End of training

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: distilbert-base-uncased
+  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
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7174
+- Accuracy: 0.625
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.625,
+    "eval_loss": 0.7173987030982971,
+    "eval_runtime": 6.6755,
+    "eval_samples": 400,
+    "eval_samples_per_second": 59.921,
+    "eval_steps_per_second": 1.947,
+    "total_flos": 423895675699200.0,
+    "train_loss": 0.8155731964111328,
+    "train_runtime": 150.3838,
+    "train_samples": 1600,
+    "train_samples_per_second": 21.279,
+    "train_steps_per_second": 1.33
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.625,
+    "eval_loss": 0.7173987030982971,
+    "eval_runtime": 6.6755,
+    "eval_samples": 400,
+    "eval_samples_per_second": 59.921,
+    "eval_steps_per_second": 1.947
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280a839ce58e5e3886662c399901b0e6673ee086c4ffe400bc031aa4ff2f5578
+size 267832560

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 423895675699200.0,
+    "train_loss": 0.8155731964111328,
+    "train_runtime": 150.3838,
+    "train_samples": 1600,
+    "train_samples_per_second": 21.279,
+    "train_steps_per_second": 1.33
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f45cf977ac1d3aaf68b95ec33efe1a7c834606334871d346e9dd633d92ffd0
+size 4920