Initial commit

.gitattributes

@@ -6,3 +6,4 @@
 *.tar.gz filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "sst2",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "type_vocab_size": 2,
+  "vocab_size": 28996,
+  "id2label": {
+        0: "NEGATIVE",
+	1: "POSITIVE"
+  },
+  "label2id": {
+	"NEGATIVE": 0,
+	"POSITIVE": 1
+  }
+}

eval_results_sst2.txt

@@ -0,0 +1,5 @@
+epoch = 3.0
+eval_accuracy = 0.9162844036697247
+eval_loss = 0.27853715419769287
+eval_runtime = 1.7949
+eval_samples_per_second = 485.827

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4878e659aafaf7120d59ba2b3ff8fec90598f6a9cda3d747ee99c99765f28e9b
+size 433336585

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-cased"}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 3.0
+train_runtime = 488.8595
+train_samples_per_second = 6.462

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 3159,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4748338081671415,
+      "learning_rate": 1.6834441278885725e-05,
+      "loss": 0.2771715087890625,
+      "step": 500
+    },
+    {
+      "epoch": 0.949667616334283,
+      "learning_rate": 1.3668882557771448e-05,
+      "loss": 0.17857017517089843,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "learning_rate": 1.0503323836657171e-05,
+      "loss": 0.1144794921875,
+      "step": 1500
+    },
+    {
+      "epoch": 1.899335232668566,
+      "learning_rate": 7.337765115542894e-06,
+      "loss": 0.11068717193603515,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3741690408357075,
+      "learning_rate": 4.172206394428617e-06,
+      "loss": 0.08253809356689454,
+      "step": 2500
+    },
+    {
+      "epoch": 2.849002849002849,
+      "learning_rate": 1.00664767331434e-06,
+      "loss": 0.07098492431640625,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "step": 3159,
+      "train_runtime": 488.8595,
+      "train_samples_per_second": 6.462
+    }
+  ],
+  "max_steps": 3159,
+  "num_train_epochs": 3,
+  "total_flos": 16806970579253760,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff23c39bfebf28e3a250908facd0f0befde2af0bd4a33a5b98f6992aeb17d9c
+size 1839