End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_100_v1_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5270758122743683
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_lda_100_v1_rte
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6933
+- Loss: 0.6924
 - Accuracy: 0.5271
 
 ## Model description

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.692407488822937,
+    "eval_runtime": 0.1259,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2199.629,
+    "eval_steps_per_second": 15.882,
+    "total_flos": 1649219113267200.0,
+    "train_loss": 0.7379685497283935,
+    "train_runtime": 40.4003,
+    "train_samples": 2490,
+    "train_samples_per_second": 3081.66,
+    "train_steps_per_second": 12.376
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.692407488822937,
+    "eval_runtime": 0.1259,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2199.629,
+    "eval_steps_per_second": 15.882
+}

logs/events.out.tfevents.1732654178.ki-g0008.2135900.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620fadae69cd87a50ee3055f74b217ca5e9a6af5b874f5dcaa0f040c1a532177
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1649219113267200.0,
+    "train_loss": 0.7379685497283935,
+    "train_runtime": 40.4003,
+    "train_samples": 2490,
+    "train_samples_per_second": 3081.66,
+    "train_steps_per_second": 12.376
+}

trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_metric": 0.692407488822937,
+  "best_model_checkpoint": "distilbert_lda_100_v1_rte/checkpoint-50",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.396678447723389,
+      "learning_rate": 0.00098,
+      "loss": 1.0648,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.8821849822998047,
+      "eval_runtime": 0.1289,
+      "eval_samples_per_second": 2149.425,
+      "eval_steps_per_second": 15.519,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.073857545852661,
+      "learning_rate": 0.00096,
+      "loss": 0.7424,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7186089754104614,
+      "eval_runtime": 0.1466,
+      "eval_samples_per_second": 1889.824,
+      "eval_steps_per_second": 13.645,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.21421770751476288,
+      "learning_rate": 0.00094,
+      "loss": 0.7107,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6934792399406433,
+      "eval_runtime": 0.1278,
+      "eval_samples_per_second": 2168.181,
+      "eval_steps_per_second": 15.655,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5161170363426208,
+      "learning_rate": 0.00092,
+      "loss": 0.6989,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6947343349456787,
+      "eval_runtime": 0.1272,
+      "eval_samples_per_second": 2178.479,
+      "eval_steps_per_second": 15.729,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5159440636634827,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.695,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.692407488822937,
+      "eval_runtime": 0.1246,
+      "eval_samples_per_second": 2223.421,
+      "eval_steps_per_second": 16.054,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.08322759717702866,
+      "learning_rate": 0.00088,
+      "loss": 0.6939,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6932536363601685,
+      "eval_runtime": 0.1434,
+      "eval_samples_per_second": 1931.802,
+      "eval_steps_per_second": 13.948,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.1319161206483841,
+      "learning_rate": 0.00086,
+      "loss": 0.6933,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6936765909194946,
+      "eval_runtime": 0.1255,
+      "eval_samples_per_second": 2206.912,
+      "eval_steps_per_second": 15.934,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.10088898986577988,
+      "learning_rate": 0.00084,
+      "loss": 0.694,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6934651136398315,
+      "eval_runtime": 0.1299,
+      "eval_samples_per_second": 2132.876,
+      "eval_steps_per_second": 15.4,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.16308189928531647,
+      "learning_rate": 0.00082,
+      "loss": 0.6935,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6930421590805054,
+      "eval_runtime": 0.1287,
+      "eval_samples_per_second": 2152.531,
+      "eval_steps_per_second": 15.542,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.16548249125480652,
+      "learning_rate": 0.0008,
+      "loss": 0.6933,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6932536363601685,
+      "eval_runtime": 0.1329,
+      "eval_samples_per_second": 2084.947,
+      "eval_steps_per_second": 15.054,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "step": 100,
+      "total_flos": 1649219113267200.0,
+      "train_loss": 0.7379685497283935,
+      "train_runtime": 40.4003,
+      "train_samples_per_second": 3081.66,
+      "train_steps_per_second": 12.376
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "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": 1649219113267200.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}