Training in progress, step 500

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google/t5-efficient-tiny",
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 1024,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 256,
+  "d_model": 512,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,12 +18,42 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 4,
-  "num_heads": 4,
-  "num_layers": 4,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "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: "
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.36.2",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec5e19390f915af7d82e4e4d4ab59cbb91dfd4e2451e13a4fd5b2fcb2756dcd2
-size 62293080
+oid sha256:f1129866eb4c8915fffe5a05feb236f39a2124734e8915db71a625da699ee9c1
+size 242041896

tokenizer_config.json

@@ -931,10 +931,9 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "max_length": 20,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "<pad>",
   "padding": "max_length",
-  "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
   "truncation": true,
   "unk_token": "<unk>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db9cb4a3c0c4cff7198d4740dd744efbe849def912ed86f2fcef67782251689
+oid sha256:4a9c0de4633bd97f9a4ecf1628ba3d8b368bfd3cbdcbf3f3dbbaf9e57c0545a3
 size 4411