:sparkles: AM0628

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-bidirection",
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "encoder_attention_type": "transient-global",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "local_radius": 127,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0",
+  "use_cache": true,
+  "vocab_size": 64100
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546c4d041a3bc3851d7c0d74985fb40868e0407a9c74b5d7afe23fc6087b8f6b
+size 2373746501

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bfd3f733f90b95dcc7c359beb03cfa7a1cfb6b4647c09ef2800bccc23d22bb
+size 1186888873

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42e2807635c919e14d32e40844364d3a20d3f7a05dd5ae3abca6bcb4e2904bb
+size 15597

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab902f159224e21f81ba12869ee31afe1267988476bd4526a10ae02270baf3d
+size 627

trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 48.78048780487805,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 12.2,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 0.8905,
+      "step": 500
+    },
+    {
+      "epoch": 24.39,
+      "learning_rate": 3.780487804878049e-05,
+      "loss": 0.0511,
+      "step": 1000
+    },
+    {
+      "epoch": 36.59,
+      "learning_rate": 3.170731707317073e-05,
+      "loss": 0.0304,
+      "step": 1500
+    },
+    {
+      "epoch": 48.78,
+      "learning_rate": 2.5609756097560977e-05,
+      "loss": 0.0265,
+      "step": 2000
+    }
+  ],
+  "max_steps": 4100,
+  "num_train_epochs": 100,
+  "total_flos": 2065509794709504.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bc2a70fc79f2422b578b9b322268df477f1e8e5744100eb8cfb675733b334b
+size 3707