Training in progress, epoch 5

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/flan-t5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "vocab_size": 32128
+}

logs/events.out.tfevents.1722686306.3b678e7990d3.1967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fc3975cee01c51949122c10198fc7bf1f46173c8f8ea4eab29f9733da1bc35
+size 11545

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df07c919039f4c3ec50d351242e1907a6f2ab6116c82e62d53353d3fa9caaf6
+size 3132668808

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3aa80874c0f493455b63649e5b0fc946cc4213ecec999a5305567d621256e77
+size 5368