Initial upload

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb290d3df9bd1d92466eee96236d9b172db9e85631a098cc7e2b9cc9bf170fb7
+size 997696473

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddca50e3e641be99f9a779d2b3c181f7d042f6b5842829be5424cc021593152
+size 498861675

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f1741aae87bd0f0398cde11a542792529ea9429e3b78f0705e8894bc6cb017
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462aabcd620cbd24d4941a7cc07d2ad6c351934622b2352207eccb5b5866b980
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.943181818181818,
+  "global_step": 7000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.6448863636363636e-05,
+      "loss": 1.4544,
+      "step": 500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.289772727272727e-05,
+      "loss": 1.0914,
+      "step": 1000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.934659090909091e-05,
+      "loss": 0.9652,
+      "step": 1500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 3.579545454545455e-05,
+      "loss": 0.8756,
+      "step": 2000
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 3.2244318181818185e-05,
+      "loss": 0.7816,
+      "step": 2500
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 2.869318181818182e-05,
+      "loss": 0.7508,
+      "step": 3000
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 2.5142045454545453e-05,
+      "loss": 0.6598,
+      "step": 3500
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 2.1590909090909093e-05,
+      "loss": 0.6049,
+      "step": 4000
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.8039772727272727e-05,
+      "loss": 0.5639,
+      "step": 4500
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 1.4488636363636366e-05,
+      "loss": 0.5258,
+      "step": 5000
+    },
+    {
+      "epoch": 7.81,
+      "learning_rate": 1.09375e-05,
+      "loss": 0.4905,
+      "step": 5500
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 7.386363636363637e-06,
+      "loss": 0.4758,
+      "step": 6000
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 3.835227272727273e-06,
+      "loss": 0.4578,
+      "step": 6500
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 2.840909090909091e-07,
+      "loss": 0.4302,
+      "step": 7000
+    }
+  ],
+  "max_steps": 7040,
+  "num_train_epochs": 10,
+  "total_flos": 2593764359423028.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d5a1e9b1ed051c8e6271904cc371dd840a071c4d1676612744bb998eafbe29
+size 2607