Upload 12 files

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "google/bigbird-pegasus-large-pubmed",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "BigBirdPegasusForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 2,
+  "classifier_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": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 16,
+  "eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "length_penalty": 0.8,
+  "max_length": 256,
+  "max_position_embeddings": 4096,
+  "model_type": "bigbird_pegasus",
+  "num_beams": 5,
+  "num_hidden_layers": 16,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "tokenizer_class": "PegasusTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_bias": false,
+  "use_cache": true,
+  "vocab_size": 96103
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 1,
+  "length_penalty": 0.8,
+  "max_length": 256,
+  "num_beams": 5,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa26621c527cea70874e18a56f1414bc4d3fdc8e59fca8d1cb6353b5825c818
+size 4615427341

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f923a36999ed399620f1e20a9d7833c65f5b45d0e258f543c7a4e832ca7e0d
+size 2308118957

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426c311aecfb876306447f44c362d29aba03801d3e079c249a0c7bb4d2006beb
+size 15533

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb3a07d02472a0c7263892683f16fb010db062c726c2f5630f74b29bd08c4bc
+size 627

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1b40df7e8825709c0172639c47338a68d5622e9e3b6cc0fae516537cae738b
+size 1915455

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "[MASK]",
+  "mask_token_sent": null,
+  "model_max_length": 4096,
+  "offset": 0,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "PegasusTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.455252918287936,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.97,
+      "learning_rate": 1e-05,
+      "loss": 4.9557,
+      "step": 500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2e-05,
+      "loss": 3.7006,
+      "step": 1000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 3.289,
+      "step": 1500
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 3.047,
+      "step": 2000
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 2.9495,
+      "step": 2500
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 2.876,
+      "step": 3000
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 2.809,
+      "step": 3500
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.7617,
+      "step": 4000
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 2.7072,
+      "step": 4500
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 2.6693,
+      "step": 5000
+    },
+    {
+      "epoch": 10.7,
+      "learning_rate": 1e-05,
+      "loss": 2.6301,
+      "step": 5500
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 2.5909,
+      "step": 6000
+    },
+    {
+      "epoch": 12.65,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 2.5704,
+      "step": 6500
+    },
+    {
+      "epoch": 13.62,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.5511,
+      "step": 7000
+    },
+    {
+      "epoch": 14.59,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 2.5306,
+      "step": 7500
+    },
+    {
+      "epoch": 15.56,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 2.5132,
+      "step": 8000
+    },
+    {
+      "epoch": 16.54,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.5107,
+      "step": 8500
+    },
+    {
+      "epoch": 17.51,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 2.4966,
+      "step": 9000
+    },
+    {
+      "epoch": 18.48,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 2.4931,
+      "step": 9500
+    },
+    {
+      "epoch": 19.46,
+      "learning_rate": 0.0,
+      "loss": 2.4808,
+      "step": 10000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 20,
+  "total_flos": 2.3067637826401075e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe79423d77972bb9151b319a3638fe4e101321f14ad85020cf8104b69a5075f
+size 3771