Upload ./ with huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "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": "4.26.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dff9b9cf27fc796d85111642ce107a09bd5df8b74931dddf1942d2e0f7cc298
+size 6265537309

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a79bf58146f2b0eb690838a3ebd3f2e28766002e396a30985194f1171d4127
+size 3132793669

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0da9c41f3a2274f2b1446341f810a1a6d2df648639b4402e936cac2fa7c4cc
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7954effb3ff235e7d009f2c81769140d27337b36d3cfd3a13afd2e649f203f74
+size 627

trainer_state.json

@@ -0,0 +1,297 @@
+{
+  "best_metric": 1.2028405666351318,
+  "best_model_checkpoint": "flan-t5-large-samsum/checkpoint-3683",
+  "epoch": 5.0,
+  "global_step": 18415,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.8642411077925605e-05,
+      "loss": 1.2079,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.728482215585121e-05,
+      "loss": 1.2091,
+      "step": 1000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.592723323377681e-05,
+      "loss": 1.1932,
+      "step": 1500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.456964431170242e-05,
+      "loss": 1.1904,
+      "step": 2000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.321205538962802e-05,
+      "loss": 1.1767,
+      "step": 2500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.1854466467553626e-05,
+      "loss": 1.1794,
+      "step": 3000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.049687754547923e-05,
+      "loss": 1.1814,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 16.73870573870574,
+      "eval_loss": 1.2028405666351318,
+      "eval_rouge1": 48.847,
+      "eval_rouge2": 25.4282,
+      "eval_rougeL": 41.7343,
+      "eval_rougeLsum": 44.9999,
+      "eval_runtime": 280.4507,
+      "eval_samples_per_second": 2.92,
+      "eval_steps_per_second": 0.731,
+      "step": 3683
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.913928862340484e-05,
+      "loss": 1.0624,
+      "step": 4000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.7781699701330434e-05,
+      "loss": 1.0085,
+      "step": 4500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.6424110779256044e-05,
+      "loss": 0.9909,
+      "step": 5000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.506652185718165e-05,
+      "loss": 1.0098,
+      "step": 5500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.370893293510725e-05,
+      "loss": 1.0163,
+      "step": 6000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.235134401303285e-05,
+      "loss": 1.0424,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.099375509095846e-05,
+      "loss": 1.0294,
+      "step": 7000
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 17.39072039072039,
+      "eval_loss": 1.2175439596176147,
+      "eval_rouge1": 49.175,
+      "eval_rouge2": 25.9148,
+      "eval_rougeL": 41.729,
+      "eval_rougeLsum": 45.2583,
+      "eval_runtime": 283.3808,
+      "eval_samples_per_second": 2.89,
+      "eval_steps_per_second": 0.723,
+      "step": 7366
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 2.963616616888406e-05,
+      "loss": 1.0013,
+      "step": 7500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 2.8278577246809667e-05,
+      "loss": 0.8928,
+      "step": 8000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.692098832473527e-05,
+      "loss": 0.8853,
+      "step": 8500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.5563399402660876e-05,
+      "loss": 0.8968,
+      "step": 9000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 2.420581048058648e-05,
+      "loss": 0.8965,
+      "step": 9500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.2848221558512085e-05,
+      "loss": 0.8974,
+      "step": 10000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.1490632636437688e-05,
+      "loss": 0.8862,
+      "step": 10500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 2.013304371436329e-05,
+      "loss": 0.9026,
+      "step": 11000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 17.076923076923077,
+      "eval_loss": 1.2396090030670166,
+      "eval_rouge1": 49.1776,
+      "eval_rouge2": 25.5811,
+      "eval_rougeL": 41.6807,
+      "eval_rougeLsum": 44.9973,
+      "eval_runtime": 281.6416,
+      "eval_samples_per_second": 2.908,
+      "eval_steps_per_second": 0.728,
+      "step": 11049
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 1.8775454792288897e-05,
+      "loss": 0.8011,
+      "step": 11500
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 1.74178658702145e-05,
+      "loss": 0.7933,
+      "step": 12000
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 1.6060276948140106e-05,
+      "loss": 0.8209,
+      "step": 12500
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 1.4702688026065709e-05,
+      "loss": 0.8106,
+      "step": 13000
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.3345099103991313e-05,
+      "loss": 0.8001,
+      "step": 13500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1.1987510181916916e-05,
+      "loss": 0.8196,
+      "step": 14000
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 1.062992125984252e-05,
+      "loss": 0.808,
+      "step": 14500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 17.313797313797313,
+      "eval_loss": 1.2748357057571411,
+      "eval_rouge1": 49.3102,
+      "eval_rouge2": 25.9028,
+      "eval_rougeL": 42.1036,
+      "eval_rougeLsum": 45.485,
+      "eval_runtime": 281.9584,
+      "eval_samples_per_second": 2.905,
+      "eval_steps_per_second": 0.727,
+      "step": 14732
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 9.272332337768125e-06,
+      "loss": 0.7884,
+      "step": 15000
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 7.91474341569373e-06,
+      "loss": 0.7615,
+      "step": 15500
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 6.557154493619333e-06,
+      "loss": 0.752,
+      "step": 16000
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 5.199565571544936e-06,
+      "loss": 0.748,
+      "step": 16500
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 3.8419766494705405e-06,
+      "loss": 0.7518,
+      "step": 17000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.4843877273961445e-06,
+      "loss": 0.7522,
+      "step": 17500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 1.1267988053217486e-06,
+      "loss": 0.7482,
+      "step": 18000
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 17.304029304029303,
+      "eval_loss": 1.3044484853744507,
+      "eval_rouge1": 49.1547,
+      "eval_rouge2": 25.5204,
+      "eval_rougeL": 41.9049,
+      "eval_rougeLsum": 45.2342,
+      "eval_runtime": 283.7828,
+      "eval_samples_per_second": 2.886,
+      "eval_steps_per_second": 0.722,
+      "step": 18415
+    }
+  ],
+  "max_steps": 18415,
+  "num_train_epochs": 5,
+  "total_flos": 2.5465381088919552e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f063f7a15c9d303c2f8ea8ff616907447cd6da894916a80ebc834aa3adc33e62
+size 3643