Upload 13 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": "4.28.0",
+  "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": "4.28.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752cbe9af97d102d3cdb5866a7bf51224dd24cd71090e0fcd77bb8f430db710b
+size 3250632155

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28166bc3001b30bd6a7d4a3ca019888fc13ce9131b7f1c2c7044ab849deda6b9
+size 1625541389

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed2276b4431d9b17ee65e3c4ddafddbc6b3c6fb5cfb450cd94f18ef913c15af
+size 15597

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb3a07d02472a0c7263892683f16fb010db062c726c2f5630f74b29bd08c4bc
+size 627

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": 19.455252918287936,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.97,
+      "learning_rate": 1e-05,
+      "loss": 2.8118,
+      "step": 500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2e-05,
+      "loss": 2.4654,
+      "step": 1000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 2.3309,
+      "step": 1500
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 2.2215,
+      "step": 2000
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 2.1339,
+      "step": 2500
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 2.0631,
+      "step": 3000
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 1.996,
+      "step": 3500
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.9465,
+      "step": 4000
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 1.8886,
+      "step": 4500
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.8507,
+      "step": 5000
+    },
+    {
+      "epoch": 10.7,
+      "learning_rate": 1e-05,
+      "loss": 1.8059,
+      "step": 5500
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.77,
+      "step": 6000
+    },
+    {
+      "epoch": 12.65,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 1.7359,
+      "step": 6500
+    },
+    {
+      "epoch": 13.62,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.7084,
+      "step": 7000
+    },
+    {
+      "epoch": 14.59,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.685,
+      "step": 7500
+    },
+    {
+      "epoch": 15.56,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.6599,
+      "step": 8000
+    },
+    {
+      "epoch": 16.54,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.6413,
+      "step": 8500
+    },
+    {
+      "epoch": 17.51,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.6267,
+      "step": 9000
+    },
+    {
+      "epoch": 18.48,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.6128,
+      "step": 9500
+    },
+    {
+      "epoch": 19.46,
+      "learning_rate": 0.0,
+      "loss": 1.6036,
+      "step": 10000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 20,
+  "total_flos": 1.730801432568791e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e439f507e5420f74423ac96b2ddaa8308d9ab013be90f2d54dcea503df7c37f2
+size 3771