Training in progress, epoch 0

config.json

@@ -1,37 +1,59 @@
 {
-  "_name_or_path": "google/flan-t5-large",
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 2816,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 1024,
+  "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,
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
-  "quantization_config": {
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_8bit": true
-  },
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "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": "4.28.1",
   "use_cache": true,
   "vocab_size": 32128

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e2e65a60a357b044f8254ec72a926c8fa14e4c2237035d39941ac75af52fee4
-size 1266894853
+oid sha256:b93a24a276350be7e54c57e1d79834eea4e496b1895ce85a8144ab927d96e036
+size 891702929

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6359a27e6dbfa5865af9d08f7773f5504beebc21957ecdb85370ebd03dc60bb4
+oid sha256:e1a01827012070f00862f4c8ff8bc2c7f1ff36be8052c04939ac00f02b0c9a7f
 size 3707