Upload 7 files

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555987e82aa01fd43482c90ae51877d519be2a0214c0766bb626871493ed8ad1
+size 438020213

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a7666114aead033db3c4c59484cb5f219668929dcac5f9f00d65720bc36198
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b2bd6a948067c32ab04aead7e0211efbc27c1d7157625eb99bd34b378230b0
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d30b14c9d1bb58e338f3b52564bc77c8c6f639e2983e13372177453da337a2
+size 627

trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9023913370431644,
+  "global_step": 18000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9499674136461627e-05,
+      "loss": 0.1142,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.899834561588209e-05,
+      "loss": 0.0585,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8497017095302553e-05,
+      "loss": 0.0572,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.7995688574723017e-05,
+      "loss": 0.053,
+      "step": 2000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.749436005414348e-05,
+      "loss": 0.0523,
+      "step": 2500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.6993031533563946e-05,
+      "loss": 0.0451,
+      "step": 3000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.6492705670025568e-05,
+      "loss": 0.0462,
+      "step": 3500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.5991377149446032e-05,
+      "loss": 0.0512,
+      "step": 4000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.5490048628866497e-05,
+      "loss": 0.0473,
+      "step": 4500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.4988720108286963e-05,
+      "loss": 0.0404,
+      "step": 5000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.4487391587707427e-05,
+      "loss": 0.0453,
+      "step": 5500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.3986063067127892e-05,
+      "loss": 0.0476,
+      "step": 6000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.3484734546548354e-05,
+      "loss": 0.0435,
+      "step": 6500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.2983406025968819e-05,
+      "loss": 0.0434,
+      "step": 7000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.248308016243044e-05,
+      "loss": 0.0419,
+      "step": 7500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.1982754298892064e-05,
+      "loss": 0.0431,
+      "step": 8000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.1481425778312529e-05,
+      "loss": 0.0406,
+      "step": 8500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.0981099914774151e-05,
+      "loss": 0.0414,
+      "step": 9000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0479771394194615e-05,
+      "loss": 0.0412,
+      "step": 9500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.978442873615081e-06,
+      "loss": 0.0436,
+      "step": 10000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.477114353035544e-06,
+      "loss": 0.0398,
+      "step": 10500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.975785832456009e-06,
+      "loss": 0.0375,
+      "step": 11000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.474457311876473e-06,
+      "loss": 0.0393,
+      "step": 11500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.974131448338097e-06,
+      "loss": 0.0391,
+      "step": 12000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.472802927758561e-06,
+      "loss": 0.0383,
+      "step": 12500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.971474407179026e-06,
+      "loss": 0.0391,
+      "step": 13000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.470145886599489e-06,
+      "loss": 0.04,
+      "step": 13500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.968817366019954e-06,
+      "loss": 0.0412,
+      "step": 14000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.467488845440417e-06,
+      "loss": 0.0379,
+      "step": 14500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.9661603248608816e-06,
+      "loss": 0.0381,
+      "step": 15000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.464831804281346e-06,
+      "loss": 0.0408,
+      "step": 15500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.96350328370181e-06,
+      "loss": 0.0329,
+      "step": 16000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.462174763122274e-06,
+      "loss": 0.0369,
+      "step": 16500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.960846242542739e-06,
+      "loss": 0.0369,
+      "step": 17000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.4605203790043617e-06,
+      "loss": 0.0366,
+      "step": 17500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.959191858424826e-06,
+      "loss": 0.0365,
+      "step": 18000
+    }
+  ],
+  "max_steps": 19947,
+  "num_train_epochs": 1,
+  "total_flos": 3.7889352695808e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4907f1e57294ca013af340be8a8019feee701e7aa152ed188876248b129904
+size 3579