Training in progress, step 415

config.json

@@ -1,25 +1,31 @@
 {
   "architectures": [
-    "BertForQuestionAnswering"
+    "T5ForConditionalGeneration"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "classifier_dropout": 0.0,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
-  "type_vocab_size": 2,
+  "transformers_version": "4.51.3",
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819da1d45ebec0c45525c4c4610044eded33fe4e750f143dcc2cc4bdfcb51324
-size 1336424168
+oid sha256:a59a12ba27cbbd4c979db9bc69b02e29c5dda2080c0829769e508ff4e5a2c25b
+size 3132668808

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e98c3b4cf05ec5122e4a06cf95b3d24e54989cfbaf0704de19a70497381e0a1
+oid sha256:f144cbdc34ac57164f7fbefec25810c51e32352809e6c9fab52bb3fe2403fa65
 size 5304