Upload 10 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMabel"
+  ],
+  "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": 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",
+  "transformers_version": "4.2.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d41b808e3ed51e72b3dc7a1d4a533e65ffe30de29bf6db0ab57602f8996efb67
+size 498872747

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-base"}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 2.0
+train_runtime = 2105.7691
+train_samples_per_second = 1.055

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": 7.74977497749775e-05,
+      "loss": 3.0294,
+      "step": 500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.4995499549954995e-05,
+      "loss": 1.7905,
+      "step": 1000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 3.2493249324932494e-05,
+      "loss": 1.5222,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 9.990999099909991e-06,
+      "loss": 1.3883,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "step": 2222,
+      "train_runtime": 2105.7691,
+      "train_samples_per_second": 1.055
+    }
+  ],
+  "max_steps": 2222,
+  "num_train_epochs": 2,
+  "total_flos": 161621779478999040,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce55beaeb9614e44d8e53a4843a8949219ea394a0194f7c7cab8ea8b77a846be
+size 2159