[Model] bert-base-uncased-sst2

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "sst2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12a84336807ff577babf0cbb83dabb29ad418fb583d6f99146a7fe5247c6dbd
+size 875997219

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a25d8250266ce9d1b7ee05cea4dcae78282d04bc4b1dffe2bb0bd593e588e79
+size 438024851

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae3f6d8e480d1c250760508243b798ce99d6ed7c97a463ac33cb638d9238c4e
+size 14659

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2d2e57c287fce33099c15f6387a75485d0e41f4f29467d7c866ce16cbaea7c
+size 623

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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": 0.22027112543582916,
+  "best_model_checkpoint": "output_dir/finetuned_best_sst2/checkpoint-1000",
+  "epoch": 2.6128266033254155,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9049881235154395e-05,
+      "loss": 0.2923,
+      "step": 500
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.9059633027522935,
+      "eval_loss": 0.26220595836639404,
+      "eval_runtime": 9.462,
+      "eval_samples_per_second": 92.158,
+      "eval_steps_per_second": 11.52,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.809976247030879e-05,
+      "loss": 0.2077,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.9128440366972477,
+      "eval_loss": 0.22027112543582916,
+      "eval_runtime": 7.6526,
+      "eval_samples_per_second": 113.948,
+      "eval_steps_per_second": 14.243,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7149643705463184e-05,
+      "loss": 0.1788,
+      "step": 1500
+    },
+    {
+      "epoch": 0.71,
+      "eval_accuracy": 0.9197247706422018,
+      "eval_loss": 0.23272211849689484,
+      "eval_runtime": 8.0847,
+      "eval_samples_per_second": 107.859,
+      "eval_steps_per_second": 13.482,
+      "step": 1500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6199524940617578e-05,
+      "loss": 0.1683,
+      "step": 2000
+    },
+    {
+      "epoch": 0.95,
+      "eval_accuracy": 0.9243119266055045,
+      "eval_loss": 0.23030078411102295,
+      "eval_runtime": 7.2988,
+      "eval_samples_per_second": 119.472,
+      "eval_steps_per_second": 14.934,
+      "step": 2000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.5249406175771972e-05,
+      "loss": 0.1224,
+      "step": 2500
+    },
+    {
+      "epoch": 1.19,
+      "eval_accuracy": 0.9174311926605505,
+      "eval_loss": 0.2473384588956833,
+      "eval_runtime": 7.244,
+      "eval_samples_per_second": 120.376,
+      "eval_steps_per_second": 15.047,
+      "step": 2500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.4299287410926367e-05,
+      "loss": 0.113,
+      "step": 3000
+    },
+    {
+      "epoch": 1.43,
+      "eval_accuracy": 0.9231651376146789,
+      "eval_loss": 0.27146443724632263,
+      "eval_runtime": 5.5379,
+      "eval_samples_per_second": 157.462,
+      "eval_steps_per_second": 19.683,
+      "step": 3000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.3349168646080762e-05,
+      "loss": 0.1172,
+      "step": 3500
+    },
+    {
+      "epoch": 1.66,
+      "eval_accuracy": 0.9162844036697247,
+      "eval_loss": 0.2674899697303772,
+      "eval_runtime": 3.9248,
+      "eval_samples_per_second": 222.178,
+      "eval_steps_per_second": 27.772,
+      "step": 3500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.2399049881235155e-05,
+      "loss": 0.109,
+      "step": 4000
+    },
+    {
+      "epoch": 1.9,
+      "eval_accuracy": 0.930045871559633,
+      "eval_loss": 0.25721675157546997,
+      "eval_runtime": 4.4172,
+      "eval_samples_per_second": 197.409,
+      "eval_steps_per_second": 24.676,
+      "step": 4000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.144893111638955e-05,
+      "loss": 0.0852,
+      "step": 4500
+    },
+    {
+      "epoch": 2.14,
+      "eval_accuracy": 0.9277522935779816,
+      "eval_loss": 0.2888570725917816,
+      "eval_runtime": 3.7013,
+      "eval_samples_per_second": 235.594,
+      "eval_steps_per_second": 29.449,
+      "step": 4500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.0498812351543943e-05,
+      "loss": 0.0755,
+      "step": 5000
+    },
+    {
+      "epoch": 2.38,
+      "eval_accuracy": 0.9254587155963303,
+      "eval_loss": 0.2975403666496277,
+      "eval_runtime": 3.8908,
+      "eval_samples_per_second": 224.116,
+      "eval_steps_per_second": 28.014,
+      "step": 5000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 9.548693586698338e-06,
+      "loss": 0.0748,
+      "step": 5500
+    },
+    {
+      "epoch": 2.61,
+      "eval_accuracy": 0.9334862385321101,
+      "eval_loss": 0.27799510955810547,
+      "eval_runtime": 3.8809,
+      "eval_samples_per_second": 224.689,
+      "eval_steps_per_second": 28.086,
+      "step": 5500
+    }
+  ],
+  "max_steps": 10525,
+  "num_train_epochs": 5,
+  "total_flos": 1.157543932503552e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903609768ed94e847ce61f0b89aff85f9c0153b7f54de38f5ab9064986c15c44
+size 2927