e
+size 515

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 11.0,
+    "total_flos": 1058068929662976.0,
+    "train_loss": 0.6397525556159742,
+    "train_runtime": 32.0741,
+    "train_samples": 3668,
+    "train_samples_per_second": 5718.002,
+    "train_steps_per_second": 23.383
+}

trainer_state.json

@@ -0,0 +1,249 @@
+{
+  "best_metric": 0.6233484745025635,
+  "best_model_checkpoint": "bert_tiny_lda_20_v1_mrpc/checkpoint-90",
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 165,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3626367449760437,
+      "learning_rate": 0.00098,
+      "loss": 0.7043,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6263547539710999,
+      "eval_runtime": 0.1373,
+      "eval_samples_per_second": 2972.281,
+      "eval_steps_per_second": 14.57,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.480228066444397,
+      "learning_rate": 0.00096,
+      "loss": 0.6367,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6249425411224365,
+      "eval_runtime": 0.144,
+      "eval_samples_per_second": 2832.746,
+      "eval_steps_per_second": 13.886,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5654810667037964,
+      "learning_rate": 0.00094,
+      "loss": 0.6299,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6277430057525635,
+      "eval_runtime": 0.1408,
+      "eval_samples_per_second": 2898.537,
+      "eval_steps_per_second": 14.209,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6313713788986206,
+      "learning_rate": 0.00092,
+      "loss": 0.6347,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6264792680740356,
+      "eval_runtime": 0.1397,
+      "eval_samples_per_second": 2920.306,
+      "eval_steps_per_second": 14.315,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.23377956449985504,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.633,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.626091480255127,
+      "eval_runtime": 0.1403,
+      "eval_samples_per_second": 2908.355,
+      "eval_steps_per_second": 14.257,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.40783149003982544,
+      "learning_rate": 0.00088,
+      "loss": 0.6335,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6233484745025635,
+      "eval_runtime": 0.1371,
+      "eval_samples_per_second": 2976.003,
+      "eval_steps_per_second": 14.588,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.4742684066295624,
+      "learning_rate": 0.00086,
+      "loss": 0.6321,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6243536472320557,
+      "eval_runtime": 0.1448,
+      "eval_samples_per_second": 2817.356,
+      "eval_steps_per_second": 13.811,
+      "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.4599599540233612,
+      "learning_rate": 0.00084,
+      "loss": 0.6341,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.624885082244873,
+      "eval_runtime": 0.1371,
+      "eval_samples_per_second": 2975.46,
+      "eval_steps_per_second": 14.586,
+      "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6461894512176514,
+      "learning_rate": 0.00082,
+      "loss": 0.6283,
+      "step": 135
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6298109889030457,
+      "eval_runtime": 0.142,
+      "eval_samples_per_second": 2872.907,
+      "eval_steps_per_second": 14.083,
+      "step": 135
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.2639431357383728,
+      "learning_rate": 0.0008,
+      "loss": 0.6357,
+      "step": 150
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6238223314285278,
+      "eval_runtime": 0.1445,
+      "eval_samples_per_second": 2824.153,
+      "eval_steps_per_second": 13.844,
+      "step": 150
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.7383787035942078,
+      "learning_rate": 0.0007800000000000001,
+      "loss": 0.635,
+      "step": 165
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6249233484268188,
+      "eval_runtime": 0.1377,
+      "eval_samples_per_second": 2962.771,
+      "eval_steps_per_second": 14.523,
+      "step": 165
+    },
+    {
+      "epoch": 11.0,
+      "step": 165,
+      "total_flos": 1058068929662976.0,
+      "train_loss": 0.6397525556159742,
+      "train_runtime": 32.0741,
+      "train_samples_per_second": 5718.002,
+      "train_steps_per_second": 23.383
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "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": 1058068929662976.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}