Initial commit

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": "4.14.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0faad8b521e65cd2426635b29b28ea4f6e386c6865643129032376d3df88aba
+size 1115513717

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3815f2c4f12defa0a5978de011704b5789be8f3b44b11e838bc0a11023a2e7f4
+size 557979193

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a7dffaffa7f4cbaa97bc87fde3fb69c1096a49131dcb623834ea57deb14436
+size 14439

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0985573bd3a5d9a4b43a4a03e5808372461006ce985904977e4d05bc623921d6
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aaad11eb37b53c6e1ff0a06338561ab27aa64cc708ed3e3aacfdcbe6f4fff79
+size 623

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

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 3.2501280307769775,
+  "best_model_checkpoint": "./results-bart-base/checkpoint-38400",
+  "epoch": 4.0,
+  "global_step": 38400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5003125e-05,
+      "loss": 3.4014,
+      "step": 9600
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.2687737941741943,
+      "eval_runtime": 36.2388,
+      "eval_samples_per_second": 40.951,
+      "eval_steps_per_second": 40.951,
+      "step": 9600
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.0005208333333334e-05,
+      "loss": 3.1216,
+      "step": 19200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.2523913383483887,
+      "eval_runtime": 36.0255,
+      "eval_samples_per_second": 41.193,
+      "eval_steps_per_second": 41.193,
+      "step": 19200
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.006770833333334e-06,
+      "loss": 2.984,
+      "step": 28800
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.2509608268737793,
+      "eval_runtime": 36.1722,
+      "eval_samples_per_second": 41.026,
+      "eval_steps_per_second": 41.026,
+      "step": 28800
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 8.333333333333335e-09,
+      "loss": 2.9004,
+      "step": 38400
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.2501280307769775,
+      "eval_runtime": 36.2569,
+      "eval_samples_per_second": 40.93,
+      "eval_steps_per_second": 40.93,
+      "step": 38400
+    }
+  ],
+  "max_steps": 38400,
+  "num_train_epochs": 4,
+  "total_flos": 3.277740271583232e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82194da2cc62dbd1ab45e7b26e865bf1ad2fdc02082f65abe3eba76d6695f7f1
+size 3055