Training in progress, step 375

config.json

@@ -1,26 +1,26 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "google/flan-t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 1024,
   "d_kv": 64,
   "d_model": 512,
   "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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
@@ -54,6 +54,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.49.0",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232504847bdc677b8ec41d51a39dfcea1c98a74596df75340a41dbf4e754ff65
-size 242041896
+oid sha256:12ece3a0266ea88d4d6452f9c7dc8cb6d0d9966030bd323a0e22fcf14ba5fe68
+size 307867048