Upload 14 files

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "GanjinZero/biobart-v2-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_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
+  },
+  "length_penalty": 2.0,
+  "max_length": 512,
+  "max_position_embeddings": 1024,
+  "min_length": 64,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "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": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 85401
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 512,
+  "min_length": 64,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee2a4dc14683bc14275b74e34dcc84af7769c8edeb9d16b1af705639a85342c
+size 1331389301

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7384ebea5db2009bd42df9301ce698994b2212147d59694c04583953d7ad118
+size 666047481

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e9c1bfa68bb6751eb2b85baf263096ae21a1aebb28e1790a40d13ff5685689
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:662dfb33bc4817e27dd1f5f17f4b2e3cb40f1f1b8bdc8cb01b7ae2d340adbbbf
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e405e1cf39a4eb197fb46af3a5479a43a2f47adbe7431828178bc578fbfe9991
+size 623

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "GanjinZero/biobart-v2-base",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 16875,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.90167244633686e-05,
+      "loss": 1.8507,
+      "step": 5625
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 118.742,
+      "eval_loss": 1.7119792699813843,
+      "eval_rouge1": 43.9318,
+      "eval_rouge2": 20.5803,
+      "eval_rougeL": 29.8807,
+      "eval_rougeLsum": 29.8748,
+      "eval_runtime": 8010.5572,
+      "eval_samples_per_second": 2.497,
+      "eval_steps_per_second": 2.497,
+      "step": 5625
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.914182871691323e-05,
+      "loss": 1.7161,
+      "step": 11250
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 110.7688,
+      "eval_loss": 1.6913355588912964,
+      "eval_rouge1": 43.936,
+      "eval_rouge2": 20.632,
+      "eval_rougeL": 30.1181,
+      "eval_rougeLsum": 30.1042,
+      "eval_runtime": 7456.3007,
+      "eval_samples_per_second": 2.682,
+      "eval_steps_per_second": 2.682,
+      "step": 11250
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.92686888196304e-05,
+      "loss": 1.6018,
+      "step": 16875
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 114.912,
+      "eval_loss": 1.6871464252471924,
+      "eval_rouge1": 44.5277,
+      "eval_rouge2": 21.0646,
+      "eval_rougeL": 30.3498,
+      "eval_rougeLsum": 30.3357,
+      "eval_runtime": 7764.9424,
+      "eval_samples_per_second": 2.576,
+      "eval_steps_per_second": 2.576,
+      "step": 16875
+    }
+  ],
+  "max_steps": 50625,
+  "num_train_epochs": 9,
+  "total_flos": 1.5024380365403136e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d897be7b7888bec452a7ac7beafa3ad0d76edf5fc932451707af6c0bc7c95060
+size 3631