[Model] bart-base-mrpc

config.json

@@ -0,0 +1,74 @@
+{
+  "_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": "mrpc",
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 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": "single_label_classification",
+  "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:b8eaa08c80a99f86d51c979acdfa12e3fbfa18c2230fffc2b5f76114b97924ff
+size 1120266491

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2f779a8e650ec93660730930129427c815711a08182371a4e68b8e02b93d53
+size 560154805

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6239b4bd31ab65f4cbe41f13bd5255146e95529c725465834c841d341509bb6d
+size 14659

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89fa3caadb7ca0b7615cfb0346ae6d13f4e13a14b6a4c349ca7e187eb6fe574
+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 +1,135 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.173913043478262,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.891891891891892e-05,
+      "loss": 0.5364,
+      "step": 200
+    },
+    {
+      "epoch": 1.74,
+      "eval_accuracy": 0.8382352941176471,
+      "eval_combined_score": 0.8622210953346856,
+      "eval_f1": 0.8862068965517241,
+      "eval_loss": 0.35622578859329224,
+      "eval_runtime": 3.0414,
+      "eval_samples_per_second": 134.148,
+      "eval_steps_per_second": 4.274,
+      "step": 200
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 1.711711711711712e-05,
+      "loss": 0.3136,
+      "step": 400
+    },
+    {
+      "epoch": 3.48,
+      "eval_accuracy": 0.8259803921568627,
+      "eval_combined_score": 0.8546979136482178,
+      "eval_f1": 0.883415435139573,
+      "eval_loss": 0.480543851852417,
+      "eval_runtime": 1.4071,
+      "eval_samples_per_second": 289.952,
+      "eval_steps_per_second": 9.239,
+      "step": 400
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 1.5315315315315316e-05,
+      "loss": 0.1818,
+      "step": 600
+    },
+    {
+      "epoch": 5.22,
+      "eval_accuracy": 0.8627450980392157,
+      "eval_combined_score": 0.8808310327741204,
+      "eval_f1": 0.8989169675090252,
+      "eval_loss": 0.4389028251171112,
+      "eval_runtime": 1.4446,
+      "eval_samples_per_second": 282.425,
+      "eval_steps_per_second": 8.999,
+      "step": 600
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 1.3513513513513515e-05,
+      "loss": 0.1187,
+      "step": 800
+    },
+    {
+      "epoch": 6.96,
+      "eval_accuracy": 0.8627450980392157,
+      "eval_combined_score": 0.8824215000685589,
+      "eval_f1": 0.9020979020979022,
+      "eval_loss": 0.46325385570526123,
+      "eval_runtime": 1.4574,
+      "eval_samples_per_second": 279.945,
+      "eval_steps_per_second": 8.92,
+      "step": 800
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 1.1711711711711713e-05,
+      "loss": 0.0622,
+      "step": 1000
+    },
+    {
+      "epoch": 8.7,
+      "eval_accuracy": 0.8725490196078431,
+      "eval_combined_score": 0.8919059091213277,
+      "eval_f1": 0.9112627986348123,
+      "eval_loss": 0.8588500618934631,
+      "eval_runtime": 1.4112,
+      "eval_samples_per_second": 289.113,
+      "eval_steps_per_second": 9.212,
+      "step": 1000
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 9.90990990990991e-06,
+      "loss": 0.0524,
+      "step": 1200
+    },
+    {
+      "epoch": 10.43,
+      "eval_accuracy": 0.8774509803921569,
+      "eval_combined_score": 0.8945558788886578,
+      "eval_f1": 0.9116607773851589,
+      "eval_loss": 0.6909387111663818,
+      "eval_runtime": 1.4612,
+      "eval_samples_per_second": 279.229,
+      "eval_steps_per_second": 8.897,
+      "step": 1200
+    },
+    {
+      "epoch": 12.17,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 0.043,
+      "step": 1400
+    },
+    {
+      "epoch": 12.17,
+      "eval_accuracy": 0.875,
+      "eval_combined_score": 0.8943527918781726,
+      "eval_f1": 0.9137055837563453,
+      "eval_loss": 0.876980185508728,
+      "eval_runtime": 1.4427,
+      "eval_samples_per_second": 282.811,
+      "eval_steps_per_second": 9.011,
+      "step": 1400
+    }
+  ],
+  "max_steps": 2300,
+  "num_train_epochs": 20,
+  "total_flos": 3423856486686720.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327097767a37332e9264b31e53092e3bc9959d78156badb3437a1cd7a72599a1
+size 2991