Add checkpoint

config.json

@@ -0,0 +1,27 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1849e6b0ceae742d3bdeaceeebda3b1929e1911cc6fe2cdda518a4348f4917
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee49f24f5fd140b6aca1adc82bec788a2daad6286d689b0bd46062f548a7ffcf
+size 627

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.88,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7333333333333336e-05,
+      "loss": 0.4226,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 0.3551,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3366,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.933333333333333e-05,
+      "loss": 0.3058,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.2993,
+      "step": 2500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.3112,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.921,
+      "eval_loss": 0.23617929220199585,
+      "eval_runtime": 800.1431,
+      "eval_samples_per_second": 31.244,
+      "eval_steps_per_second": 3.906,
+      "step": 3125
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.1333333333333334e-05,
+      "loss": 0.2277,
+      "step": 3500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8666666666666668e-05,
+      "loss": 0.2069,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.1996,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.1761,
+      "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.0666666666666666e-05,
+      "loss": 0.1696,
+      "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.8e-05,
+      "loss": 0.1994,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.93344,
+      "eval_loss": 0.30366918444633484,
+      "eval_runtime": 801.421,
+      "eval_samples_per_second": 31.195,
+      "eval_steps_per_second": 3.899,
+      "step": 6250
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 0.136,
+      "step": 6500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2666666666666668e-05,
+      "loss": 0.0866,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1e-05,
+      "loss": 0.0818,
+      "step": 7500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.333333333333334e-06,
+      "loss": 0.0716,
+      "step": 8000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.0733,
+      "step": 8500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.058,
+      "step": 9000
+    }
+  ],
+  "max_steps": 9375,
+  "num_train_epochs": 3,
+  "total_flos": 1.785774199386624e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d290b6e6465ba565f6fa7a7fa7527ca19422dee29308edcb5447d921407c5f6e
+size 3899