Upload 11 files

config.json

@@ -19,7 +19,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.26.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:084f7060a2d4e459e8f34a8c9d28522799810579ffff7777c4d91e6e62f8f071
+oid sha256:9822d451c23c9d1a4219b5d731af3967b5694b24922818c968112db44e13a654
 size 331073989

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b1f5e604bb2113932238477c13a8f1860a1c905693facf5d783e96f99a79aef
+oid sha256:2767f946ca70f29f55cd0c13d8e46517e20c1b62ea5c70450eed00ea7f1d8d74
 size 165547637

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8332db9dd41ad5c0859a96a265c824d1244e1ac28822bb3c87d560fccdc26cda
-size 14575
+oid sha256:110f64100f09e85f8a8659dd6c765d0c05410e455733b95db82da65c9a985306
+size 15597

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a776579ae12db457f9c3df76d9976cab904241a9c5dffa4cafa356e6aca712
+oid sha256:466f0b6297493eed05f2d1ce63809b3d054e71f229177cc77584e4462fd9dace
 size 627

tokenizer_config.json

@@ -1,11 +1,12 @@
 {
-  "clean_up_tokenization_spaces": true,
   "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",

trainer_state.json

@@ -1,283 +1,115 @@
 {
-  "best_metric": 0.9478841870824053,
-  "best_model_checkpoint": "finetune-bert-Med-SST2/checkpoint-18945",
+  "best_metric": 0.9498144023756496,
+  "best_model_checkpoint": "finetune-bert-Med-SST2\\checkpoint-3792",
   "epoch": 5.0,
-  "global_step": 18945,
+  "global_step": 4740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.13,
-      "learning_rate": 4.86803906043811e-05,
-      "loss": 0.416,
-      "step": 500
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 4.7360781208762204e-05,
-      "loss": 0.3286,
-      "step": 1000
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 4.604117181314331e-05,
-      "loss": 0.29,
-      "step": 1500
-    },
     {
       "epoch": 0.53,
-      "learning_rate": 4.472156241752442e-05,
-      "loss": 0.2661,
-      "step": 2000
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 4.340195302190552e-05,
-      "loss": 0.2539,
-      "step": 2500
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 4.208234362628662e-05,
-      "loss": 0.2475,
-      "step": 3000
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 4.076273423066773e-05,
-      "loss": 0.2378,
-      "step": 3500
+      "learning_rate": 4.4725738396624474e-05,
+      "loss": 0.3201,
+      "step": 500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9287305122494433,
-      "eval_loss": 0.19024422764778137,
-      "eval_runtime": 10.4888,
-      "eval_samples_per_second": 642.112,
-      "eval_steps_per_second": 40.138,
-      "step": 3789
-    },
-    {
-      "epoch": 1.06,
-      "learning_rate": 3.944312483504883e-05,
-      "loss": 0.2065,
-      "step": 4000
-    },
-    {
-      "epoch": 1.19,
-      "learning_rate": 3.812351543942993e-05,
-      "loss": 0.1747,
-      "step": 4500
-    },
-    {
-      "epoch": 1.32,
-      "learning_rate": 3.680390604381103e-05,
-      "loss": 0.1775,
-      "step": 5000
+      "eval_accuracy": 0.9319970304380104,
+      "eval_loss": 0.18009190261363983,
+      "eval_runtime": 8.6367,
+      "eval_samples_per_second": 779.81,
+      "eval_steps_per_second": 12.273,
+      "step": 948
     },
     {
-      "epoch": 1.45,
-      "learning_rate": 3.5484296648192136e-05,
-      "loss": 0.1797,
-      "step": 5500
+      "epoch": 1.05,
+      "learning_rate": 3.945147679324895e-05,
+      "loss": 0.2192,
+      "step": 1000
     },
     {
       "epoch": 1.58,
-      "learning_rate": 3.4164687252573244e-05,
-      "loss": 0.1649,
-      "step": 6000
-    },
-    {
-      "epoch": 1.72,
-      "learning_rate": 3.2845077856954345e-05,
-      "loss": 0.1741,
-      "step": 6500
-    },
-    {
-      "epoch": 1.85,
-      "learning_rate": 3.1525468461335445e-05,
-      "loss": 0.1713,
-      "step": 7000
-    },
-    {
-      "epoch": 1.98,
-      "learning_rate": 3.0205859065716553e-05,
-      "loss": 0.1725,
-      "step": 7500
+      "learning_rate": 3.4177215189873416e-05,
+      "loss": 0.1468,
+      "step": 1500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9449146250927988,
-      "eval_loss": 0.1960470974445343,
-      "eval_runtime": 10.3689,
-      "eval_samples_per_second": 649.541,
-      "eval_steps_per_second": 40.602,
-      "step": 7578
+      "eval_accuracy": 0.9452115812917594,
+      "eval_loss": 0.16460973024368286,
+      "eval_runtime": 9.1827,
+      "eval_samples_per_second": 733.445,
+      "eval_steps_per_second": 11.543,
+      "step": 1896
     },
     {
       "epoch": 2.11,
-      "learning_rate": 2.8886249670097653e-05,
-      "loss": 0.1167,
-      "step": 8000
-    },
-    {
-      "epoch": 2.24,
-      "learning_rate": 2.7566640274478754e-05,
-      "loss": 0.1264,
-      "step": 8500
-    },
-    {
-      "epoch": 2.38,
-      "learning_rate": 2.6247030878859858e-05,
-      "loss": 0.1206,
-      "step": 9000
-    },
-    {
-      "epoch": 2.51,
-      "learning_rate": 2.4927421483240962e-05,
-      "loss": 0.1157,
-      "step": 9500
+      "learning_rate": 2.8902953586497894e-05,
+      "loss": 0.1255,
+      "step": 2000
     },
     {
       "epoch": 2.64,
-      "learning_rate": 2.3607812087622063e-05,
-      "loss": 0.1227,
-      "step": 10000
-    },
-    {
-      "epoch": 2.77,
-      "learning_rate": 2.228820269200317e-05,
-      "loss": 0.1207,
-      "step": 10500
-    },
-    {
-      "epoch": 2.9,
-      "learning_rate": 2.096859329638427e-05,
-      "loss": 0.1201,
-      "step": 11000
+      "learning_rate": 2.3628691983122365e-05,
+      "loss": 0.094,
+      "step": 2500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.9469933184855234,
-      "eval_loss": 0.23182542622089386,
-      "eval_runtime": 10.3744,
-      "eval_samples_per_second": 649.192,
-      "eval_steps_per_second": 40.581,
-      "step": 11367
-    },
-    {
-      "epoch": 3.04,
-      "learning_rate": 1.9648983900765375e-05,
-      "loss": 0.1192,
-      "step": 11500
-    },
-    {
-      "epoch": 3.17,
-      "learning_rate": 1.8329374505146475e-05,
-      "loss": 0.0794,
-      "step": 12000
-    },
-    {
-      "epoch": 3.3,
-      "learning_rate": 1.7009765109527583e-05,
-      "loss": 0.0819,
-      "step": 12500
-    },
-    {
-      "epoch": 3.43,
-      "learning_rate": 1.5690155713908683e-05,
-      "loss": 0.0957,
-      "step": 13000
+      "eval_accuracy": 0.9483296213808463,
+      "eval_loss": 0.17333245277404785,
+      "eval_runtime": 9.4505,
+      "eval_samples_per_second": 712.663,
+      "eval_steps_per_second": 11.216,
+      "step": 2844
     },
     {
-      "epoch": 3.56,
-      "learning_rate": 1.4370546318289787e-05,
-      "loss": 0.0822,
-      "step": 13500
+      "epoch": 3.16,
+      "learning_rate": 1.8354430379746836e-05,
+      "loss": 0.0816,
+      "step": 3000
     },
     {
       "epoch": 3.69,
-      "learning_rate": 1.305093692267089e-05,
-      "loss": 0.0909,
-      "step": 14000
-    },
-    {
-      "epoch": 3.83,
-      "learning_rate": 1.1731327527051992e-05,
-      "loss": 0.0895,
-      "step": 14500
-    },
-    {
-      "epoch": 3.96,
-      "learning_rate": 1.0411718131433096e-05,
-      "loss": 0.0811,
-      "step": 15000
+      "learning_rate": 1.308016877637131e-05,
+      "loss": 0.0645,
+      "step": 3500
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.947735708982925,
-      "eval_loss": 0.2433549165725708,
-      "eval_runtime": 10.3802,
-      "eval_samples_per_second": 648.831,
-      "eval_steps_per_second": 40.558,
-      "step": 15156
-    },
-    {
-      "epoch": 4.09,
-      "learning_rate": 9.092108735814198e-06,
-      "loss": 0.0591,
-      "step": 15500
+      "eval_accuracy": 0.9498144023756496,
+      "eval_loss": 0.19728632271289825,
+      "eval_runtime": 9.0479,
+      "eval_samples_per_second": 744.374,
+      "eval_steps_per_second": 11.715,
+      "step": 3792
     },
     {
       "epoch": 4.22,
-      "learning_rate": 7.772499340195302e-06,
-      "loss": 0.0589,
-      "step": 16000
-    },
-    {
-      "epoch": 4.35,
-      "learning_rate": 6.4528899445764055e-06,
-      "loss": 0.0553,
-      "step": 16500
-    },
-    {
-      "epoch": 4.49,
-      "learning_rate": 5.133280548957509e-06,
-      "loss": 0.0576,
-      "step": 17000
-    },
-    {
-      "epoch": 4.62,
-      "learning_rate": 3.813671153338612e-06,
-      "loss": 0.061,
-      "step": 17500
+      "learning_rate": 7.805907172995782e-06,
+      "loss": 0.0538,
+      "step": 4000
     },
     {
       "epoch": 4.75,
-      "learning_rate": 2.494061757719715e-06,
-      "loss": 0.0533,
-      "step": 18000
-    },
-    {
-      "epoch": 4.88,
-      "learning_rate": 1.1744523621008182e-06,
-      "loss": 0.0648,
-      "step": 18500
+      "learning_rate": 2.531645569620253e-06,
+      "loss": 0.0424,
+      "step": 4500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9478841870824053,
-      "eval_loss": 0.27820324897766113,
-      "eval_runtime": 10.4353,
-      "eval_samples_per_second": 645.403,
-      "eval_steps_per_second": 40.344,
-      "step": 18945
+      "eval_accuracy": 0.9484780994803267,
+      "eval_loss": 0.2303222268819809,
+      "eval_runtime": 9.3041,
+      "eval_samples_per_second": 723.873,
+      "eval_steps_per_second": 11.393,
+      "step": 4740
     }
   ],
-  "max_steps": 18945,
+  "max_steps": 4740,
   "num_train_epochs": 5,
-  "total_flos": 1630739369585616.0,
+  "total_flos": 2062420909600608.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28093861817ce584c9417a32a2951733caa888fd46d56babe7bda6b3efd018f
-size 3899
+oid sha256:541291882fa1c55858b0ae60dc84c3ac0b0b4904fc379c3ea1509409619514bf
+size 3515