Upload 7 files

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "google/pegasus-cnn_dailymail",
+  "activation_dropout": 0.1,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "PegasusForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 16,
+  "decoder_start_token_id": 0,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 16,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 1,
+  "forced_eos_token_id": 1,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 0.8,
+  "max_length": 128,
+  "max_position_embeddings": 1024,
+  "min_length": 32,
+  "model_type": "pegasus",
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 8,
+  "num_hidden_layers": 16,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 96103
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "length_penalty": 0.8,
+  "max_length": 128,
+  "min_length": 32,
+  "num_beams": 8,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:047b81f075bc8ba09e1904738edd1b99719fe9d9c343f32670df70c911d53c18
+size 2283652852

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39842494973a688fdaeab2158de2a4c846fe492373c57165b0894b8a9f3429f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6941b0148b96f216d548ef74b2292c99b1f325d239bd8add18019446b1250b
+size 1064

trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.9984,
+  "eval_steps": 500,
+  "global_step": 7810,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 114357.3359375,
+      "learning_rate": 4.740596627756161e-05,
+      "loss": 3.7821,
+      "step": 500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 114484.1171875,
+      "learning_rate": 4.4163424124513617e-05,
+      "loss": 1.3466,
+      "step": 1000
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 74623.7109375,
+      "learning_rate": 4.092088197146563e-05,
+      "loss": 1.2312,
+      "step": 1500
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 90289.9375,
+      "learning_rate": 3.767833981841764e-05,
+      "loss": 1.1712,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 48473.625,
+      "learning_rate": 3.4435797665369654e-05,
+      "loss": 1.1258,
+      "step": 2500
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 48174.4140625,
+      "learning_rate": 3.119325551232166e-05,
+      "loss": 1.1166,
+      "step": 3000
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 48501.65234375,
+      "learning_rate": 2.7950713359273672e-05,
+      "loss": 1.0865,
+      "step": 3500
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 51178.6875,
+      "learning_rate": 2.4708171206225684e-05,
+      "loss": 1.0675,
+      "step": 4000
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 90527.828125,
+      "learning_rate": 2.146562905317769e-05,
+      "loss": 1.0602,
+      "step": 4500
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 54371.5234375,
+      "learning_rate": 1.8223086900129702e-05,
+      "loss": 1.043,
+      "step": 5000
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 159429.1875,
+      "learning_rate": 1.4980544747081713e-05,
+      "loss": 1.0311,
+      "step": 5500
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 55272.26171875,
+      "learning_rate": 1.1738002594033724e-05,
+      "loss": 1.0335,
+      "step": 6000
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 42917.234375,
+      "learning_rate": 8.495460440985733e-06,
+      "loss": 1.0229,
+      "step": 6500
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 53693.88671875,
+      "learning_rate": 5.2529182879377435e-06,
+      "loss": 1.0176,
+      "step": 7000
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 48436.2265625,
+      "learning_rate": 2.0103761348897538e-06,
+      "loss": 1.0157,
+      "step": 7500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7810,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 30000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.026686829985792e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66005b7e7ff3f1e154ce1da573ff9084fb1c117b563300764fe809f79dc9e921
+size 5112