First commit

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446b7c1d0aae036cd76cc658947ebb996d11963070fa4125d2eb4e766dcf6556
+size 535700065

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954bc13ef8c16ac1166ca329dee788ba897727a25f471d1673d626a6f4811f60
+size 267854321

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316f57b54794e8217437adff19828bf3211d43ce8edcd1e1c556a4d384c813de
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6a05060cf87c9154cd8ec8b533f14193797c1571031ce73fba49f7cd7b6f8b
+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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}

trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.62962962962963,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.57912457912458e-05,
+      "loss": 0.2927,
+      "step": 500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.158249158249159e-05,
+      "loss": 0.1893,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.962,
+      "eval_f1": 0.9604989604989606,
+      "eval_loss": 0.14235617220401764,
+      "eval_runtime": 1.4452,
+      "eval_samples_per_second": 345.973,
+      "eval_steps_per_second": 43.593,
+      "step": 1188
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.7373737373737376e-05,
+      "loss": 0.1151,
+      "step": 1500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.3164983164983165e-05,
+      "loss": 0.0722,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.956,
+      "eval_f1": 0.9539748953974895,
+      "eval_loss": 0.2519678771495819,
+      "eval_runtime": 1.3777,
+      "eval_samples_per_second": 362.913,
+      "eval_steps_per_second": 45.727,
+      "step": 2376
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 2.8956228956228958e-05,
+      "loss": 0.0563,
+      "step": 2500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 2.474747474747475e-05,
+      "loss": 0.0135,
+      "step": 3000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 2.0538720538720542e-05,
+      "loss": 0.0204,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.962,
+      "eval_f1": 0.9608247422680413,
+      "eval_loss": 0.2846008539199829,
+      "eval_runtime": 1.2758,
+      "eval_samples_per_second": 391.904,
+      "eval_steps_per_second": 49.38,
+      "step": 3564
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 1.632996632996633e-05,
+      "loss": 0.005,
+      "step": 4000
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 0.0001,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.956,
+      "eval_f1": 0.9541666666666667,
+      "eval_loss": 0.3692273795604706,
+      "eval_runtime": 1.4564,
+      "eval_samples_per_second": 343.322,
+      "eval_steps_per_second": 43.259,
+      "step": 4752
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 7.912457912457913e-06,
+      "loss": 0.0024,
+      "step": 5000
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.0,
+      "step": 5500
+    }
+  ],
+  "max_steps": 5940,
+  "num_train_epochs": 5,
+  "total_flos": 555135681114528.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f43a7012131c612efbe4afc6b48a1af3ef1002538e100750ddbcb5fba5cf0a2
+size 3055