Model update

New model files after re-training.

README.md

@@ -1,6 +1,52 @@
 ---
 language:
 - en
+metrics:
+- accuracy
+model-index:
+- name: dgpt-small-mt
+  results: []
 ---
 
-DialoGPT small fine-tuned on the MapTask corpus. More details soon.
+# dgpt-small-mt
+
+This model is a fine-tuned version of [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) on the MapTask dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2238
+- Accuracy: 0.5338
+
+## 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": 0.5337530906790869,
+    "eval_loss": 2.223806858062744,
+    "eval_runtime": 2.3003,
+    "eval_samples": 34,
+    "eval_samples_per_second": 14.781,
+    "eval_steps_per_second": 3.043,
+    "perplexity": 9.242448669461155,
+    "train_loss": 2.4565388997395834,
+    "train_runtime": 673.0137,
+    "train_samples": 178,
+    "train_samples_per_second": 5.29,
+    "train_steps_per_second": 1.07
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.5337530906790869,
+    "eval_loss": 2.223806858062744,
+    "eval_runtime": 2.3003,
+    "eval_samples": 34,
+    "eval_samples_per_second": 14.781,
+    "eval_steps_per_second": 3.043,
+    "perplexity": 9.242448669461155
+}

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 sha256:39d2bacd8b4b113f82081a71a737fe9ff36206c7836be78e8887b0556427abde
+oid sha256:28ef587b6f2cf44fcf4ae525a4d4a1844c46ead2716ff662e84d68e944850160
 size 510398013

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 2.4565388997395834,
+    "train_runtime": 673.0137,
+    "train_samples": 178,
+    "train_samples_per_second": 5.29,
+    "train_steps_per_second": 1.07
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "global_step": 720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 13.89,
+      "learning_rate": 1.527777777777778e-05,
+      "loss": 2.6405,
+      "step": 500
+    },
+    {
+      "epoch": 20.0,
+      "step": 720,
+      "total_flos": 1860399267840000.0,
+      "train_loss": 2.4565388997395834,
+      "train_runtime": 673.0137,
+      "train_samples_per_second": 5.29,
+      "train_steps_per_second": 1.07
+    }
+  ],
+  "max_steps": 720,
+  "num_train_epochs": 20,
+  "total_flos": 1860399267840000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:986fbcb51fa3144dad812cd63a2c4c691189c0ae4e9faa814989606d4966ab37
-size 3579
+oid sha256:00c461014766e6880f76012958d9e671b69b5f4ec251d415d9a43f10fc8770ac
+size 3515