Upload 9 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

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, "name_or_path": "roberta-large"}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 2.0
+train_runtime = 3913.5949
+train_samples_per_second = 0.568

trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 2222,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.000154995499549955,
+      "loss": 4.8347,
+      "step": 500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00010999099909990999,
+      "loss": 2.2463,
+      "step": 1000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 6.498649864986499e-05,
+      "loss": 1.6708,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.9981998199819982e-05,
+      "loss": 1.3752,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "step": 2222,
+      "train_runtime": 3913.5949,
+      "train_samples_per_second": 0.568
+    }
+  ],
+  "max_steps": 2222,
+  "num_train_epochs": 2,
+  "total_flos": 401870376571760640,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d067a3c187595936cc0b6c37940decc22a9f34b59550ec45d668010f0f285787
+size 2159