Upload 7 files

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "ElectraForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62bf43cdf7db4ac1643625bfefe2ee212a2ec808d5458c1e7aa81e5ca19a3bbc
+size 128593361

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75c937c758bf6e1c3b4e44e459e8dfbe545fe6aec529748adf10465c17e20bd
+size 64310119

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b13b0d85e27839584bc7b35d43479c3fc3d5824b2826c55d18a163f943f6c31
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0bfa72ab3c84e760eb47ef61b9da92ab03517879feb5fbc69affb7cbd0d8096
+size 623

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 1840640,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.5e-05,
+      "loss": 6.4348,
+      "step": 184064
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4e-05,
+      "loss": 5.3925,
+      "step": 368128
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.5e-05,
+      "loss": 5.0967,
+      "step": 552192
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 4.9327,
+      "step": 736256
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 4.8269,
+      "step": 920320
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2e-05,
+      "loss": 4.7486,
+      "step": 1104384
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.5e-05,
+      "loss": 4.6854,
+      "step": 1288448
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1e-05,
+      "loss": 4.6333,
+      "step": 1472512
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 5e-06,
+      "loss": 4.5918,
+      "step": 1656576
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 4.5572,
+      "step": 1840640
+    }
+  ],
+  "max_steps": 1840640,
+  "num_train_epochs": 10,
+  "total_flos": 3.184855687291592e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b223e6fdf9c31644fd42d1521811a97c7c7062ee89a9ab685f0253e2b662ca
+size 3183