Upload model files

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": "gelu",
+  "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": "4.30.2",
+  "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:f8373ce2b4e59502bb2035593c4b8f7107141b4f8e9cc043321955bd4d96916d
+size 876232773

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd8f5ca83503d8c886882ac4ef9aa7e8251d43f97b03c312203cf750e9cbaa1
+size 438130617

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14591e6d6a2795be4ec49696a553722b60d96775371af75c82f5f7666a9909a0
+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": 0.00037940836045891047,
+  "best_model_checkpoint": "data/further_pretraining/bert-base-uncased/checkpoint-2155",
+  "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": 0.0545,
+      "step": 500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9071925754060325e-05,
+      "loss": 0.0012,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.860788863109049e-05,
+      "loss": 0.0017,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.8143851508120652e-05,
+      "loss": 0.0003,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.00037940836045891047,
+      "eval_runtime": 164.4067,
+      "eval_samples_per_second": 419.32,
+      "eval_steps_per_second": 13.108,
+      "step": 2155
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.7679814385150812e-05,
+      "loss": 0.0006,
+      "step": 2500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.7215777262180976e-05,
+      "loss": 0.0005,
+      "step": 3000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.675174013921114e-05,
+      "loss": 0.001,
+      "step": 3500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.62877030162413e-05,
+      "loss": 0.0007,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.00047821112093515694,
+      "eval_runtime": 161.3062,
+      "eval_samples_per_second": 427.38,
+      "eval_steps_per_second": 13.36,
+      "step": 4310
+    }
+  ],
+  "max_steps": 21550,
+  "num_train_epochs": 10,
+  "total_flos": 9072538294809600.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e26b2525596738a1da8706431b0c14f92faeb6662ddf47c040ca7f1399cf12b
+size 3963