First model version

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "relu",
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8fc3e1d5481b2447065ad15cf114ceac93b68a6b2ef5267d3c558683c30773
+size 876232773

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5171b88e15c2dd5ed71dd11c249fe5aa18aa4ee3491e9cedb3d2e0d63ee913db
+size 438130617

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef6f4e886b583cc1ceb21ae73475fea540f989e14824461c1cee44414187928c
+size 14511

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05deb4649a99bbb9b75ba3c910e2505e98e5f567e9b75a333252117800ba40b
+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 +1,85 @@
+{
+  "best_metric": 1.7642425298690796,
+  "best_model_checkpoint": "/net/tscratch/people/plgpiorczynskim/saved_models/relu-bert-base-uncased/checkpoint-5000",
+  "epoch": 0.09378047865556306,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.975e-05,
+      "loss": 2.2388,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 1.9998,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9250000000000004e-05,
+      "loss": 1.9622,
+      "step": 1500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.9e-05,
+      "loss": 1.9386,
+      "step": 2000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.875e-05,
+      "loss": 1.9249,
+      "step": 2500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.85e-05,
+      "loss": 1.914,
+      "step": 3000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.825e-05,
+      "loss": 1.9023,
+      "step": 3500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.8e-05,
+      "loss": 1.8955,
+      "step": 4000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.775e-05,
+      "loss": 1.8862,
+      "step": 4500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.75e-05,
+      "loss": 1.885,
+      "step": 5000
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.6519307229448076,
+      "eval_loss": 1.7642425298690796,
+      "eval_runtime": 2235.5625,
+      "eval_samples_per_second": 961.542,
+      "eval_steps_per_second": 1.252,
+      "step": 5000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 2,
+  "total_flos": 2.52676620288e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be57af02e918ce52c206c1aedb639309a1dd35bcd4f368d91c3dae50f9e408d9
+size 4027