Training in progress, step 500

config.json

@@ -1,26 +1,26 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "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,
-  "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,
@@ -54,9 +54,8 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.45.1",
   "use_cache": true,
   "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7009e4ea5f57e09c9ab1675519b8d258422383d881371160193b4c31b57cb49e
-size 990345064
+oid sha256:39a1806ec539e9a6eb463bb754b06d4f633704b985bf6df4e302916177837a94
+size 242041896

runs/Dec08_10-06-25_3875563cc298/events.out.tfevents.1733652523.3875563cc298.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd997614c47b329cb1f26793f393d924e0125f1f98e712f6ed3f1f44a009e162
+size 5905

runs/Dec08_10-09-35_3875563cc298/events.out.tfevents.1733652590.3875563cc298.30.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fa7990c2e697dd08bada18814e4117e1fd045ab0c8987ae9c3ee977e5ad814
+size 6641

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",
@@ -928,13 +927,11 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "legacy": true,
   "model_max_length": 512,
   "pad_token": "<pad>",
-  "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d6e457c0a55e0213a861f8f02789df63a11ef50d618c97141fc9a05d83c636
-size 5432
+oid sha256:70f786aca059a4da0efee4b01f25db05e7faca7c815713ddf07050b319c48856
+size 5368