End of training

README.md

@@ -0,0 +1,51 @@
+---
+license: mit
+base_model: microsoft/DialoGPT-medium
+tags:
+- generated_from_trainer
+model-index:
+- name: new_DialoGPT-medium
+  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. -->
+
+# new_DialoGPT-medium
+
+This model is a fine-tuned version of [microsoft/DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) on an unknown dataset.
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "microsoft/DialoGPT-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8d2cbc0888f98d2cba449eddfc02d9ecacb359a9e0a5bfc98fa6046bb8c9c3
+size 1419322880

runs/Feb17_18-31-34_3d7e77b5b9b6/events.out.tfevents.1708194695.3d7e77b5b9b6.564.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29939fab08f0515226252d02b38b298b466da0f6068717af0f265d1818cc9442
+size 4590

runs/Feb17_18-32-41_3d7e77b5b9b6/events.out.tfevents.1708194762.3d7e77b5b9b6.564.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9775e613ffa8e369239de7a8922cff37353c0cc10ef9e135a26f0f3b234700
+size 4184

runs/Feb17_18-39-05_3d7e77b5b9b6/events.out.tfevents.1708195147.3d7e77b5b9b6.2334.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777df259a823d0f927639b01e7c729539be10b3895c191e6befc6302ab67e203
+size 4942

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54e410163322c7056a1dd107253f3a07a44b8b457bbd98c73f87edb8bdc7785
+size 4728