Training in progress, epoch 3

checkpoint-68223/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "qqp",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_duplicate",
+    "1": "duplicate"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "duplicate": 1,
+    "not_duplicate": 0
+  },
+  "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": "4.11.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-68223/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb036df7eda69bdb890adc66ec24ee624b90a617b8a6c8916abd01ecadf4394b
+size 866611421

checkpoint-68223/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1779d016b97b471392a15815bd88d558de35e94c0ddd7b1670a78e5c55736951
+size 433331373

checkpoint-68223/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abca19fd9521543250e374ad2a41812d034253b37f7dfdddb88ca6345948756f
+size 14503

checkpoint-68223/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d21242d57e668191689cff2fcffc7dbd9db3db670ded8c6d398d3d20fe99dcd
+size 623

checkpoint-68223/special_tokens_map.json

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

checkpoint-68223/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}

checkpoint-68223/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 68223,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.308,
+      "step": 22741
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8924560969577047,
+      "eval_combined_score": 0.8740405069726762,
+      "eval_f1": 0.8556249169876479,
+      "eval_loss": 0.2548316419124603,
+      "eval_runtime": 413.8779,
+      "eval_samples_per_second": 97.686,
+      "eval_steps_per_second": 12.211,
+      "step": 22741
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.201,
+      "step": 45482
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9032401681919366,
+      "eval_combined_score": 0.886515570715593,
+      "eval_f1": 0.8697909732392491,
+      "eval_loss": 0.2880714237689972,
+      "eval_runtime": 412.3711,
+      "eval_samples_per_second": 98.043,
+      "eval_steps_per_second": 12.256,
+      "step": 45482
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1416,
+      "step": 68223
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9083848627256987,
+      "eval_combined_score": 0.8925741188794849,
+      "eval_f1": 0.8767633750332712,
+      "eval_loss": 0.37517139315605164,
+      "eval_runtime": 412.699,
+      "eval_samples_per_second": 97.965,
+      "eval_steps_per_second": 12.246,
+      "step": 68223
+    }
+  ],
+  "max_steps": 68223,
+  "num_train_epochs": 3,
+  "total_flos": 2.8719571514554368e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-68223/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6215fd2fbd87e3a32e37bbf8b010344513fcafbfbf1dfe761fed7bac26bf7003
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc28f1ded35274849b36e1181fc6bd9db3570bca90a299fb21c25f5804ad7d3e
+oid sha256:1779d016b97b471392a15815bd88d558de35e94c0ddd7b1670a78e5c55736951
 size 433331373

runs/Sep18_08-14-37_patrick-general-gpu/events.out.tfevents.1631953045.patrick-general-gpu.335601.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621036b7f16614ad500be1169de0c1b43673718ebf1f92b1d90381594963d45d
-size 4428
+oid sha256:9f853e91b2e927d8ca1deb31b45d5ba7f3948455898369ead463f99f3e656ab7
+size 5023