End of training

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: distilbert-base-uncased-finetuned-emotion
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# distilbert-base-uncased-finetuned-emotion
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3068
+- Accuracy: 0.9085
+- F1 Score: 0.9086
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
+| 0.9641        | 1.0   | 250  | 0.6194          | 0.792    | 0.7819   |
+| 0.4398        | 2.0   | 500  | 0.3389          | 0.883    | 0.8825   |
+| 0.258         | 3.0   | 750  | 0.2948          | 0.8945   | 0.8951   |
+| 0.1744        | 4.0   | 1000 | 0.2841          | 0.9035   | 0.9038   |
+| 0.132         | 5.0   | 1250 | 0.2937          | 0.8985   | 0.8983   |
+| 0.1078        | 6.0   | 1500 | 0.2770          | 0.9055   | 0.9054   |
+| 0.0888        | 7.0   | 1750 | 0.3017          | 0.903    | 0.9028   |
+| 0.0739        | 8.0   | 2000 | 0.2829          | 0.9095   | 0.9096   |
+| 0.0611        | 9.0   | 2250 | 0.3062          | 0.91     | 0.9102   |
+| 0.0506        | 10.0  | 2500 | 0.3068          | 0.9085   | 0.9086   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Tokenizers 0.19.1

losses.json

@@ -0,0 +1,191 @@
+[
+    {
+        "loss": 0.9641,
+        "grad_norm": 12.902933120727539,
+        "learning_rate": 1.8e-05,
+        "epoch": 1.0,
+        "step": 250
+    },
+    {
+        "eval_loss": 0.6194158792495728,
+        "eval_accuracy": 0.792,
+        "eval_f1_score": 0.7818567350710909,
+        "eval_runtime": 4.3481,
+        "eval_samples_per_second": 459.97,
+        "eval_steps_per_second": 7.36,
+        "epoch": 1.0,
+        "step": 250
+    },
+    {
+        "loss": 0.4398,
+        "grad_norm": 8.209343910217285,
+        "learning_rate": 1.6000000000000003e-05,
+        "epoch": 2.0,
+        "step": 500
+    },
+    {
+        "eval_loss": 0.33885374665260315,
+        "eval_accuracy": 0.883,
+        "eval_f1_score": 0.8825473908240207,
+        "eval_runtime": 4.3879,
+        "eval_samples_per_second": 455.804,
+        "eval_steps_per_second": 7.293,
+        "epoch": 2.0,
+        "step": 500
+    },
+    {
+        "loss": 0.258,
+        "grad_norm": 7.1059184074401855,
+        "learning_rate": 1.4e-05,
+        "epoch": 3.0,
+        "step": 750
+    },
+    {
+        "eval_loss": 0.2948116958141327,
+        "eval_accuracy": 0.8945,
+        "eval_f1_score": 0.8950761079856652,
+        "eval_runtime": 4.3338,
+        "eval_samples_per_second": 461.493,
+        "eval_steps_per_second": 7.384,
+        "epoch": 3.0,
+        "step": 750
+    },
+    {
+        "loss": 0.1744,
+        "grad_norm": 14.858270645141602,
+        "learning_rate": 1.2e-05,
+        "epoch": 4.0,
+        "step": 1000
+    },
+    {
+        "eval_loss": 0.28408634662628174,
+        "eval_accuracy": 0.9035,
+        "eval_f1_score": 0.9038343567745306,
+        "eval_runtime": 4.2528,
+        "eval_samples_per_second": 470.273,
+        "eval_steps_per_second": 7.524,
+        "epoch": 4.0,
+        "step": 1000
+    },
+    {
+        "loss": 0.132,
+        "grad_norm": 10.98675537109375,
+        "learning_rate": 1e-05,
+        "epoch": 5.0,
+        "step": 1250
+    },
+    {
+        "eval_loss": 0.29371485114097595,
+        "eval_accuracy": 0.8985,
+        "eval_f1_score": 0.8982752344158218,
+        "eval_runtime": 4.368,
+        "eval_samples_per_second": 457.874,
+        "eval_steps_per_second": 7.326,
+        "epoch": 5.0,
+        "step": 1250
+    },
+    {
+        "loss": 0.1078,
+        "grad_norm": 1.496416449546814,
+        "learning_rate": 8.000000000000001e-06,
+        "epoch": 6.0,
+        "step": 1500
+    },
+    {
+        "eval_loss": 0.27695581316947937,
+        "eval_accuracy": 0.9055,
+        "eval_f1_score": 0.9053682374738501,
+        "eval_runtime": 4.2619,
+        "eval_samples_per_second": 469.274,
+        "eval_steps_per_second": 7.508,
+        "epoch": 6.0,
+        "step": 1500
+    },
+    {
+        "loss": 0.0888,
+        "grad_norm": 2.4278478622436523,
+        "learning_rate": 6e-06,
+        "epoch": 7.0,
+        "step": 1750
+    },
+    {
+        "eval_loss": 0.3017047643661499,
+        "eval_accuracy": 0.903,
+        "eval_f1_score": 0.9027803797533116,
+        "eval_runtime": 4.3556,
+        "eval_samples_per_second": 459.177,
+        "eval_steps_per_second": 7.347,
+        "epoch": 7.0,
+        "step": 1750
+    },
+    {
+        "loss": 0.0739,
+        "grad_norm": 2.9510045051574707,
+        "learning_rate": 4.000000000000001e-06,
+        "epoch": 8.0,
+        "step": 2000
+    },
+    {
+        "eval_loss": 0.28290167450904846,
+        "eval_accuracy": 0.9095,
+        "eval_f1_score": 0.9096314060750578,
+        "eval_runtime": 4.3333,
+        "eval_samples_per_second": 461.542,
+        "eval_steps_per_second": 7.385,
+        "epoch": 8.0,
+        "step": 2000
+    },
+    {
+        "loss": 0.0611,
+        "grad_norm": 9.680631637573242,
+        "learning_rate": 2.0000000000000003e-06,
+        "epoch": 9.0,
+        "step": 2250
+    },
+    {
+        "eval_loss": 0.306204229593277,
+        "eval_accuracy": 0.91,
+        "eval_f1_score": 0.9101550513849552,
+        "eval_runtime": 4.3144,
+        "eval_samples_per_second": 463.564,
+        "eval_steps_per_second": 7.417,
+        "epoch": 9.0,
+        "step": 2250
+    },
+    {
+        "loss": 0.0506,
+        "grad_norm": 3.266329050064087,
+        "learning_rate": 0.0,
+        "epoch": 10.0,
+        "step": 2500
+    },
+    {
+        "eval_loss": 0.3068402111530304,
+        "eval_accuracy": 0.9085,
+        "eval_f1_score": 0.9086081968965166,
+        "eval_runtime": 4.2835,
+        "eval_samples_per_second": 466.913,
+        "eval_steps_per_second": 7.471,
+        "epoch": 10.0,
+        "step": 2500
+    },
+    {
+        "train_runtime": 1334.5966,
+        "train_samples_per_second": 119.886,
+        "train_steps_per_second": 1.873,
+        "total_flos": 3891507413760000.0,
+        "train_loss": 0.23506236724853516,
+        "epoch": 10.0,
+        "step": 2500
+    },
+    {
+        "eval_loss": 0.3068402111530304,
+        "eval_accuracy": 0.9085,
+        "eval_f1_score": 0.9086081968965166,
+        "eval_runtime": 4.7892,
+        "eval_samples_per_second": 417.606,
+        "eval_steps_per_second": 6.682,
+        "epoch": 10.0,
+        "step": 2500
+    }
+]

metrics.json

@@ -0,0 +1,9 @@
+{
+    "eval_loss": 0.3068402111530304,
+    "eval_accuracy": 0.9085,
+    "eval_f1_score": 0.9086081968965166,
+    "eval_runtime": 4.7892,
+    "eval_samples_per_second": 417.606,
+    "eval_steps_per_second": 6.682,
+    "epoch": 10.0
+}

runs/Jul13_03-58-13_152124859d1a/events.out.tfevents.1720843097.152124859d1a.1408.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7031af55908f8fc567c83c6a8a31cc4cc491d30d04be3e51e0605744d6ea8514
-size 10565
+oid sha256:e1a518f832e15c9b8e371617f3f82da7c7dc4d8c6a5730600f1336a2841cb212
+size 11294

runs/Jul13_03-58-13_152124859d1a/events.out.tfevents.1720845740.152124859d1a.1408.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feae7515bb86469a334511a1b6f3c05bfe650fda4bf1e32b3beaa5842e85296a
+size 463