Model update

New model files after re-training.

README.md

@@ -1,4 +1,9 @@
 ---
+metrics:
+- accuracy
+model-index:
+- name: dgpt-small-sw
+  results: []
 language:
 - en
 widget:
@@ -6,4 +11,45 @@ widget:
   example_title: "SW Example 1"
 ---
 
-DialoGPT small fine-tuned on the SwitchBoard corpus. More details soon.
+# dgpt-small-sw
+
+This model is a fine-tuned version of [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) on the SwitchBoard dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4817
+- Accuracy: 0.4646
+
+## Model description
+
+More details soon.
+
+## Intended uses & limitations
+
+More details soon.
+
+## Training and evaluation data
+
+More details soon.
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 5
+- eval_batch_size: 5
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.26.0
+- Pytorch 1.13.1
+- Datasets 2.9.0
+- Tokenizers 0.13.0.dev0

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.4645697044890593,
+    "eval_loss": 2.4816598892211914,
+    "eval_runtime": 13.9852,
+    "eval_samples": 208,
+    "eval_samples_per_second": 14.873,
+    "eval_steps_per_second": 3.003,
+    "perplexity": 11.961102053527732,
+    "train_loss": 2.365706356890222,
+    "train_runtime": 6608.9309,
+    "train_samples": 1741,
+    "train_samples_per_second": 5.269,
+    "train_steps_per_second": 1.056
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.4645697044890593,
+    "eval_loss": 2.4816598892211914,
+    "eval_runtime": 13.9852,
+    "eval_samples": 208,
+    "eval_samples_per_second": 14.873,
+    "eval_steps_per_second": 3.003,
+    "perplexity": 11.961102053527732
+}

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ t
 Ġ a
 h e

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4177806cf4cc63618d43c055a14cba01964d490ca454c690f25da168cf5ddadc
+oid sha256:5fbe42a51327e3e5df35ce7a6c54b6c54037dcab0173a4669f0a835ad42693af
 size 510398013

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 2.365706356890222,
+    "train_runtime": 6608.9309,
+    "train_samples": 1741,
+    "train_samples_per_second": 5.269,
+    "train_steps_per_second": 1.056
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "global_step": 6980,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.641833810888253e-05,
+      "loss": 3.1564,
+      "step": 500
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 4.2836676217765046e-05,
+      "loss": 2.6213,
+      "step": 1000
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 3.9255014326647564e-05,
+      "loss": 2.503,
+      "step": 1500
+    },
+    {
+      "epoch": 5.73,
+      "learning_rate": 3.567335243553009e-05,
+      "loss": 2.4353,
+      "step": 2000
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 3.2091690544412614e-05,
+      "loss": 2.3785,
+      "step": 2500
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 2.851002865329513e-05,
+      "loss": 2.3302,
+      "step": 3000
+    },
+    {
+      "epoch": 10.03,
+      "learning_rate": 2.492836676217765e-05,
+      "loss": 2.2988,
+      "step": 3500
+    },
+    {
+      "epoch": 11.46,
+      "learning_rate": 2.1346704871060173e-05,
+      "loss": 2.2569,
+      "step": 4000
+    },
+    {
+      "epoch": 12.89,
+      "learning_rate": 1.7765042979942695e-05,
+      "loss": 2.235,
+      "step": 4500
+    },
+    {
+      "epoch": 14.33,
+      "learning_rate": 1.4183381088825215e-05,
+      "loss": 2.2087,
+      "step": 5000
+    },
+    {
+      "epoch": 15.76,
+      "learning_rate": 1.0601719197707736e-05,
+      "loss": 2.19,
+      "step": 5500
+    },
+    {
+      "epoch": 17.19,
+      "learning_rate": 7.020057306590258e-06,
+      "loss": 2.1762,
+      "step": 6000
+    },
+    {
+      "epoch": 18.62,
+      "learning_rate": 3.4383954154727795e-06,
+      "loss": 2.1656,
+      "step": 6500
+    },
+    {
+      "epoch": 20.0,
+      "step": 6980,
+      "total_flos": 1.819637710848e+16,
+      "train_loss": 2.365706356890222,
+      "train_runtime": 6608.9309,
+      "train_samples_per_second": 5.269,
+      "train_steps_per_second": 1.056
+    }
+  ],
+  "max_steps": 6980,
+  "num_train_epochs": 20,
+  "total_flos": 1.819637710848e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff22df290acbf793d6bd48f8aec530121291562df746db88baa09550b303bdf
-size 3579
+oid sha256:338aec6a31bc28ca0c79c5ca1e08c265007bfaef7330233806b41e142086cb62
+size 3515