Training in progress, epoch 3

checkpoint-19641/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": "qnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "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-19641/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d1f397454c346dcab80c5f16d50d8ec4cf6cde01f120d98e51104e3bdafa11
+size 866610973

checkpoint-19641/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606e4831c810be4254f43c220e7a50151c901ccb64cabd7689b06a9d1806dce4
+size 433331373

checkpoint-19641/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fafad9bc2ed9989b84c048e821560acf152fa9ad7a106dd0aeffdebe6647876
+size 14503

checkpoint-19641/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf713a80a9c8fd994ed1ace14615354b3454f45dc7a0a20bb4f953559263f7a0
+size 623

checkpoint-19641/special_tokens_map.json

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

checkpoint-19641/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-19641/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 19641,
+  "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": 0.337,
+      "step": 6547
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9013362621270364,
+      "eval_loss": 0.24480287730693817,
+      "eval_runtime": 55.721,
+      "eval_samples_per_second": 98.042,
+      "eval_steps_per_second": 12.258,
+      "step": 6547
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1971,
+      "step": 13094
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.914332784184514,
+      "eval_loss": 0.28385764360427856,
+      "eval_runtime": 55.6845,
+      "eval_samples_per_second": 98.106,
+      "eval_steps_per_second": 12.266,
+      "step": 13094
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1175,
+      "step": 19641
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9099395936298736,
+      "eval_loss": 0.39857929944992065,
+      "eval_runtime": 55.8016,
+      "eval_samples_per_second": 97.9,
+      "eval_steps_per_second": 12.24,
+      "step": 19641
+    }
+  ],
+  "max_steps": 19641,
+  "num_train_epochs": 3,
+  "total_flos": 8.267712381471744e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-19641/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc54d0f744ff426ea106709cabc71730fd2811c6f430ce8415d7ad0f58f4f5a1
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e01a90907960e98e1cc2acb681ebc6c26f909f22c20ee008041bd0030962721
+oid sha256:606e4831c810be4254f43c220e7a50151c901ccb64cabd7689b06a9d1806dce4
 size 433331373

runs/Sep17_14-24-47_patrick-general-gpu/events.out.tfevents.1631888732.patrick-general-gpu.282818.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4ea807b12eeb9530ee9070cdf2d0a9d5c68681902b5c4224c44df1c5270722
-size 4206
+oid sha256:15eb957929d8687b25f1324428b52c655e937ef578c121fb8577a82b83b344c9
+size 4695