End of training

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: facebook/blenderbot-400M-distill
+tags:
+- generated_from_trainer
+datasets:
+- daily_dialog
+model-index:
+- name: blenderbot-400M-distill-dialy-dialog
+  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. -->
+
+# blenderbot-400M-distill-dialy-dialog
+
+This model is a fine-tuned version of [facebook/blenderbot-400M-distill](https://huggingface.co/facebook/blenderbot-400M-distill) on the daily_dialog dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5989
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 10   | 1.0994          |
+| No log        | 2.0   | 20   | 0.7949          |
+| No log        | 3.0   | 30   | 0.6735          |
+| No log        | 4.0   | 40   | 0.6152          |
+| No log        | 5.0   | 50   | 0.5989          |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "facebook/blenderbot-400M-distill",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "BlenderbotForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1280,
+  "decoder_attention_heads": 32,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 32,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 2,
+  "encoder_no_repeat_ngram_size": 3,
+  "eos_token_id": 2,
+  "extra_layer_norm": false,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layernorm_variant": "prelayernorm",
+  "length_penalty": 0.65,
+  "max_length": 60,
+  "max_position_embeddings": 128,
+  "min_length": 20,
+  "model_type": "blenderbot",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 10,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "unk_token_id": 3,
+  "use_cache": true,
+  "vocab_size": 8008
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "encoder_no_repeat_ngram_size": 3,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "length_penalty": 0.65,
+  "max_length": 60,
+  "min_length": 20,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 10,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88402407df391d7068048d1a501db3e02f4305a43527ffae8097f1d0b8eb9269
+size 1459362445

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71306c4b02432434368304ff5cb38b08c51b7b2c46aab84ae4d9d9029c042bd6
+size 4091