End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: t5-small
+base_model: google/flan-t5-large
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mythology-t5
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0599
+This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
 
 ## Model description
 
@@ -43,15 +41,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 54   | 1.9814          |
-| No log        | 2.0   | 108  | 0.1734          |
-| No log        | 3.0   | 162  | 0.0599          |
-
-
 ### Framework versions
 
 - Transformers 4.47.1

config.json

@@ -1,59 +1,31 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "google/flan-t5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 2816,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "relu",
+  "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 200,
-      "min_length": 30,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4,
-      "prefix": "summarize: "
-    },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
-    }
-  },
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24059bfbc01447dc8a8544b50d72bf555b638644936470c515ddc578b44a7ec
-size 242041896
+oid sha256:86504672daf4f9714268be10f171bcf0be0a6f5c52264ff5af93d88745ef078f
+size 3132668808

tokenizer_config.json

@@ -928,7 +928,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_ids": 100,
   "extra_special_tokens": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2297e1c431ecc969bc46aec10ef6ff055a5a153b9f67289a3a0acc8bdc8b1015
+oid sha256:1ad2408f847ea4da12d187a4fbb7da4ec46a7b52b77e815dd30ccdd06448a529
 size 5304