Upload 9 files

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": "4.32.1",
+  "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": "4.32.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a610847bb61b16b3d320fd9e81f063cf8ac86d3093734f77b45dc6aefb62ed18
+size 1625541389

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 9012,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.722592099422992e-05,
+      "loss": 1.4475,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.4451841988459835e-05,
+      "loss": 1.176,
+      "step": 1000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.167776298268975e-05,
+      "loss": 1.1202,
+      "step": 1500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.890368397691966e-05,
+      "loss": 1.0756,
+      "step": 2000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.612960497114958e-05,
+      "loss": 1.0282,
+      "step": 2500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.3355525965379494e-05,
+      "loss": 1.0141,
+      "step": 3000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.058144695960941e-05,
+      "loss": 0.9844,
+      "step": 3500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.7807367953839327e-05,
+      "loss": 0.9714,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5033288948069243e-05,
+      "loss": 0.9554,
+      "step": 4500
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.225920994229916e-05,
+      "loss": 0.864,
+      "step": 5000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.9485130936529072e-05,
+      "loss": 0.8439,
+      "step": 5500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.671105193075899e-05,
+      "loss": 0.84,
+      "step": 6000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.3936972924988904e-05,
+      "loss": 0.8381,
+      "step": 6500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.116289391921882e-05,
+      "loss": 0.83,
+      "step": 7000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.388814913448735e-06,
+      "loss": 0.8192,
+      "step": 7500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5.614735907678651e-06,
+      "loss": 0.8102,
+      "step": 8000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.8406569019085665e-06,
+      "loss": 0.805,
+      "step": 8500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.657789613848203e-08,
+      "loss": 0.8009,
+      "step": 9000
+    },
+    {
+      "epoch": 2.0,
+      "step": 9012,
+      "total_flos": 2.0306395703938253e+17,
+      "train_loss": 0.9567329946010842,
+      "train_runtime": 10006.773,
+      "train_samples_per_second": 14.409,
+      "train_steps_per_second": 0.901
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9012,
+  "num_train_epochs": 2,
+  "save_steps": 4500,
+  "total_flos": 2.0306395703938253e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685220e03e507a42c6e1ec908410c4379daed3de2f1a31148df34582acecaaad
+size 4155