Upload model files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "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": "4.30.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b2b519733d318131e855475ff8def629cf59fff7291c78febd4659db6366c6
+size 2681627077

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4553ec99cf8e643db5dd5413283cd9d1f10640b2e9bc7562970f59d22390abcd
+size 1340837305

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e524dd57c14064cd59d302c0889521610bcd5c91a5fa62451034d5de493417
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533e3c733f8f9c5f7f9118844ef1c0edb15c97d82f8be8ea544e6252da945273
+size 627

trainer_state.json

@@ -0,0 +1,80 @@
+{
+  "best_metric": 0.0008013004553504288,
+  "best_model_checkpoint": "data/further_pretraining/bert-large-uncased/checkpoint-4310",
+  "epoch": 2.0,
+  "global_step": 4310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9535962877030165e-05,
+      "loss": 0.0601,
+      "step": 500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9071925754060325e-05,
+      "loss": 0.0044,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.860788863109049e-05,
+      "loss": 0.0018,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.8143851508120652e-05,
+      "loss": 0.0012,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.004205523990094662,
+      "eval_runtime": 396.7144,
+      "eval_samples_per_second": 173.775,
+      "eval_steps_per_second": 5.432,
+      "step": 2155
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.7679814385150812e-05,
+      "loss": 0.0028,
+      "step": 2500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.7215777262180976e-05,
+      "loss": 0.0008,
+      "step": 3000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.675174013921114e-05,
+      "loss": 0.0018,
+      "step": 3500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.62877030162413e-05,
+      "loss": 0.0028,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.0008013004553504288,
+      "eval_runtime": 393.1202,
+      "eval_samples_per_second": 175.364,
+      "eval_steps_per_second": 5.482,
+      "step": 4310
+    }
+  ],
+  "max_steps": 21550,
+  "num_train_epochs": 10,
+  "total_flos": 3.2126439900312576e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227af3a23be332c7ad1686921a338a683108e4886125d903da08433774939ee7
+size 3963