Training in progress, step 500

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "google/t5-efficient-tiny",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 1024,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 256,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,42 +18,12 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
-  "output_past": true,
+  "num_decoder_layers": 4,
+  "num_heads": 4,
+  "num_layers": 4,
   "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:c68246fd7c9fd3c11a5fda3914ffb8f4bda5c242e523cac6bf45cd90ae2df78a
-size 242041896
+oid sha256:2051d118d6666f2093d45861a928e68cee7b58a9ea5cc925083c70b8b5844653
+size 62293080

tokenizer_config.json

@@ -931,9 +931,10 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "max_length": 20,
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "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 sha256:62a937b1d50ed44c25b8872c93002df28604d182476a0132b3d5f1a1f2cbc1fe
+oid sha256:fb49e24fc35bef46938c5dbeb0c756542cc806ba8c53871b9b60155f0ee25336
 size 4411