First upload of previous checkpoint

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:d62c2df0dc1fba0c43ba6e940eb289273646c23efaa88523e3bea7296f70d252
+size 1625541389

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f13ddf5256b8fece8a119c2d7ec91909e35ccd9da3f350159beb8d72b9c79e
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fe714afd93a500e9bffa11d97f82c71036be3f4afde899a2c3e4ce7ced2773
+size 627

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9991823385118561,
+  "global_step": 4890,
+  "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": 0.2132,
+      "step": 500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.6584699453551913e-05,
+      "loss": 0.0331,
+      "step": 1000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.3169398907103826e-05,
+      "loss": 0.0277,
+      "step": 1500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.975409836065574e-05,
+      "loss": 0.0269,
+      "step": 2000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.633879781420765e-05,
+      "loss": 0.0261,
+      "step": 2500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.2923497267759564e-05,
+      "loss": 0.0244,
+      "step": 3000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 9.508196721311476e-06,
+      "loss": 0.0239,
+      "step": 3500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 6.092896174863388e-06,
+      "loss": 0.0232,
+      "step": 4000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.6775956284153005e-06,
+      "loss": 0.0234,
+      "step": 4500
+    }
+  ],
+  "max_steps": 4892,
+  "num_train_epochs": 2,
+  "total_flos": 4.238314825580544e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39f6c6332d1cf6ba0532edfb81cf0ec3bd7becab6f85c8b048a1530bf43305a
+size 4155