Model save

README.md

@@ -1,10 +1,8 @@
 ---
 license: apache-2.0
-base_model: t5-base
+base_model: t5-small
 tags:
 - generated_from_trainer
-datasets:
-- mbpp
 model-index:
 - name: checkpoint-t5-small-mbpp
   results: []
@@ -15,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # checkpoint-t5-small-mbpp
 
-This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the mbpp dataset.
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
 
 ## Model description
 

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 3072,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2cc4c04c26cf8c43580b0e743d1ff065267ad2d57b0b818bf78249258c07b40
-size 891644712
+oid sha256:9a034913ab1f6daff76cd1c421142a59ce26db6401ccf77c77883cd4dcc183fd
+size 242041896

runs/Nov09_04-50-00_b2533449ceec/events.out.tfevents.1699505459.b2533449ceec.1524.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a70819ba6b5f50fda4d12a86572491704e6ba8db0c54edebf97479fb6129bde1
+size 5565

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a98a97118e90e4633cd4ec54450e3cacd549fc1faca8a5e79e4591f748ba71
+oid sha256:af1bb97d03ac2bc373a20f944cc86d4d81ea1bc9df49f108d9891b3051c94646
 size 4728