Training in progress, epoch 3

checkpoint-468/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": "rte",
+  "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-468/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f23b9471a7649be5b417ae0a0866ff2aa48c58131181dac987063919a13429f
+size 866610973

checkpoint-468/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0783d5be4767753d6193915854e9ca5b787866bfe309f341f9eaa895ebe526b1
+size 433331373

checkpoint-468/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81457692369224cc617bd3ba4e80c406804fbdaff1d2ac5a72044ff4e563b30f
+size 14503

checkpoint-468/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a5bf2f5d5fb5f4bf00355a36dde18b1c59d2735f963718d2986d0692f55eae
+size 623

checkpoint-468/special_tokens_map.json

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

checkpoint-468/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-468/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 468,
+  "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": 0.6915,
+      "step": 156
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6491293907165527,
+      "eval_runtime": 2.8403,
+      "eval_samples_per_second": 97.525,
+      "eval_steps_per_second": 12.323,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.55,
+      "step": 312
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6737464666366577,
+      "eval_runtime": 2.8421,
+      "eval_samples_per_second": 97.462,
+      "eval_steps_per_second": 12.315,
+      "step": 312
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.3955,
+      "step": 468
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6714801444043321,
+      "eval_loss": 0.726006031036377,
+      "eval_runtime": 2.8441,
+      "eval_samples_per_second": 97.396,
+      "eval_steps_per_second": 12.306,
+      "step": 468
+    }
+  ],
+  "max_steps": 468,
+  "num_train_epochs": 3,
+  "total_flos": 1965439583539200.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-468/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81752ba17c8a4a9155cd9cfe51390db7f1153b33828008717736eb5a2d531b98
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf49949ab1783a4d7f8ec1586ded70d0e4245f9d69cd1e71f11c13851312cc5b
+oid sha256:0783d5be4767753d6193915854e9ca5b787866bfe309f341f9eaa895ebe526b1
 size 433331373

runs/Sep19_05-25-52_patrick-general-gpu/events.out.tfevents.1632029169.patrick-general-gpu.453668.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:661e0e15336f304ba80c6edf5956838ae85dc0baf677e3ec82000da48ccc0da4
-size 4202
+oid sha256:1d0f4f942f830ec08e3b30943e5ff4bae8d2b369a37ed6b73bdaf2598e6bd2dd
+size 4682