t5-large_PREFIX_TUNING_SEQ2SEQ_EMOTION

README.md

@@ -1,11 +1,13 @@
 ---
-license: apache-2.0
+license: mit
 library_name: peft
 tags:
+- trl
+- sft
 - generated_from_trainer
 datasets:
 - emotion
-base_model: t5-large
+base_model: gpt2
 model-index:
 - name: output_emotion
   results: []
@@ -16,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output_emotion
 
-This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the emotion dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.9008
+- Loss: 7.0852
 
 ## Model description
 
@@ -43,14 +45,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 7.3148        | 2.0   | 1800 | 6.9641          |
-| 7.243         | 4.0   | 3600 | 6.9008          |
+| 8.5945        | 2.0   | 1800 | 7.5670          |
+| 7.7948        | 4.0   | 3600 | 7.0852          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,15 +1,15 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "t5-large",
-  "encoder_hidden_size": 1024,
+  "base_model_name_or_path": "gpt2",
+  "encoder_hidden_size": 768,
   "inference_mode": true,
-  "num_attention_heads": 16,
-  "num_layers": 24,
-  "num_transformer_submodules": 2,
+  "num_attention_heads": 12,
+  "num_layers": 12,
+  "num_transformer_submodules": 1,
   "num_virtual_tokens": 20,
   "peft_type": "PREFIX_TUNING",
   "prefix_projection": false,
   "revision": null,
-  "task_type": "SEQ_2_SEQ_LM",
-  "token_dim": 1024
+  "task_type": "CAUSAL_LM",
+  "token_dim": 768
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebba8b22ac27f2315d4f4a3ed95623b6b40dd4f234b54ab71a7e032b0d4a187
-size 3932288
+oid sha256:d5eb993463d87b17c54f1002ca3696b0a3c4119108f0a980777e29262dbbf2e2
+size 1474688

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:258163b6c372cb200e4a20cd72507fbac270a717e115e0d2c7d6ac2dc5ea4564
-size 4347
+oid sha256:01d43876c345d1baf67f49e8db9f2c55e987541a027dc3ae941960105c22f03e
+size 4219