Upload 8 files

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "google/flan-t5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 512,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 8,
+      "prefix": "generate_story: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 32128
+}

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": "4.27.4"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ba328d369f73747eb3dd2ea81ae8c9325461779f5923fe8eb8ce3b621c4dbc
+size 5776813

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e536ae1b62aa567f86131006ad35c17685734af574605db1a72ba86f16e33c
+size 3132793669

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8248cf825a25970da8446be4ec0f74a71d37921b46fe5fd8ed9ab571f6549e49
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb72051173e24a40cb2a7fb6f96e2d2799b525e22695800cb57718eea62b150
+size 627

trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.979384651289432,
+  "global_step": 16000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.805477746654217e-05,
+      "loss": 3.0433,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.610955493308435e-05,
+      "loss": 2.9881,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.416433239962652e-05,
+      "loss": 2.9623,
+      "step": 1500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.221910986616869e-05,
+      "loss": 2.9484,
+      "step": 2000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.027388733271086e-05,
+      "loss": 2.9376,
+      "step": 2500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.832866479925304e-05,
+      "loss": 2.9268,
+      "step": 3000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.638344226579521e-05,
+      "loss": 2.9135,
+      "step": 3500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.443821973233738e-05,
+      "loss": 2.9008,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.2492997198879555e-05,
+      "loss": 2.899,
+      "step": 4500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 3.0547774665421726e-05,
+      "loss": 2.8906,
+      "step": 5000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.86025521319639e-05,
+      "loss": 2.8878,
+      "step": 5500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.665732959850607e-05,
+      "loss": 2.8841,
+      "step": 6000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 2.4712107065048243e-05,
+      "loss": 2.879,
+      "step": 6500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 2.2766884531590417e-05,
+      "loss": 2.8676,
+      "step": 7000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.0821661998132587e-05,
+      "loss": 2.8657,
+      "step": 7500
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.8876439464674758e-05,
+      "loss": 2.8636,
+      "step": 8000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.693121693121693e-05,
+      "loss": 2.8664,
+      "step": 8500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.4985994397759103e-05,
+      "loss": 2.8641,
+      "step": 9000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.3040771864301277e-05,
+      "loss": 2.8596,
+      "step": 9500
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 1.1095549330843449e-05,
+      "loss": 2.8559,
+      "step": 10000
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 9.150326797385621e-06,
+      "loss": 2.8521,
+      "step": 10500
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 7.205104263927794e-06,
+      "loss": 2.8517,
+      "step": 11000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 5.259881730469966e-06,
+      "loss": 2.8496,
+      "step": 11500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 3.3146591970121383e-06,
+      "loss": 2.8498,
+      "step": 12000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.3694366635543105e-06,
+      "loss": 2.8509,
+      "step": 12500
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 9.539371304077187e-06,
+      "loss": 2.8453,
+      "step": 13000
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 7.983193277310924e-06,
+      "loss": 2.8481,
+      "step": 13500
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 6.427015250544663e-06,
+      "loss": 2.8479,
+      "step": 14000
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 4.8708372237784005e-06,
+      "loss": 2.8431,
+      "step": 14500
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 3.3146591970121383e-06,
+      "loss": 2.8463,
+      "step": 15000
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 1.7584811702458762e-06,
+      "loss": 2.8432,
+      "step": 15500
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 2.023031434796141e-07,
+      "loss": 2.8453,
+      "step": 16000
+    }
+  ],
+  "max_steps": 16065,
+  "num_train_epochs": 5,
+  "total_flos": 1.550918552519762e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a98236d0ebe64231fc8e76b91bce130534005a4fa7a4337c449d935e860ec3
+size 3643