Training in progress, epoch 3

checkpoint-1869/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "bert-large-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "rte",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "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-1869/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd092b3dbba7392b7d3dec48c211de62c9250ed29845b707ae5badee1f348db
+size 2668879261

checkpoint-1869/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd98ab7c062cf6d09ae971f775ce1954052e4fec65fd550594865dfe958a038
+size 1334486957

checkpoint-1869/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:005059942f55550ca2fdcc705756874455cd1f0e23815e0ec180051275d0278b
+size 14503

checkpoint-1869/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2780fd14be91c71e9874620e45e474625b70b5f31dd07192fac262b87276483d
+size 623

checkpoint-1869/special_tokens_map.json

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

checkpoint-1869/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-large-cased", "tokenizer_class": "BertTokenizer"}

checkpoint-1869/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1869,
+  "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": 0.6969,
+      "step": 623
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5342960288808665,
+      "eval_loss": 0.7039318680763245,
+      "eval_runtime": 9.0213,
+      "eval_samples_per_second": 30.705,
+      "eval_steps_per_second": 3.88,
+      "step": 623
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5903,
+      "step": 1246
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7184115523465704,
+      "eval_loss": 0.6461479663848877,
+      "eval_runtime": 8.9942,
+      "eval_samples_per_second": 30.798,
+      "eval_steps_per_second": 3.891,
+      "step": 1246
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.4557,
+      "step": 1869
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 1.5187355279922485,
+      "eval_runtime": 9.0028,
+      "eval_samples_per_second": 30.768,
+      "eval_steps_per_second": 3.888,
+      "step": 1869
+    }
+  ],
+  "max_steps": 1869,
+  "num_train_epochs": 3,
+  "total_flos": 6961527284060160.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1869/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7d10d8668d1f1967ef4c4281a48895971354bd8101c64a0769eb783535687a
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5f082d4c30792a01ac8c08f5cd852ec7b6e0571778d04dcd17e6d63e00020f
+oid sha256:7cd98ab7c062cf6d09ae971f775ce1954052e4fec65fd550594865dfe958a038
 size 1334486957

runs/Oct09_13-52-41_patrick-general-gpu/events.out.tfevents.1633787594.patrick-general-gpu.50676.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf50ec445c0fbfaefb98643bf59132248df3767a7d95661e56b61227757d618
-size 4397
+oid sha256:b3c8993d0d6043c0a05392b7383e0c8af4d4d2ce5d2d3b0aaf32d8f1b8200016
+size 4877