Upload 8 files

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "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": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "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": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff45c8b85839ddf5943c6bddc2ba1138b81362b180f2a843d29d29b1e809ccfc
+size 557969145

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9997758637251448,
+  "global_step": 7806,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.74046197767973e-05,
+      "loss": 1.6733,
+      "step": 500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.4160394497793926e-05,
+      "loss": 1.2466,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.091616921879056e-05,
+      "loss": 1.1359,
+      "step": 1500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.767194393978718e-05,
+      "loss": 1.0703,
+      "step": 2000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.442771866078381e-05,
+      "loss": 1.0288,
+      "step": 2500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.1183493381780434e-05,
+      "loss": 0.984,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.793926810277706e-05,
+      "loss": 0.9522,
+      "step": 3500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.4695042823773685e-05,
+      "loss": 0.9249,
+      "step": 4000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.1450817544770312e-05,
+      "loss": 0.8816,
+      "step": 4500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8206592265766935e-05,
+      "loss": 0.8639,
+      "step": 5000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.4962366986763562e-05,
+      "loss": 0.8497,
+      "step": 5500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.1718141707760188e-05,
+      "loss": 0.8336,
+      "step": 6000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.473916428756813e-06,
+      "loss": 0.8292,
+      "step": 6500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.229691149753439e-06,
+      "loss": 0.8207,
+      "step": 7000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.985465870750065e-06,
+      "loss": 0.8128,
+      "step": 7500
+    },
+    {
+      "epoch": 2.0,
+      "step": 7806,
+      "total_flos": 2.5178769031430144e+17,
+      "train_loss": 0.9868680038667171,
+      "train_runtime": 7400.7434,
+      "train_samples_per_second": 405.116,
+      "train_steps_per_second": 1.055
+    }
+  ],
+  "max_steps": 7806,
+  "num_train_epochs": 2,
+  "total_flos": 2.5178769031430144e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66b99209ff0a2cfe93ed9176774023224d8ae21852b86d0e40f92b9dcc0dfad
+size 3311