First Commit

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "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": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c44af8f7f690db95d8291d3cd5cd635667bc00a6ffab318285c90c87ca7444be
+size 866844869

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:797b3005a940bef68b8bf958668d447bac9d57a7bb74b8ce176fadc889170d06
+size 433436665

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b1d479e61fc6d0e3522d64dc7f3f0305d72c90070ea2ca5f98cd45be4dd815
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228f1d3daa77d685940d358a41b7552dcd943c5d58a62ccad020079b3cc2bf3c
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5729550453572d5f0bb228ca9a47ae211eb447b2153da756caaeef7c5950d9
+size 627

trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998440667394355,
+  "global_step": 3206,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 8.440424204616345e-05,
+      "loss": 2.503,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 6.880848409232689e-05,
+      "loss": 2.5143,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.321272613849033e-05,
+      "loss": 2.4359,
+      "step": 1500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.761696818465378e-05,
+      "loss": 2.379,
+      "step": 2000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.202121023081722e-05,
+      "loss": 2.3396,
+      "step": 2500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6.456643792888335e-06,
+      "loss": 2.3217,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.1647815704345703,
+      "eval_runtime": 58.8555,
+      "eval_samples_per_second": 484.27,
+      "eval_steps_per_second": 7.578,
+      "step": 3206
+    }
+  ],
+  "max_steps": 3206,
+  "num_train_epochs": 1,
+  "total_flos": 6.750556804153344e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af63f9e17d2dbe3dbf260a42c084c8fdcb1f12080885c8b430f49dd4a812e1a
+size 3579