Initial commit, uploading initial kingdom model

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05ea0f52eda06a00cff29b76f62fe06a2861f51f2e6e3449a703b004c652d7a
+size 1625541389

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8061692e1837787eabdd9e01c01f04bf2dcf5394a2db61b4b4b069e9b5511eb8
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:040a64c72d3697dfdefef82ce9a59674c64056e5c9a292d8436b8a9dece2bb03
+size 627

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.998773507767784,
+  "global_step": 7335,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 3e-05,
+      "loss": 0.1737,
+      "step": 500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.8384317104696252e-05,
+      "loss": 0.067,
+      "step": 1000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.6768634209392504e-05,
+      "loss": 0.063,
+      "step": 1500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.5152951314088755e-05,
+      "loss": 0.0614,
+      "step": 2000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.3537268418785007e-05,
+      "loss": 0.0592,
+      "step": 2500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2.1921585523481258e-05,
+      "loss": 0.0563,
+      "step": 3000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.030590262817751e-05,
+      "loss": 0.0543,
+      "step": 3500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.8690219732873765e-05,
+      "loss": 0.0545,
+      "step": 4000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.7074536837570013e-05,
+      "loss": 0.0546,
+      "step": 4500
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.5458853942266264e-05,
+      "loss": 0.0536,
+      "step": 5000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.3843171046962518e-05,
+      "loss": 0.0512,
+      "step": 5500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.2227488151658767e-05,
+      "loss": 0.0506,
+      "step": 6000
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 1.0611805256355019e-05,
+      "loss": 0.0498,
+      "step": 6500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 8.996122361051272e-06,
+      "loss": 0.0496,
+      "step": 7000
+    }
+  ],
+  "max_steps": 9784,
+  "num_train_epochs": 4,
+  "total_flos": 6.357201350295552e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b7db2368246a8eca2c967c1b6a8c44c0184f0163c70656b5fc3f9d94ec8704
+size 4155