End of training

README.md

@@ -4,6 +4,8 @@ license: apache-2.0
 base_model: hiieu/halong_embedding
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: quality_classifier_new
   results: []
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 # quality_classifier_new
 
 This model is a fine-tuned version of [hiieu/halong_embedding](https://huggingface.co/hiieu/halong_embedding) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0020
+- Accuracy: 0.9997
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.9997,
+    "eval_loss": 0.001978046027943492,
+    "eval_runtime": 274.7892,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 72.783,
+    "eval_steps_per_second": 4.549,
+    "total_flos": 4.717499098595328e+16,
+    "train_loss": 0.002790896061228381,
+    "train_runtime": 10030.0024,
+    "train_samples": 180000,
+    "train_samples_per_second": 17.946,
+    "train_steps_per_second": 0.561
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.9997,
+    "eval_loss": 0.001978046027943492,
+    "eval_runtime": 274.7892,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 72.783,
+    "eval_steps_per_second": 4.549
+}

runs/Aug29_09-25-20_286f062e03cf/events.out.tfevents.1724934025.286f062e03cf.90.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24b0d9accfeaa7f9c1d5f1518f98fc48344339d4d1bfeb6b883e7b655a9eee6
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.717499098595328e+16,
+    "train_loss": 0.002790896061228381,
+    "train_runtime": 10030.0024,
+    "train_samples": 180000,
+    "train_samples_per_second": 17.946,
+    "train_steps_per_second": 0.561
+}

trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5625,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.0033580672461539507,
+      "learning_rate": 1.8222222222222224e-05,
+      "loss": 0.0163,
+      "step": 500
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.0032137867528945208,
+      "learning_rate": 1.6444444444444444e-05,
+      "loss": 0.0049,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.0005140109569765627,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.0017,
+      "step": 1500
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.0011386671103537083,
+      "learning_rate": 1.288888888888889e-05,
+      "loss": 0.0023,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.00034964593942277133,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.0023,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0003020924050360918,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.0005,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.00018544949125498533,
+      "learning_rate": 7.555555555555556e-06,
+      "loss": 0.0,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.00014620221918448806,
+      "learning_rate": 5.777777777777778e-06,
+      "loss": 0.0009,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.0002616309211589396,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0018,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.00019133607565890998,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.0004,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.0001481592480558902,
+      "learning_rate": 4.444444444444445e-07,
+      "loss": 0.0001,
+      "step": 5500
+    },
+    {
+      "epoch": 1.0,
+      "step": 5625,
+      "total_flos": 4.717499098595328e+16,
+      "train_loss": 0.002790896061228381,
+      "train_runtime": 10030.0024,
+      "train_samples_per_second": 17.946,
+      "train_steps_per_second": 0.561
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.717499098595328e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}