initial upload

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.963302752293578,
+    "eval_loss": 0.19932273030281067,
+    "eval_runtime": 4.0116,
+    "eval_samples": 872,
+    "eval_samples_per_second": 217.369,
+    "eval_steps_per_second": 3.49,
+    "train_loss": 0.0722438246860803,
+    "train_runtime": 2878.5938,
+    "train_samples": 67349,
+    "train_samples_per_second": 233.965,
+    "train_steps_per_second": 1.219
+}

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": "sst2",
+  "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": 0.963302752293578,
+    "eval_loss": 0.19932273030281067,
+    "eval_runtime": 4.0116,
+    "eval_samples": 872,
+    "eval_samples_per_second": 217.369,
+    "eval_steps_per_second": 3.49
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d88706b392af51877b02f892487f392fd19dd386f9ec03969fd12aadae17bf
+size 1421616723

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": 0.0722438246860803,
+    "train_runtime": 2878.5938,
+    "train_samples": 67349,
+    "train_samples_per_second": 233.965,
+    "train_steps_per_second": 1.219
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 3510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.7150997150997152e-05,
+      "loss": 0.2235,
+      "step": 500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.4301994301994305e-05,
+      "loss": 0.1031,
+      "step": 1000
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 1.1452991452991454e-05,
+      "loss": 0.0651,
+      "step": 1500
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 8.603988603988605e-06,
+      "loss": 0.0455,
+      "step": 2000
+    },
+    {
+      "epoch": 7.12,
+      "learning_rate": 5.7549857549857555e-06,
+      "loss": 0.0321,
+      "step": 2500
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 2.9059829059829063e-06,
+      "loss": 0.0216,
+      "step": 3000
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 5.6980056980056986e-08,
+      "loss": 0.0158,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "step": 3510,
+      "total_flos": 1.8380744804433408e+17,
+      "train_loss": 0.0722438246860803,
+      "train_runtime": 2878.5938,
+      "train_samples_per_second": 233.965,
+      "train_steps_per_second": 1.219
+    }
+  ],
+  "max_steps": 3510,
+  "num_train_epochs": 10,
+  "total_flos": 1.8380744804433408e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d99dbd5ada36e0fe8bb088f808e8972a18d84780df62abc447984324ec3bc64
+size 2479