Training in progress, epoch 1

config.json

@@ -1,20 +1,20 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "MaRiOrOsSi/t5-base-finetuned-question-answering",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 3072,
   "d_kv": 64,
   "d_model": 768,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
+  "dense_act_fn": "relu",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
+  "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
+  "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
@@ -54,7 +54,6 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaa41a9b1c791dfbeea78adbd3801fb3d519ca419d4ae646226d477947efa629
-size 990345064
+oid sha256:624af5bbfe4e3ce7d1ec28b80941228e0078761cb16f7bd899a1e6dbbc9ca52e
+size 891644712

runs/Dec07_12-36-27_ws-l4-008/events.out.tfevents.1733560606.ws-l4-008.3145579.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad6eb8b6e89831cd12acc5de679047ccbaa7ffbbaf0e70293885897d5045d38
+size 6268

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36f9c919574aa28591e35e2f1c18f6be550974f76041981b80b8b5e2ee833ec
+oid sha256:a83dd392bfd6aed4f49295a55dfd1be06f91e1c7a36be3046b22a7c5a2ce3c7f
 size 5368