Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,29 @@
+{
+    "ave/id": 0.814885685064828,
+    "ave/ood": 0.6040905770635501,
+    "ave/stress": 77.33218437992298,
+    "ave/transfer": 0.7922077922077924,
+    "epoch": 3.0,
+    "eval_accuracy": 68.62745098039215,
+    "eval_combined_score": 0.7922077922077924,
+    "eval_f1": 0.7922077922077924,
+    "eval_loss": 0.8416510224342346,
+    "eval_runtime": 2.1923,
+    "eval_samples_per_second": 186.11,
+    "eval_steps_per_second": 0.912,
+    "gap/ood": 0.21079510800127788,
+    "gap/stress": 4.156384126559814,
+    "gap/transfer": 0.022677892857035586,
+    "ood": 0.6040905770635501,
+    "qqp": 0.814885685064828,
+    "stress-antonym": 70.67374895163545,
+    "stress-length_mismatch": 77.4223759095166,
+    "stress-negation": 81.71691107055196,
+    "stress-spelling_error": 75.08700102354146,
+    "stress-word_overlap": 81.76088494436941,
+    "train_loss": 0.6687755357152263,
+    "train_runtime": 7270.4925,
+    "train_samples_per_second": 150.133,
+    "train_steps_per_second": 4.692,
+    "transfer": 0.7922077922077924
+}

ood_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_combined_score": 0.6040905770635501,
+    "eval_f1": 0.6040905770635501,
+    "eval_loss": 1.6317058801651,
+    "eval_runtime": 23.59,
+    "eval_samples_per_second": 339.127,
+    "eval_steps_per_second": 1.357
+}

pred_ood.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:147fde8e4388463262853c50aaee36e29a83340f798b320a7ab57a013a622621
+size 64128

pred_qqp.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f816519dcc408966dc4eb6335fde7974a7ee7a4a270bb4b58a1b3f821c4ddb
+size 323568

pred_stress-antonym.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fe94b8a7ff316f15958517d13505a9b89e2f328c28b21a3bdb7711ff37866a
+size 55640

pred_stress-length_mismatch.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3690046dcf8126eb96ee8a80ca6bf64bca26df68d771875d3d5ad51d7f260a5
+size 323568

pred_stress-negation.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da9eab8378a0abf4c762d269d10b1f9664821de70bd99263ced080dc5b862a8
+size 323568

pred_stress-spelling_error.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478a94e2e102173ad0150d0a300da94ffda7081b6b6048cb9ac650b1aca667ad
+size 323560

pred_stress-word_overlap.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0962808319090258cfd4de1923ad8f02d759cdee12b36c3cd230f7f09a155e
+size 323568

pred_transfer.npz.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0b7c6dff30c24b4ba20e9a55a97f1252e5ac82c2a1023ad4ca097a46585948
+size 3392

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35442494bfd0ff646f239ed1d2e14f7d4131ef4b867deb09542351de2a22fc7a
+size 183448325

qqp_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_combined_score": 0.814885685064828,
+    "eval_f1": 0.814885685064828,
+    "eval_loss": 0.3177751898765564,
+    "eval_runtime": 112.2847,
+    "eval_samples_per_second": 360.067,
+    "eval_steps_per_second": 1.407
+}

rep_ood.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb89c1bfa9bf260691246d03b2b479d4094d2e506fe3758efb36189401e309b
+size 131141490

rep_qqp.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f1bce10e7e1bbaee84c4eb49ebf16509c603acd9c0ac144fb6f324a92b648a
+size 662749338

rep_transfer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c99473290b0c47facac82de2ba2ed4c7c6449048f9727315c26563b06205a9c
+size 6690122

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": 54.647643752702116,
+    "eval_combined_score": 62.660696352168785,
+    "eval_f1": 70.67374895163545,
+    "eval_loss": 1.0299919843673706,
+    "eval_runtime": 18.1327,
+    "eval_samples_per_second": 382.68,
+    "eval_steps_per_second": 1.544
+}

stress-length_mismatch_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 84.49666089537472,
+    "eval_combined_score": 80.95951840244567,
+    "eval_f1": 77.4223759095166,
+    "eval_loss": 0.35398587584495544,
+    "eval_runtime": 106.1714,
+    "eval_samples_per_second": 380.799,
+    "eval_steps_per_second": 1.488
+}

stress-negation_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 85.62948305713579,
+    "eval_combined_score": 83.67319706384387,
+    "eval_f1": 81.71691107055196,
+    "eval_loss": 0.35075807571411133,
+    "eval_runtime": 105.8746,
+    "eval_samples_per_second": 381.867,
+    "eval_steps_per_second": 1.492
+}

stress-spelling_error_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 81.93870736352619,
+    "eval_combined_score": 78.51285419353383,
+    "eval_f1": 75.08700102354146,
+    "eval_loss": 0.4257154166698456,
+    "eval_runtime": 106.3656,
+    "eval_samples_per_second": 380.095,
+    "eval_steps_per_second": 1.485
+}

stress-word_overlap_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 85.97081375216423,
+    "eval_combined_score": 83.86584934826682,
+    "eval_f1": 81.76088494436941,
+    "eval_loss": 0.33746978640556335,
+    "eval_runtime": 106.1412,
+    "eval_samples_per_second": 380.908,
+    "eval_steps_per_second": 1.489
+}

test_results.json

@@ -0,0 +1,10 @@
+{
+    "ave/id": 0.814885685064828,
+    "ave/ood": 0.6040905770635501,
+    "ave/transfer": 0.7922077922077924,
+    "gap/ood": 0.21079510800127788,
+    "gap/transfer": 0.022677892857035586,
+    "ood": 0.6040905770635501,
+    "qqp": 0.814885685064828,
+    "transfer": 0.7922077922077924
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "google/bert_uncased_L-8_H-512_A-8",
+  "never_split": null,
+  "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": 0.6687755357152263,
+    "train_runtime": 7270.4925,
+    "train_samples_per_second": 150.133,
+    "train_steps_per_second": 4.692
+}

trainer_state.json

@@ -0,0 +1,466 @@
+{
+  "best_metric": 81.48856850648279,
+  "best_model_checkpoint": "outputs/bert-medium/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": 1.1052,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9413713247149183e-05,
+      "loss": 0.9827,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9120569870723774e-05,
+      "loss": 0.9411,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.882742649429836e-05,
+      "loss": 0.9184,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8534283117872952e-05,
+      "loss": 0.8824,
+      "step": 2500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8241139741447543e-05,
+      "loss": 0.8506,
+      "step": 3000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7947996365022134e-05,
+      "loss": 0.8293,
+      "step": 3500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.7654852988596725e-05,
+      "loss": 0.8302,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.7361709612171312e-05,
+      "loss": 0.8115,
+      "step": 4500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7068566235745903e-05,
+      "loss": 0.7882,
+      "step": 5000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6775422859320497e-05,
+      "loss": 0.802,
+      "step": 5500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.6482279482895085e-05,
+      "loss": 0.7852,
+      "step": 6000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6189136106469676e-05,
+      "loss": 0.7845,
+      "step": 6500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5895992730044266e-05,
+      "loss": 0.7755,
+      "step": 7000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5602849353618857e-05,
+      "loss": 0.7744,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5309705977193448e-05,
+      "loss": 0.7629,
+      "step": 8000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.5016562600768037e-05,
+      "loss": 0.7497,
+      "step": 8500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4723419224342628e-05,
+      "loss": 0.7299,
+      "step": 9000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.4430275847917217e-05,
+      "loss": 0.7426,
+      "step": 9500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.4137132471491808e-05,
+      "loss": 0.7292,
+      "step": 10000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.3843989095066399e-05,
+      "loss": 0.7333,
+      "step": 10500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.3550845718640988e-05,
+      "loss": 0.7246,
+      "step": 11000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 83.31189710610933,
+      "eval_combined_score": 81.1331624399507,
+      "eval_f1": 78.95442777379208,
+      "eval_loss": 0.36778926849365234,
+      "eval_runtime": 106.4889,
+      "eval_samples_per_second": 379.664,
+      "eval_steps_per_second": 1.484,
+      "step": 11371
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.3257702342215579e-05,
+      "loss": 0.6926,
+      "step": 11500
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.2964558965790168e-05,
+      "loss": 0.656,
+      "step": 12000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.2671415589364759e-05,
+      "loss": 0.6554,
+      "step": 12500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.2378272212939351e-05,
+      "loss": 0.6457,
+      "step": 13000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.208512883651394e-05,
+      "loss": 0.6531,
+      "step": 13500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.1791985460088531e-05,
+      "loss": 0.6553,
+      "step": 14000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.149884208366312e-05,
+      "loss": 0.6447,
+      "step": 14500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.1205698707237711e-05,
+      "loss": 0.623,
+      "step": 15000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.0912555330812302e-05,
+      "loss": 0.64,
+      "step": 15500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0619411954386891e-05,
+      "loss": 0.6371,
+      "step": 16000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.0326268577961482e-05,
+      "loss": 0.6519,
+      "step": 16500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0033125201536071e-05,
+      "loss": 0.6368,
+      "step": 17000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.739981825110662e-06,
+      "loss": 0.6436,
+      "step": 17500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.446838448685253e-06,
+      "loss": 0.6382,
+      "step": 18000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.153695072259843e-06,
+      "loss": 0.625,
+      "step": 18500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.860551695834433e-06,
+      "loss": 0.638,
+      "step": 19000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.567408319409023e-06,
+      "loss": 0.6326,
+      "step": 19500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 8.274264942983614e-06,
+      "loss": 0.6194,
+      "step": 20000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.981121566558205e-06,
+      "loss": 0.624,
+      "step": 20500
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.687978190132794e-06,
+      "loss": 0.635,
+      "step": 21000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 7.394834813707384e-06,
+      "loss": 0.629,
+      "step": 21500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 7.101691437281976e-06,
+      "loss": 0.6191,
+      "step": 22000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.808548060856566e-06,
+      "loss": 0.6142,
+      "step": 22500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 85.40934949295078,
+      "eval_combined_score": 83.03703568914804,
+      "eval_f1": 80.6647218853453,
+      "eval_loss": 0.32606932520866394,
+      "eval_runtime": 105.2719,
+      "eval_samples_per_second": 384.053,
+      "eval_steps_per_second": 1.501,
+      "step": 22742
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 6.515404684431156e-06,
+      "loss": 0.591,
+      "step": 23000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 6.222261308005746e-06,
+      "loss": 0.5543,
+      "step": 23500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5.929117931580336e-06,
+      "loss": 0.5572,
+      "step": 24000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 5.6359745551549274e-06,
+      "loss": 0.5657,
+      "step": 24500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.3428311787295174e-06,
+      "loss": 0.5572,
+      "step": 25000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 5.049687802304107e-06,
+      "loss": 0.5606,
+      "step": 25500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 4.756544425878697e-06,
+      "loss": 0.5592,
+      "step": 26000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.463401049453288e-06,
+      "loss": 0.564,
+      "step": 26500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 4.170257673027878e-06,
+      "loss": 0.5672,
+      "step": 27000
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 3.877114296602469e-06,
+      "loss": 0.5639,
+      "step": 27500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 3.583970920177059e-06,
+      "loss": 0.5605,
+      "step": 28000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 3.290827543751649e-06,
+      "loss": 0.5448,
+      "step": 28500
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 2.9976841673262398e-06,
+      "loss": 0.5588,
+      "step": 29000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.7045407909008298e-06,
+      "loss": 0.5416,
+      "step": 29500
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.41139741447542e-06,
+      "loss": 0.5532,
+      "step": 30000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.1182540380500106e-06,
+      "loss": 0.5475,
+      "step": 30500
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.825110661624601e-06,
+      "loss": 0.5412,
+      "step": 31000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.531967285199191e-06,
+      "loss": 0.554,
+      "step": 31500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.2388239087737813e-06,
+      "loss": 0.5532,
+      "step": 32000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 9.456805323483717e-07,
+      "loss": 0.5533,
+      "step": 32500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 6.525371559229619e-07,
+      "loss": 0.5351,
+      "step": 33000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 3.5939377949755233e-07,
+      "loss": 0.5447,
+      "step": 33500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 6.62504030721426e-08,
+      "loss": 0.5349,
+      "step": 34000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 86.12169181301013,
+      "eval_combined_score": 83.80513015974645,
+      "eval_f1": 81.48856850648279,
+      "eval_loss": 0.3177751898765564,
+      "eval_runtime": 105.2798,
+      "eval_samples_per_second": 384.024,
+      "eval_steps_per_second": 1.501,
+      "step": 34113
+    },
+    {
+      "epoch": 3.0,
+      "step": 34113,
+      "total_flos": 0.0,
+      "train_loss": 0.6687755357152263,
+      "train_runtime": 7270.4925,
+      "train_samples_per_second": 150.133,
+      "train_steps_per_second": 4.692
+    }
+  ],
+  "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 sha256:571423933137e161e1bf46056d30e0a33302368e398c441b6375c02b2784c456
+size 4091

transfer_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_combined_score": 0.7922077922077924,
+    "eval_f1": 0.7922077922077924,
+    "eval_loss": 0.8416510224342346,
+    "eval_runtime": 2.1923,
+    "eval_samples_per_second": 186.11,
+    "eval_steps_per_second": 0.912
+}