initial upload

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9469156141314297,
+    "eval_loss": 0.37976524233818054,
+    "eval_runtime": 24.7324,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 220.885,
+    "eval_steps_per_second": 3.477,
+    "train_loss": 0.07572162915498783,
+    "train_runtime": 4508.6421,
+    "train_samples": 104743,
+    "train_samples_per_second": 232.316,
+    "train_steps_per_second": 1.211
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "qnli",
+  "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",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9469156141314297,
+    "eval_loss": 0.37976524233818054,
+    "eval_runtime": 24.7324,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 220.885,
+    "eval_steps_per_second": 3.477
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4470ab1548631d2262e437a592213f60420186c41843c59874df722c7534329a
+size 1421616720

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-large"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.07572162915498783,
+    "train_runtime": 4508.6421,
+    "train_samples": 104743,
+    "train_samples_per_second": 232.316,
+    "train_steps_per_second": 1.211
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 5460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.816849816849817e-05,
+      "loss": 0.2816,
+      "step": 500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.633699633699634e-05,
+      "loss": 0.1677,
+      "step": 1000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.4505494505494506e-05,
+      "loss": 0.114,
+      "step": 1500
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.2673992673992674e-05,
+      "loss": 0.0777,
+      "step": 2000
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 1.0842490842490842e-05,
+      "loss": 0.0569,
+      "step": 2500
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 9.010989010989011e-06,
+      "loss": 0.04,
+      "step": 3000
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 0.0314,
+      "step": 3500
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 5.347985347985348e-06,
+      "loss": 0.0206,
+      "step": 4000
+    },
+    {
+      "epoch": 8.24,
+      "learning_rate": 3.516483516483517e-06,
+      "loss": 0.0171,
+      "step": 4500
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 1.6849816849816852e-06,
+      "loss": 0.0119,
+      "step": 5000
+    },
+    {
+      "epoch": 10.0,
+      "step": 5460,
+      "total_flos": 2.8586235178707456e+17,
+      "train_loss": 0.07572162915498783,
+      "train_runtime": 4508.6421,
+      "train_samples_per_second": 232.316,
+      "train_steps_per_second": 1.211
+    }
+  ],
+  "max_steps": 5460,
+  "num_train_epochs": 10,
+  "total_flos": 2.8586235178707456e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9b2435ca5323e886b58d49d25f95d1eeff6afaedceea081258e4b73e0e3c94
+size 2479