End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_50_v1_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5091743119266054
 ---
 
 <!-- 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_50_v1_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_50_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_50_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_50_v1) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6970
+- Loss: 0.6954
 - Accuracy: 0.5092
 
 ## Model description

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.5091743119266054,
+    "eval_loss": 0.6954379081726074,
+    "eval_runtime": 0.377,
+    "eval_samples": 872,
+    "eval_samples_per_second": 2312.818,
+    "eval_steps_per_second": 10.609,
+    "total_flos": 4.014696074437325e+16,
+    "train_loss": 0.6891397867941295,
+    "train_runtime": 578.6042,
+    "train_samples": 67349,
+    "train_samples_per_second": 5819.954,
+    "train_steps_per_second": 22.814
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.5091743119266054,
+    "eval_loss": 0.6954379081726074,
+    "eval_runtime": 0.377,
+    "eval_samples": 872,
+    "eval_samples_per_second": 2312.818,
+    "eval_steps_per_second": 10.609
+}

logs/events.out.tfevents.1732644488.ki-g0008.2135900.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14cb195b7b7485e55447f297d42a653478efd6684f156bd7e5730b200cd5183
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 4.014696074437325e+16,
+    "train_loss": 0.6891397867941295,
+    "train_runtime": 578.6042,
+    "train_samples": 67349,
+    "train_samples_per_second": 5819.954,
+    "train_steps_per_second": 22.814
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.6954379081726074,
+  "best_model_checkpoint": "distilbert_lda_50_v1_sst2/checkpoint-1056",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 2376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4881739616394043,
+      "learning_rate": 0.00098,
+      "loss": 0.7089,
+      "step": 264
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6971402168273926,
+      "eval_runtime": 0.3976,
+      "eval_samples_per_second": 2192.975,
+      "eval_steps_per_second": 10.06,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.350206583738327,
+      "learning_rate": 0.00096,
+      "loss": 0.6871,
+      "step": 528
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.695724606513977,
+      "eval_runtime": 0.3768,
+      "eval_samples_per_second": 2314.264,
+      "eval_steps_per_second": 10.616,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5072749257087708,
+      "learning_rate": 0.00094,
+      "loss": 0.6867,
+      "step": 792
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.698914110660553,
+      "eval_runtime": 0.388,
+      "eval_samples_per_second": 2247.185,
+      "eval_steps_per_second": 10.308,
+      "step": 792
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5293957591056824,
+      "learning_rate": 0.00092,
+      "loss": 0.6868,
+      "step": 1056
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6954379081726074,
+      "eval_runtime": 0.373,
+      "eval_samples_per_second": 2337.899,
+      "eval_steps_per_second": 10.724,
+      "step": 1056
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.16188092529773712,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6867,
+      "step": 1320
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6972835659980774,
+      "eval_runtime": 0.3778,
+      "eval_samples_per_second": 2307.995,
+      "eval_steps_per_second": 10.587,
+      "step": 1320
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.0814874991774559,
+      "learning_rate": 0.00088,
+      "loss": 0.6866,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.698914110660553,
+      "eval_runtime": 0.3728,
+      "eval_samples_per_second": 2338.898,
+      "eval_steps_per_second": 10.729,
+      "step": 1584
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.1502029448747635,
+      "learning_rate": 0.00086,
+      "loss": 0.6862,
+      "step": 1848
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6969968676567078,
+      "eval_runtime": 0.3762,
+      "eval_samples_per_second": 2317.815,
+      "eval_steps_per_second": 10.632,
+      "step": 1848
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.050043512135744095,
+      "learning_rate": 0.00084,
+      "loss": 0.6866,
+      "step": 2112
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6970685124397278,
+      "eval_runtime": 0.3742,
+      "eval_samples_per_second": 2330.096,
+      "eval_steps_per_second": 10.689,
+      "step": 2112
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.18645544350147247,
+      "learning_rate": 0.00082,
+      "loss": 0.6867,
+      "step": 2376
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6969968676567078,
+      "eval_runtime": 0.382,
+      "eval_samples_per_second": 2282.808,
+      "eval_steps_per_second": 10.472,
+      "step": 2376
+    },
+    {
+      "epoch": 9.0,
+      "step": 2376,
+      "total_flos": 4.014696074437325e+16,
+      "train_loss": 0.6891397867941295,
+      "train_runtime": 578.6042,
+      "train_samples_per_second": 5819.954,
+      "train_steps_per_second": 22.814
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 13200,
+  "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": 4.014696074437325e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}