Initial commit

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "roberta-base",
+  "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": 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": "4.5.1",
+  "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:d9fc389677b7d0fbe8b3e746a286f51b25bbb36676eb836ea84609cc316c692d
+size 997706211

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a96d9e3828cfae9b5392cd854c720dc1b0785400006ecb6f84dbdeee8d58a93c
+size 498880850

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ce912848630acf66111cfa8430822d9f8ebf66d307bcf6ff3294b92001119c
+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"}

trainer_state.json

@@ -0,0 +1,270 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9372888823615804,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9510451852939737e-05,
+      "loss": 2.5338,
+      "step": 500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9020903705879475e-05,
+      "loss": 2.4335,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.853135555881921e-05,
+      "loss": 2.3284,
+      "step": 1500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.8041807411758948e-05,
+      "loss": 2.3165,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7552259264698686e-05,
+      "loss": 2.2819,
+      "step": 2500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.706271111763842e-05,
+      "loss": 2.2629,
+      "step": 3000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.657316297057816e-05,
+      "loss": 2.2099,
+      "step": 3500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6083614823517894e-05,
+      "loss": 2.2439,
+      "step": 4000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5594066676457633e-05,
+      "loss": 2.1858,
+      "step": 4500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5104518529397367e-05,
+      "loss": 2.1387,
+      "step": 5000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.4614970382337104e-05,
+      "loss": 2.1852,
+      "step": 5500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.412542223527684e-05,
+      "loss": 2.1869,
+      "step": 6000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3635874088216576e-05,
+      "loss": 2.0771,
+      "step": 6500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.0530622005462646,
+      "eval_runtime": 23.6575,
+      "eval_samples_per_second": 255.817,
+      "step": 6809
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.3146325941156315e-05,
+      "loss": 2.1258,
+      "step": 7000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.2656777794096052e-05,
+      "loss": 2.0593,
+      "step": 7500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2167229647035787e-05,
+      "loss": 2.0118,
+      "step": 8000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.1677681499975524e-05,
+      "loss": 1.9987,
+      "step": 8500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.118813335291526e-05,
+      "loss": 2.0134,
+      "step": 9000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0698585205854997e-05,
+      "loss": 1.9785,
+      "step": 9500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0209037058794733e-05,
+      "loss": 1.928,
+      "step": 10000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.71948891173447e-06,
+      "loss": 1.9685,
+      "step": 10500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.229940764674206e-06,
+      "loss": 1.8942,
+      "step": 11000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.740392617613943e-06,
+      "loss": 1.9443,
+      "step": 11500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 8.25084447055368e-06,
+      "loss": 1.8947,
+      "step": 12000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.761296323493416e-06,
+      "loss": 1.9557,
+      "step": 12500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 7.271748176433154e-06,
+      "loss": 1.9083,
+      "step": 13000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.782200029372889e-06,
+      "loss": 1.966,
+      "step": 13500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8375927209854126,
+      "eval_runtime": 23.5457,
+      "eval_samples_per_second": 257.032,
+      "step": 13618
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 6.292651882312626e-06,
+      "loss": 1.943,
+      "step": 14000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 5.8031037352523625e-06,
+      "loss": 1.7706,
+      "step": 14500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.313555588192098e-06,
+      "loss": 1.8079,
+      "step": 15000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.824007441131836e-06,
+      "loss": 1.9021,
+      "step": 15500
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 4.334459294071572e-06,
+      "loss": 1.8314,
+      "step": 16000
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 3.844911147011309e-06,
+      "loss": 1.7882,
+      "step": 16500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 3.3553629999510454e-06,
+      "loss": 1.8472,
+      "step": 17000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.865814852890782e-06,
+      "loss": 1.8157,
+      "step": 17500
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.3762667058305186e-06,
+      "loss": 1.8546,
+      "step": 18000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.8867185587702552e-06,
+      "loss": 1.8019,
+      "step": 18500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.3971704117099918e-06,
+      "loss": 1.7841,
+      "step": 19000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 9.076222646497284e-07,
+      "loss": 1.7894,
+      "step": 19500
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 4.1807411758946493e-07,
+      "loss": 1.8128,
+      "step": 20000
+    }
+  ],
+  "max_steps": 20427,
+  "num_train_epochs": 3,
+  "total_flos": 2165411575408158.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d2e6087a9e1ec57857fe40f288f744868c4c9e28d28f51cd7c6205755b4384
+size 2351