End

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: google/flan-t5-large
 tags:
 - generated_from_trainer
-base_model: google/flan-t5-small
 model-index:
 - name: events-mem-large-test
   results: []
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # events-mem-large-test
 
-This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
+This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 45.8774
+- Loss: 35.1229
 
 ## Model description
 
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 43.1919       | 0.0075 | 10   | 45.8774         |
+| 36.4164       | 0.0075 | 10   | 35.1229         |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google/flan-t5-small",
+  "_name_or_path": "google/flan-t5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 1024,
+  "d_ff": 2816,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -18,45 +18,16 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 8,
-  "num_heads": 6,
-  "num_layers": 8,
+  "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": "4.40.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d03767c68e0ebe2f7d49baa172f80b98f56e1485a2a0fc8ecb2c0f7b9f2018
-size 307867048
+oid sha256:dbabeb033d9444f743a13730664c481c7cb15ddb2d7bd8a754dc872fa487e919
+size 3132668808

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707fd10f84a0656163240d378a397b03c4420a9c9cfa3d0a16833ac1f3867d8e
+oid sha256:c53119d0ae0bf34028edf82979f3ebf159b1c4116545486b619b0d1da6442928
 size 5112