[Model] bart-base-squad

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": [
+    "BartForQuestionAnswering"
+  ],
+  "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"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "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": "4.16.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec8dd92f3cd4244945c54334a432a67a4402358e9a71193ea9e8f68bf8a313b
+size 1115540499

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a3380040688dbff92f0b62f060d69caf44f2d159a954cc531174a744c9238f
+size 557791521

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0eeb4c39a07ddb70b1d384a455f848d4f95bcdc6cc019c4de38536be6f39e23
+size 14659

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae6f423e03bb6a7ffc892c618affa609bc708ee76cd70a7fde72d43bf9569cb
+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, "use_fase": true, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base", "tokenizer_class": "BartTokenizer"}

trainer_state.json

@@ -0,0 +1,340 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.877167630057803,
+  "global_step": 27000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 6.020469596628538e-06,
+      "loss": 3.6306,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18,
+      "eval_exact_match": 61.45695364238411,
+      "eval_f1": 72.78282401033857,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.869710596102849e-06,
+      "loss": 1.6038,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36,
+      "eval_exact_match": 75.1844843897824,
+      "eval_f1": 84.48829717580529,
+      "step": 2000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.485376071332488e-06,
+      "loss": 1.2887,
+      "step": 3000
+    },
+    {
+      "epoch": 0.54,
+      "eval_exact_match": 78.53358561967833,
+      "eval_f1": 87.09051972422425,
+      "step": 3000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.101041546562128e-06,
+      "loss": 1.1686,
+      "step": 4000
+    },
+    {
+      "epoch": 0.72,
+      "eval_exact_match": 79.52696310312204,
+      "eval_f1": 87.93479628909573,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.716707021791769e-06,
+      "loss": 1.1108,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9,
+      "eval_exact_match": 80.53926206244087,
+      "eval_f1": 88.73699523092536,
+      "step": 5000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.332372497021408e-06,
+      "loss": 1.0369,
+      "step": 6000
+    },
+    {
+      "epoch": 1.08,
+      "eval_exact_match": 81.81646168401136,
+      "eval_f1": 89.39106999844736,
+      "step": 6000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 7.948037972251048e-06,
+      "loss": 0.958,
+      "step": 7000
+    },
+    {
+      "epoch": 1.26,
+      "eval_exact_match": 81.91106906338695,
+      "eval_f1": 89.56880578196049,
+      "step": 7000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 7.563703447480688e-06,
+      "loss": 0.9526,
+      "step": 8000
+    },
+    {
+      "epoch": 1.45,
+      "eval_exact_match": 82.65846736045411,
+      "eval_f1": 90.03671875268634,
+      "step": 8000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.179368922710328e-06,
+      "loss": 0.9191,
+      "step": 9000
+    },
+    {
+      "epoch": 1.63,
+      "eval_exact_match": 82.99905392620624,
+      "eval_f1": 90.20622146176154,
+      "step": 9000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 6.795034397939968e-06,
+      "loss": 0.9354,
+      "step": 10000
+    },
+    {
+      "epoch": 1.81,
+      "eval_exact_match": 82.79091769157995,
+      "eval_f1": 90.11036500429192,
+      "step": 10000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 6.410699873169607e-06,
+      "loss": 0.899,
+      "step": 11000
+    },
+    {
+      "epoch": 1.99,
+      "eval_exact_match": 83.07473982970671,
+      "eval_f1": 90.31558728723542,
+      "step": 11000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 6.026365348399247e-06,
+      "loss": 0.8149,
+      "step": 12000
+    },
+    {
+      "epoch": 2.17,
+      "eval_exact_match": 84.03973509933775,
+      "eval_f1": 90.85216746584881,
+      "step": 12000
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 5.6420308236288864e-06,
+      "loss": 0.8048,
+      "step": 13000
+    },
+    {
+      "epoch": 2.35,
+      "eval_exact_match": 83.92620624408704,
+      "eval_f1": 90.85115666556608,
+      "step": 13000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 5.257696298858527e-06,
+      "loss": 0.8114,
+      "step": 14000
+    },
+    {
+      "epoch": 2.53,
+      "eval_exact_match": 83.65184484389782,
+      "eval_f1": 90.78896967774679,
+      "step": 14000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.873361774088167e-06,
+      "loss": 0.7993,
+      "step": 15000
+    },
+    {
+      "epoch": 2.71,
+      "eval_exact_match": 84.19110690633869,
+      "eval_f1": 91.08154074192161,
+      "step": 15000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 4.4890272493178065e-06,
+      "loss": 0.7827,
+      "step": 16000
+    },
+    {
+      "epoch": 2.89,
+      "eval_exact_match": 84.19110690633869,
+      "eval_f1": 91.13367427096787,
+      "step": 16000
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 4.104692724547447e-06,
+      "loss": 0.7532,
+      "step": 17000
+    },
+    {
+      "epoch": 3.07,
+      "eval_exact_match": 84.21948912015137,
+      "eval_f1": 91.1856347835388,
+      "step": 17000
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.720358199777086e-06,
+      "loss": 0.7193,
+      "step": 18000
+    },
+    {
+      "epoch": 3.25,
+      "eval_exact_match": 84.26679280983917,
+      "eval_f1": 91.23320546520823,
+      "step": 18000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 3.3360236750067258e-06,
+      "loss": 0.7207,
+      "step": 19000
+    },
+    {
+      "epoch": 3.43,
+      "eval_exact_match": 84.50331125827815,
+      "eval_f1": 91.35916978909299,
+      "step": 19000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 2.951689150236366e-06,
+      "loss": 0.7191,
+      "step": 20000
+    },
+    {
+      "epoch": 3.61,
+      "eval_exact_match": 84.41816461684012,
+      "eval_f1": 91.31523088316432,
+      "step": 20000
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 2.567354625466006e-06,
+      "loss": 0.7171,
+      "step": 21000
+    },
+    {
+      "epoch": 3.79,
+      "eval_exact_match": 84.50331125827815,
+      "eval_f1": 91.36423189060977,
+      "step": 21000
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 2.1830201006956455e-06,
+      "loss": 0.705,
+      "step": 22000
+    },
+    {
+      "epoch": 3.97,
+      "eval_exact_match": 84.76821192052981,
+      "eval_f1": 91.50448097761131,
+      "step": 22000
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 1.7986855759252856e-06,
+      "loss": 0.6757,
+      "step": 23000
+    },
+    {
+      "epoch": 4.15,
+      "eval_exact_match": 84.33301797540209,
+      "eval_f1": 91.37392029075976,
+      "step": 23000
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 1.4143510511549255e-06,
+      "loss": 0.6607,
+      "step": 24000
+    },
+    {
+      "epoch": 4.34,
+      "eval_exact_match": 84.59791863765373,
+      "eval_f1": 91.43676774222646,
+      "step": 24000
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 1.0300165263845651e-06,
+      "loss": 0.6783,
+      "step": 25000
+    },
+    {
+      "epoch": 4.52,
+      "eval_exact_match": 84.64522232734153,
+      "eval_f1": 91.49154084773687,
+      "step": 25000
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 6.45682001614205e-07,
+      "loss": 0.6592,
+      "step": 26000
+    },
+    {
+      "epoch": 4.7,
+      "eval_exact_match": 84.82497634815516,
+      "eval_f1": 91.6291225955011,
+      "step": 26000
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 2.613474768438449e-07,
+      "loss": 0.671,
+      "step": 27000
+    },
+    {
+      "epoch": 4.88,
+      "eval_exact_match": 84.78713339640493,
+      "eval_f1": 91.63400716675376,
+      "step": 27000
+    }
+  ],
+  "max_steps": 27680,
+  "num_train_epochs": 5,
+  "total_flos": 9.877152009845146e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:970eaa587156caf23ef2f702269e5ba0a19bf72d4577e39ad54533fffd6ed8bb
+size 3055