Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,29 @@
+{
+    "ave/id": 0.822529723920199,
+    "ave/ood": 0.5996446273262882,
+    "ave/stress": 73.00517780542164,
+    "ave/transfer": 0.7847682119205298,
+    "epoch": 3.0,
+    "eval_accuracy": 68.13725490196079,
+    "eval_combined_score": 0.7847682119205298,
+    "eval_f1": 0.7847682119205298,
+    "eval_loss": 0.6564677953720093,
+    "eval_runtime": 12.1978,
+    "eval_samples_per_second": 33.449,
+    "eval_steps_per_second": 0.164,
+    "gap/ood": 0.22288509659391076,
+    "gap/stress": 9.24779458659826,
+    "gap/transfer": 0.03776151199966915,
+    "ood": 0.5996446273262882,
+    "qqp": 0.822529723920199,
+    "stress-antonym": 47.66190998902305,
+    "stress-length_mismatch": 75.9537323083555,
+    "stress-negation": 82.64870505644625,
+    "stress-spelling_error": 76.82830014924899,
+    "stress-word_overlap": 81.93324152403436,
+    "train_loss": 0.4883681108792707,
+    "train_runtime": 51068.5732,
+    "train_samples_per_second": 21.374,
+    "train_steps_per_second": 0.668,
+    "transfer": 0.7847682119205298
+}

ood_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_combined_score": 0.5996446273262882,
+    "eval_f1": 0.5996446273262882,
+    "eval_loss": 0.9656124711036682,
+    "eval_runtime": 209.9586,
+    "eval_samples_per_second": 38.103,
+    "eval_steps_per_second": 0.152
+}

pred_ood.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:728f305a898401474115f3a50cc25e7d41a5b272e38026cd50513b0212581271
+size 64128

pred_qqp.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656ddee7afc540bc9ff76d1176d7b9cbcc81077deb0b794d20b47124f31e9af0
+size 323568

pred_stress-antonym.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c40e675366e40ba67fca6bcedac3a6d61a1c08d8f76f9427fe83f49192899e
+size 55640

pred_stress-length_mismatch.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da631aaebd90bbd9d1d5b46b3ca758490cc34daac506156737c688dac9a926f
+size 323568

pred_stress-negation.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7332721b238cfe72dc66820154fcaf8fb0108e8e0daac8854a0d32f8103bf3
+size 323568

pred_stress-spelling_error.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57bb1fa31f6603bbb9673e309806d09483d1760b28eef6ca0fa906fc11d53e9d
+size 323560

pred_stress-word_overlap.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d2aaef1bb0440fafc2df9237bada9ef957493c78883472b89d24d44bde669cd
+size 323568

pred_transfer.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998267be8316a44eff64b126f5af7a14a9cdc26d2c6710718ba94268becf0d79
+size 3392

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871259e3e95be9c17b8be87966685dca1b12d85cb65c5e94cf0b94abfbe1342f
+size 1546544837

qqp_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_combined_score": 0.822529723920199,
+    "eval_f1": 0.822529723920199,
+    "eval_loss": 0.3105922341346741,
+    "eval_runtime": 1051.5551,
+    "eval_samples_per_second": 38.448,
+    "eval_steps_per_second": 0.15
+}

rep_ood.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d855c89d48979128561a0ea3f78ece9d347232e5b7e8d9d4af6e1912d35281
+size 786641778

rep_qqp.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869d33d7645de642186a8fa83d70248073aab71848f2c98d2d9d9ad3c6496c00
+size 3975468602

rep_transfer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cef47a98af9e39456df269883fc7b07813bdc89e36d19735bd571ad9c77c1a
+size 40122890

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": 31.286928952298602,
+    "eval_combined_score": 39.47441947066083,
+    "eval_f1": 47.66190998902305,
+    "eval_loss": 1.8467786312103271,
+    "eval_runtime": 87.2979,
+    "eval_samples_per_second": 79.486,
+    "eval_steps_per_second": 0.321
+}

stress-length_mismatch_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 83.4429878802869,
+    "eval_combined_score": 79.6983600943212,
+    "eval_f1": 75.9537323083555,
+    "eval_loss": 0.3636408746242523,
+    "eval_runtime": 506.4353,
+    "eval_samples_per_second": 79.833,
+    "eval_steps_per_second": 0.312
+}

stress-negation_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 86.42839475636903,
+    "eval_combined_score": 84.53854990640764,
+    "eval_f1": 82.64870505644625,
+    "eval_loss": 0.32279783487319946,
+    "eval_runtime": 506.6385,
+    "eval_samples_per_second": 79.8,
+    "eval_steps_per_second": 0.312
+}

stress-spelling_error_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 81.9510747235895,
+    "eval_combined_score": 79.38968743641925,
+    "eval_f1": 76.82830014924899,
+    "eval_loss": 0.39652082324028015,
+    "eval_runtime": 506.9646,
+    "eval_samples_per_second": 79.747,
+    "eval_steps_per_second": 0.312
+}

stress-word_overlap_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 86.37150630719762,
+    "eval_combined_score": 84.15237391561598,
+    "eval_f1": 81.93324152403436,
+    "eval_loss": 0.3270297348499298,
+    "eval_runtime": 506.5782,
+    "eval_samples_per_second": 79.81,
+    "eval_steps_per_second": 0.312
+}

test_results.json

@@ -0,0 +1,10 @@
+{
+    "ave/id": 0.822529723920199,
+    "ave/ood": 0.5996446273262882,
+    "ave/transfer": 0.7847682119205298,
+    "gap/ood": 0.22288509659391076,
+    "gap/transfer": 0.03776151199966915,
+    "ood": 0.5996446273262882,
+    "qqp": 0.822529723920199,
+    "transfer": 0.7847682119205298
+}

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-large-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": 0.4883681108792707,
+    "train_runtime": 51068.5732,
+    "train_samples_per_second": 21.374,
+    "train_steps_per_second": 0.668
+}

trainer_state.json

@@ -0,0 +1,466 @@
+{
+  "best_metric": 82.2529723920199,
+  "best_model_checkpoint": "outputs/bert-large/read/qqp_21/checkpoint-22742",
+  "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": 1.0222,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9413713247149183e-05,
+      "loss": 0.852,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9120569870723774e-05,
+      "loss": 0.8152,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.882742649429836e-05,
+      "loss": 0.7953,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8534283117872952e-05,
+      "loss": 0.7809,
+      "step": 2500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8241139741447543e-05,
+      "loss": 0.7319,
+      "step": 3000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7947996365022134e-05,
+      "loss": 0.712,
+      "step": 3500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.7654852988596725e-05,
+      "loss": 0.7126,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.7361709612171312e-05,
+      "loss": 0.7097,
+      "step": 4500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7068566235745903e-05,
+      "loss": 0.6807,
+      "step": 5000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6775422859320497e-05,
+      "loss": 0.726,
+      "step": 5500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.6482279482895085e-05,
+      "loss": 0.6732,
+      "step": 6000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6189136106469676e-05,
+      "loss": 0.6733,
+      "step": 6500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5895992730044266e-05,
+      "loss": 0.6581,
+      "step": 7000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5602849353618857e-05,
+      "loss": 0.6497,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5309705977193448e-05,
+      "loss": 0.6385,
+      "step": 8000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.5016562600768037e-05,
+      "loss": 0.6359,
+      "step": 8500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4723419224342628e-05,
+      "loss": 0.6139,
+      "step": 9000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.4430275847917217e-05,
+      "loss": 0.6196,
+      "step": 9500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.4137132471491808e-05,
+      "loss": 0.6095,
+      "step": 10000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.3843989095066399e-05,
+      "loss": 0.6072,
+      "step": 10500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.3550845718640988e-05,
+      "loss": 0.5973,
+      "step": 11000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 85.27825871877319,
+      "eval_combined_score": 82.15065399461602,
+      "eval_f1": 79.02304927045887,
+      "eval_loss": 0.3653884828090668,
+      "eval_runtime": 504.8457,
+      "eval_samples_per_second": 80.084,
+      "eval_steps_per_second": 0.313,
+      "step": 11371
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.3257702342215579e-05,
+      "loss": 0.5597,
+      "step": 11500
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.2964558965790168e-05,
+      "loss": 0.4749,
+      "step": 12000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.2671415589364759e-05,
+      "loss": 0.4788,
+      "step": 12500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.2378272212939351e-05,
+      "loss": 0.4674,
+      "step": 13000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.208512883651394e-05,
+      "loss": 0.4711,
+      "step": 13500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.1791985460088531e-05,
+      "loss": 0.4785,
+      "step": 14000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.149884208366312e-05,
+      "loss": 0.4706,
+      "step": 14500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.1205698707237711e-05,
+      "loss": 0.4547,
+      "step": 15000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.0912555330812302e-05,
+      "loss": 0.4603,
+      "step": 15500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0619411954386891e-05,
+      "loss": 0.4496,
+      "step": 16000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.0326268577961482e-05,
+      "loss": 0.4645,
+      "step": 16500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0033125201536071e-05,
+      "loss": 0.4596,
+      "step": 17000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.739981825110662e-06,
+      "loss": 0.4616,
+      "step": 17500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.446838448685253e-06,
+      "loss": 0.4528,
+      "step": 18000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.153695072259843e-06,
+      "loss": 0.4414,
+      "step": 18500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.860551695834433e-06,
+      "loss": 0.4628,
+      "step": 19000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.567408319409023e-06,
+      "loss": 0.4604,
+      "step": 19500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 8.274264942983614e-06,
+      "loss": 0.4445,
+      "step": 20000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.981121566558205e-06,
+      "loss": 0.4424,
+      "step": 20500
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.687978190132794e-06,
+      "loss": 0.4502,
+      "step": 21000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 7.394834813707384e-06,
+      "loss": 0.4467,
+      "step": 21500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 7.101691437281976e-06,
+      "loss": 0.4402,
+      "step": 22000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.808548060856566e-06,
+      "loss": 0.4292,
+      "step": 22500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 86.93049715557754,
+      "eval_combined_score": 84.59173477379872,
+      "eval_f1": 82.2529723920199,
+      "eval_loss": 0.3105922341346741,
+      "eval_runtime": 503.3674,
+      "eval_samples_per_second": 80.319,
+      "eval_steps_per_second": 0.314,
+      "step": 22742
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 6.515404684431156e-06,
+      "loss": 0.3798,
+      "step": 23000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 6.222261308005746e-06,
+      "loss": 0.308,
+      "step": 23500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5.929117931580336e-06,
+      "loss": 0.3142,
+      "step": 24000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 5.6359745551549274e-06,
+      "loss": 0.3145,
+      "step": 24500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.3428311787295174e-06,
+      "loss": 0.3071,
+      "step": 25000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 5.049687802304107e-06,
+      "loss": 0.3055,
+      "step": 25500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 4.756544425878697e-06,
+      "loss": 0.3194,
+      "step": 26000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.463401049453288e-06,
+      "loss": 0.3096,
+      "step": 26500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 4.170257673027878e-06,
+      "loss": 0.3128,
+      "step": 27000
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 3.877114296602469e-06,
+      "loss": 0.3235,
+      "step": 27500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 3.583970920177059e-06,
+      "loss": 0.3059,
+      "step": 28000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 3.290827543751649e-06,
+      "loss": 0.3027,
+      "step": 28500
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 2.9976841673262398e-06,
+      "loss": 0.3143,
+      "step": 29000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.7045407909008298e-06,
+      "loss": 0.3047,
+      "step": 29500
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.41139741447542e-06,
+      "loss": 0.3022,
+      "step": 30000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.1182540380500106e-06,
+      "loss": 0.3165,
+      "step": 30500
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.825110661624601e-06,
+      "loss": 0.2919,
+      "step": 31000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.531967285199191e-06,
+      "loss": 0.2984,
+      "step": 31500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.2388239087737813e-06,
+      "loss": 0.3019,
+      "step": 32000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 9.456805323483717e-07,
+      "loss": 0.3041,
+      "step": 32500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 6.525371559229619e-07,
+      "loss": 0.2857,
+      "step": 33000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 3.5939377949755233e-07,
+      "loss": 0.3026,
+      "step": 33500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 6.62504030721426e-08,
+      "loss": 0.2886,
+      "step": 34000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 87.05416769725451,
+      "eval_combined_score": 84.54568498803285,
+      "eval_f1": 82.03720227881118,
+      "eval_loss": 0.3072020709514618,
+      "eval_runtime": 503.7039,
+      "eval_samples_per_second": 80.265,
+      "eval_steps_per_second": 0.314,
+      "step": 34113
+    },
+    {
+      "epoch": 3.0,
+      "step": 34113,
+      "total_flos": 0.0,
+      "train_loss": 0.4883681108792707,
+      "train_runtime": 51068.5732,
+      "train_samples_per_second": 21.374,
+      "train_steps_per_second": 0.668
+    }
+  ],
+  "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 sha256:5cd0a4c5e25a3024a503c6866cabcbb86dcc4a99e0d2bb41e3c06b1b0bf85800
+size 4091

transfer_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_combined_score": 0.7847682119205298,
+    "eval_f1": 0.7847682119205298,
+    "eval_loss": 0.6564677953720093,
+    "eval_runtime": 12.1978,
+    "eval_samples_per_second": 33.449,
+    "eval_steps_per_second": 0.164
+}