Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,29 @@
+{
+    "ave/id": 0.8347382732834806,
+    "ave/ood": 0.581439393939394,
+    "ave/stress": 75.32590117876325,
+    "ave/transfer": 0.7306273062730627,
+    "epoch": 3.0,
+    "eval_accuracy": 64.2156862745098,
+    "eval_combined_score": 0.7306273062730627,
+    "eval_f1": 0.7306273062730627,
+    "eval_loss": 0.8416944146156311,
+    "eval_runtime": 4.4197,
+    "eval_samples_per_second": 92.314,
+    "eval_steps_per_second": 0.453,
+    "gap/ood": 0.25329887934408657,
+    "gap/stress": 8.14792614958482,
+    "gap/transfer": 0.10411096701041789,
+    "ood": 0.581439393939394,
+    "qqp": 0.8347382732834806,
+    "stress-antonym": 53.94653757103768,
+    "stress-length_mismatch": 76.80488163505366,
+    "stress-negation": 83.9194045174538,
+    "stress-spelling_error": 78.48741704448389,
+    "stress-word_overlap": 83.4712651257872,
+    "train_loss": 0.5190071157620331,
+    "train_runtime": 16824.7815,
+    "train_samples_per_second": 64.877,
+    "train_steps_per_second": 2.028,
+    "transfer": 0.7306273062730627
+}

ood_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_combined_score": 0.581439393939394,
+    "eval_f1": 0.581439393939394,
+    "eval_loss": 1.0221954584121704,
+    "eval_runtime": 66.1818,
+    "eval_samples_per_second": 120.879,
+    "eval_steps_per_second": 0.484
+}

pred_ood.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160a67c90bfd405257e258d5ca27c72716df5c6afe592f5a21db89f58b4d47ff
+size 64128

pred_qqp.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dbdd76266b17c61bacf59d5fe238521f891b0476d3539db57165d594066ef51
+size 323568

pred_stress-antonym.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832972c74e1673bba8383ae6ca0b50284b8b0ac92c83b8640a2055fe684d9fff
+size 55640

pred_stress-length_mismatch.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f945a4edd858f26d7eec43c60557f85fb310ffd3849a5242a6d49885f680c0
+size 323568

pred_stress-negation.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0159d1ca3a37b65f0780df8dc9505cd112ee1273fbabf294ce9751bc53aed4aa
+size 323568

pred_stress-spelling_error.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0819c54d9014c899d03c579b4a905599b4f7fcd77a7fcb220a95bdeaf81129b9
+size 323560

pred_stress-word_overlap.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a959d1a6fa4f4c419b3cb36847071fca1d00b532d7e8083313f754e53b5c5c
+size 323568

pred_transfer.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3bf886af93975f826601e2d2c24479afeb5a638885d541140d16d5c54f7e4d7
+size 3392

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd83df2533e5a9c0caf14aaa21e888eec62671f75ca0178ffd5f3fd12ffa75ee
+size 497125317

qqp_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_combined_score": 0.8347382732834806,
+    "eval_f1": 0.8347382732834806,
+    "eval_loss": 0.3031536936759949,
+    "eval_runtime": 328.4997,
+    "eval_samples_per_second": 123.075,
+    "eval_steps_per_second": 0.481
+}

rep_ood.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135f7e37e5301c44dd5a0744455a708fd1de90ebe16965141ec909d9ab7e018b
+size 295016562

rep_qqp.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4678e46c3a294f13e2340a80e131645076b0e48c4dd0bf1dfad8e35bf2da17cd
+size 1490929122

rep_transfer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e4d89ee3b4f0790b468532d0b5b76093bea8bc32a501e32e1cecbd393ec3d2
+size 15048218

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

stress-antonym_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 36.9361579478311,
+    "eval_combined_score": 45.44134775943439,
+    "eval_f1": 53.94653757103768,
+    "eval_loss": 2.105654239654541,
+    "eval_runtime": 31.9271,
+    "eval_samples_per_second": 217.339,
+    "eval_steps_per_second": 0.877
+}

stress-length_mismatch_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 84.39277764036606,
+    "eval_combined_score": 80.59882963770985,
+    "eval_f1": 76.80488163505366,
+    "eval_loss": 0.40738645195961,
+    "eval_runtime": 185.4181,
+    "eval_samples_per_second": 218.048,
+    "eval_steps_per_second": 0.852
+}

stress-negation_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 87.60326490230027,
+    "eval_combined_score": 85.76133470987703,
+    "eval_f1": 83.9194045174538,
+    "eval_loss": 0.33862820267677307,
+    "eval_runtime": 185.2649,
+    "eval_samples_per_second": 218.228,
+    "eval_steps_per_second": 0.853
+}

stress-spelling_error_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 83.80370526107497,
+    "eval_combined_score": 81.14556115277944,
+    "eval_f1": 78.48741704448389,
+    "eval_loss": 0.45842865109443665,
+    "eval_runtime": 185.7532,
+    "eval_samples_per_second": 217.649,
+    "eval_steps_per_second": 0.851
+}

stress-word_overlap_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 87.60079149146674,
+    "eval_combined_score": 85.53602830862697,
+    "eval_f1": 83.4712651257872,
+    "eval_loss": 0.3298536241054535,
+    "eval_runtime": 185.352,
+    "eval_samples_per_second": 218.125,
+    "eval_steps_per_second": 0.852
+}

test_results.json

@@ -0,0 +1,10 @@
+{
+    "ave/id": 0.8347382732834806,
+    "ave/ood": 0.581439393939394,
+    "ave/transfer": 0.7306273062730627,
+    "gap/ood": 0.25329887934408657,
+    "gap/transfer": 0.10411096701041789,
+    "ood": 0.581439393939394,
+    "qqp": 0.8347382732834806,
+    "transfer": 0.7306273062730627
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.5190071157620331,
+    "train_runtime": 16824.7815,
+    "train_samples_per_second": 64.877,
+    "train_steps_per_second": 2.028
+}

trainer_state.json

@@ -0,0 +1,466 @@
+{
+  "best_metric": 83.47382732834807,
+  "best_model_checkpoint": "outputs/bert-base/read/qqp_21/checkpoint-34113",
+  "epoch": 3.0,
+  "global_step": 34113,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9706856623574592e-05,
+      "loss": 1.0084,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9413713247149183e-05,
+      "loss": 0.8419,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9120569870723774e-05,
+      "loss": 0.8143,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.882742649429836e-05,
+      "loss": 0.7867,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8534283117872952e-05,
+      "loss": 0.7527,
+      "step": 2500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8241139741447543e-05,
+      "loss": 0.7196,
+      "step": 3000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7947996365022134e-05,
+      "loss": 0.7084,
+      "step": 3500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.7654852988596725e-05,
+      "loss": 0.7061,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.7361709612171312e-05,
+      "loss": 0.6954,
+      "step": 4500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7068566235745903e-05,
+      "loss": 0.6655,
+      "step": 5000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6775422859320497e-05,
+      "loss": 0.6848,
+      "step": 5500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.6482279482895085e-05,
+      "loss": 0.6627,
+      "step": 6000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6189136106469676e-05,
+      "loss": 0.6611,
+      "step": 6500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5895992730044266e-05,
+      "loss": 0.6529,
+      "step": 7000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5602849353618857e-05,
+      "loss": 0.6523,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5309705977193448e-05,
+      "loss": 0.6372,
+      "step": 8000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.5016562600768037e-05,
+      "loss": 0.6292,
+      "step": 8500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4723419224342628e-05,
+      "loss": 0.6175,
+      "step": 9000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.4430275847917217e-05,
+      "loss": 0.6209,
+      "step": 9500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.4137132471491808e-05,
+      "loss": 0.601,
+      "step": 10000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.3843989095066399e-05,
+      "loss": 0.6187,
+      "step": 10500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.3550845718640988e-05,
+      "loss": 0.6059,
+      "step": 11000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 85.65669057630473,
+      "eval_combined_score": 83.02644541999376,
+      "eval_f1": 80.39620026368279,
+      "eval_loss": 0.33604589104652405,
+      "eval_runtime": 185.3047,
+      "eval_samples_per_second": 218.181,
+      "eval_steps_per_second": 0.853,
+      "step": 11371
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.3257702342215579e-05,
+      "loss": 0.5663,
+      "step": 11500
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.2964558965790168e-05,
+      "loss": 0.4977,
+      "step": 12000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.2671415589364759e-05,
+      "loss": 0.5059,
+      "step": 12500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.2378272212939351e-05,
+      "loss": 0.498,
+      "step": 13000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.208512883651394e-05,
+      "loss": 0.4926,
+      "step": 13500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.1791985460088531e-05,
+      "loss": 0.5115,
+      "step": 14000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.149884208366312e-05,
+      "loss": 0.4982,
+      "step": 14500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.1205698707237711e-05,
+      "loss": 0.4844,
+      "step": 15000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.0912555330812302e-05,
+      "loss": 0.4907,
+      "step": 15500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0619411954386891e-05,
+      "loss": 0.4817,
+      "step": 16000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.0326268577961482e-05,
+      "loss": 0.4939,
+      "step": 16500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0033125201536071e-05,
+      "loss": 0.4862,
+      "step": 17000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.739981825110662e-06,
+      "loss": 0.4908,
+      "step": 17500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.446838448685253e-06,
+      "loss": 0.4905,
+      "step": 18000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.153695072259843e-06,
+      "loss": 0.4747,
+      "step": 18500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.860551695834433e-06,
+      "loss": 0.4854,
+      "step": 19000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.567408319409023e-06,
+      "loss": 0.4888,
+      "step": 19500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 8.274264942983614e-06,
+      "loss": 0.4719,
+      "step": 20000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.981121566558205e-06,
+      "loss": 0.4796,
+      "step": 20500
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.687978190132794e-06,
+      "loss": 0.4802,
+      "step": 21000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 7.394834813707384e-06,
+      "loss": 0.4785,
+      "step": 21500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 7.101691437281976e-06,
+      "loss": 0.4794,
+      "step": 22000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.808548060856566e-06,
+      "loss": 0.4631,
+      "step": 22500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 87.1852584714321,
+      "eval_combined_score": 84.72924948411651,
+      "eval_f1": 82.2732404968009,
+      "eval_loss": 0.30167102813720703,
+      "eval_runtime": 185.4875,
+      "eval_samples_per_second": 217.966,
+      "eval_steps_per_second": 0.852,
+      "step": 22742
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 6.515404684431156e-06,
+      "loss": 0.4336,
+      "step": 23000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 6.222261308005746e-06,
+      "loss": 0.3743,
+      "step": 23500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5.929117931580336e-06,
+      "loss": 0.3761,
+      "step": 24000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 5.6359745551549274e-06,
+      "loss": 0.3836,
+      "step": 24500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.3428311787295174e-06,
+      "loss": 0.374,
+      "step": 25000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 5.049687802304107e-06,
+      "loss": 0.3803,
+      "step": 25500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 4.756544425878697e-06,
+      "loss": 0.39,
+      "step": 26000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.463401049453288e-06,
+      "loss": 0.3824,
+      "step": 26500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 4.170257673027878e-06,
+      "loss": 0.3821,
+      "step": 27000
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 3.877114296602469e-06,
+      "loss": 0.3875,
+      "step": 27500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 3.583970920177059e-06,
+      "loss": 0.3796,
+      "step": 28000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 3.290827543751649e-06,
+      "loss": 0.368,
+      "step": 28500
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 2.9976841673262398e-06,
+      "loss": 0.3836,
+      "step": 29000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.7045407909008298e-06,
+      "loss": 0.3737,
+      "step": 29500
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.41139741447542e-06,
+      "loss": 0.3808,
+      "step": 30000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.1182540380500106e-06,
+      "loss": 0.3698,
+      "step": 30500
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.825110661624601e-06,
+      "loss": 0.3659,
+      "step": 31000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.531967285199191e-06,
+      "loss": 0.3741,
+      "step": 31500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.2388239087737813e-06,
+      "loss": 0.3702,
+      "step": 32000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 9.456805323483717e-07,
+      "loss": 0.3762,
+      "step": 32500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 6.525371559229619e-07,
+      "loss": 0.3653,
+      "step": 33000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 3.5939377949755233e-07,
+      "loss": 0.3711,
+      "step": 33500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 6.62504030721426e-08,
+      "loss": 0.3522,
+      "step": 34000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 87.97427652733118,
+      "eval_combined_score": 85.72405192783962,
+      "eval_f1": 83.47382732834807,
+      "eval_loss": 0.3031536936759949,
+      "eval_runtime": 185.5779,
+      "eval_samples_per_second": 217.86,
+      "eval_steps_per_second": 0.851,
+      "step": 34113
+    },
+    {
+      "epoch": 3.0,
+      "step": 34113,
+      "total_flos": 0.0,
+      "train_loss": 0.5190071157620331,
+      "train_runtime": 16824.7815,
+      "train_samples_per_second": 64.877,
+      "train_steps_per_second": 2.028
+    }
+  ],
+  "max_steps": 34113,
+  "num_train_epochs": 3,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21a4021b2eef0f00400bd5c5167b646240e28442ca498b93e674bf2f1062dd5
+size 4027

transfer_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_combined_score": 0.7306273062730627,
+    "eval_f1": 0.7306273062730627,
+    "eval_loss": 0.8416944146156311,
+    "eval_runtime": 4.4197,
+    "eval_samples_per_second": 92.314,
+    "eval_steps_per_second": 0.453
+}