Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,61 @@
+{
+ "_name_or_path": "google/flan-t5-base",
+ "architectures": [
+ "T5ForConditionalGeneration"
+ ],
+ "d_ff": 2048,
+ "d_kv": 64,
+ "d_model": 768,
+ "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": 12,
+ "num_heads": 12,
+ "num_layers": 12,
+ "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: "
+ }
+ },
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.28.1",
+ "use_cache": true,
+ "vocab_size": 32128
+}

logs/1685427965.855566/events.out.tfevents.1685427965.1b8f4c969eab.1116.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa46eab7479c830d8532c643e7a14b214a093aaa0a39076fa3c73bf213afd783
+size 6255

logs/events.out.tfevents.1685427965.1b8f4c969eab.1116.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f500a5358c629c7eabf72bd52cacce5dae02677ac15d5b5fe9b8c681e34b3fa7
+size 5255

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73ba7d7b5de47c5c4c2a5d35e35358ee11cb1b3a07e70963f12fbaaa9fef572
+size 990408885

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be072498ccafcf54036c1b38ce1c2875ba7efe2b27e3c2cd3ad6c56fad212c16
+size 3835