[Model] bart-base-stsb

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "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,
+  "finetuning_task": "stsb",
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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,
+  "problem_type": "regression",
+  "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": "4.16.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d6ce2c3b19c7e62b9429536d03dbf0304321164af2bb96abf80e0468bf1cd9
+size 1120260347

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe5ad0f1c0f94f8a461a095b975420733966fe44ff3960422974c3f70fb2499
+size 560151733

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f33ce3e444265382c02749bd91390baee688daec1f459812cd1f76a9fdb1857
+size 14659

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79950a7159c6d3a9cd6eec9a5ac2033ed241ce5232767a3d19da65905dd7ba15
+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>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base", "tokenizer_class": "BartTokenizer"}

trainer_state.json

@@ -0,0 +1,237 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.444444444444445,
+  "global_step": 2600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.9201259662181504e-05,
+      "loss": 1.9337,
+      "step": 200
+    },
+    {
+      "epoch": 1.11,
+      "eval_combined_score": 0.855672098210929,
+      "eval_loss": 0.6694014668464661,
+      "eval_pearson": 0.8565553031421368,
+      "eval_runtime": 9.7338,
+      "eval_samples_per_second": 154.103,
+      "eval_spearmanr": 0.8547888932797213,
+      "eval_steps_per_second": 4.829,
+      "step": 200
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.7483538505582595e-05,
+      "loss": 0.5478,
+      "step": 400
+    },
+    {
+      "epoch": 2.22,
+      "eval_combined_score": 0.8820736249689372,
+      "eval_loss": 0.5202434659004211,
+      "eval_pearson": 0.883058769007019,
+      "eval_runtime": 7.0124,
+      "eval_samples_per_second": 213.907,
+      "eval_spearmanr": 0.8810884809308552,
+      "eval_steps_per_second": 6.702,
+      "step": 400
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 2.5765817348983683e-05,
+      "loss": 0.3875,
+      "step": 600
+    },
+    {
+      "epoch": 3.33,
+      "eval_combined_score": 0.8848872283962617,
+      "eval_loss": 0.5168328285217285,
+      "eval_pearson": 0.8858649045223065,
+      "eval_runtime": 8.7209,
+      "eval_samples_per_second": 172.0,
+      "eval_spearmanr": 0.8839095522702168,
+      "eval_steps_per_second": 5.389,
+      "step": 600
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 0.2873,
+      "step": 800
+    },
+    {
+      "epoch": 4.44,
+      "eval_combined_score": 0.8913594385875843,
+      "eval_loss": 0.4864712357521057,
+      "eval_pearson": 0.89199629173951,
+      "eval_runtime": 5.045,
+      "eval_samples_per_second": 297.324,
+      "eval_spearmanr": 0.8907225854356586,
+      "eval_steps_per_second": 9.316,
+      "step": 800
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 2.233037503578586e-05,
+      "loss": 0.2209,
+      "step": 1000
+    },
+    {
+      "epoch": 5.56,
+      "eval_combined_score": 0.8933856482982484,
+      "eval_loss": 0.47292622923851013,
+      "eval_pearson": 0.8928073121296423,
+      "eval_runtime": 6.2607,
+      "eval_samples_per_second": 239.589,
+      "eval_spearmanr": 0.8939639844668545,
+      "eval_steps_per_second": 7.507,
+      "step": 1000
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 2.0612653879186946e-05,
+      "loss": 0.1858,
+      "step": 1200
+    },
+    {
+      "epoch": 6.67,
+      "eval_combined_score": 0.8951297426092613,
+      "eval_loss": 0.4721234440803528,
+      "eval_pearson": 0.895018574604679,
+      "eval_runtime": 5.3661,
+      "eval_samples_per_second": 279.534,
+      "eval_spearmanr": 0.8952409106138436,
+      "eval_steps_per_second": 8.759,
+      "step": 1200
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 1.8894932722588034e-05,
+      "loss": 0.1488,
+      "step": 1400
+    },
+    {
+      "epoch": 7.78,
+      "eval_combined_score": 0.891447497560241,
+      "eval_loss": 0.4770796298980713,
+      "eval_pearson": 0.8911445993678931,
+      "eval_runtime": 5.0578,
+      "eval_samples_per_second": 296.572,
+      "eval_spearmanr": 0.8917503957525889,
+      "eval_steps_per_second": 9.293,
+      "step": 1400
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 1.7177211565989122e-05,
+      "loss": 0.1304,
+      "step": 1600
+    },
+    {
+      "epoch": 8.89,
+      "eval_combined_score": 0.8970612339600279,
+      "eval_loss": 0.48936206102371216,
+      "eval_pearson": 0.8980185335797246,
+      "eval_runtime": 14.0351,
+      "eval_samples_per_second": 106.875,
+      "eval_spearmanr": 0.8961039343403312,
+      "eval_steps_per_second": 3.349,
+      "step": 1600
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.545949040939021e-05,
+      "loss": 0.109,
+      "step": 1800
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": 0.8980839993104694,
+      "eval_loss": 0.5082814693450928,
+      "eval_pearson": 0.8984275062131546,
+      "eval_runtime": 8.418,
+      "eval_samples_per_second": 178.19,
+      "eval_spearmanr": 0.8977404924077843,
+      "eval_steps_per_second": 5.583,
+      "step": 1800
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 1.3741769252791297e-05,
+      "loss": 0.0921,
+      "step": 2000
+    },
+    {
+      "epoch": 11.11,
+      "eval_combined_score": 0.8993074838528512,
+      "eval_loss": 0.48581191897392273,
+      "eval_pearson": 0.9003551226268016,
+      "eval_runtime": 5.9476,
+      "eval_samples_per_second": 252.201,
+      "eval_spearmanr": 0.8982598450789009,
+      "eval_steps_per_second": 7.902,
+      "step": 2000
+    },
+    {
+      "epoch": 12.22,
+      "learning_rate": 1.2024048096192385e-05,
+      "loss": 0.0832,
+      "step": 2200
+    },
+    {
+      "epoch": 12.22,
+      "eval_combined_score": 0.8988999314237858,
+      "eval_loss": 0.4592455327510834,
+      "eval_pearson": 0.8999128062818325,
+      "eval_runtime": 5.0336,
+      "eval_samples_per_second": 297.999,
+      "eval_spearmanr": 0.8978870565657391,
+      "eval_steps_per_second": 9.337,
+      "step": 2200
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 1.0306326939593473e-05,
+      "loss": 0.0752,
+      "step": 2400
+    },
+    {
+      "epoch": 13.33,
+      "eval_combined_score": 0.8988264761743764,
+      "eval_loss": 0.4774340093135834,
+      "eval_pearson": 0.8993306926360871,
+      "eval_runtime": 5.4436,
+      "eval_samples_per_second": 275.552,
+      "eval_spearmanr": 0.8983222597126657,
+      "eval_steps_per_second": 8.634,
+      "step": 2400
+    },
+    {
+      "epoch": 14.44,
+      "learning_rate": 8.588605782994561e-06,
+      "loss": 0.0659,
+      "step": 2600
+    },
+    {
+      "epoch": 14.44,
+      "eval_combined_score": 0.9002469671281537,
+      "eval_loss": 0.44667911529541016,
+      "eval_pearson": 0.9010897645452967,
+      "eval_runtime": 4.9948,
+      "eval_samples_per_second": 300.31,
+      "eval_spearmanr": 0.8994041697110107,
+      "eval_steps_per_second": 9.41,
+      "step": 2600
+    }
+  ],
+  "max_steps": 3600,
+  "num_train_epochs": 20,
+  "total_flos": 6367238346060288.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e764ec57195fb7fcae048823113a5f62342dc3dc39c167ef7c050eaea9b4c4a9
+size 2991