initial commit

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.805939788445891,
+    "eval_loss": 0.513519287109375,
+    "eval_runtime": 62.5244,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 157.251,
+    "train_runtime": 5823.0701,
+    "train_samples": 392702,
+    "train_samples_per_second": 2.634
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "mnli",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 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,
+  "transformers_version": "4.6.0.dev0",
+  "vocab_size": 28996
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.805939788445891,
+    "eval_loss": 0.513519287109375,
+    "eval_runtime": 62.5244,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 157.251
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c8d7a45f1cddc743dea13b54f423006aa589caa5465c0dd2c6abd1d041afd2
+size 263178391

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, "special_tokens_map_file": null, "name_or_path": "distilbert-base-cased"}

train_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 5.0,
+    "train_runtime": 5823.0701,
+    "train_samples": 392702,
+    "train_samples_per_second": 2.634
+}

trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 15340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.674054758800522e-06,
+      "loss": 0.8896,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.348109517601044e-06,
+      "loss": 0.73,
+      "step": 1000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.022164276401565e-06,
+      "loss": 0.6784,
+      "step": 1500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.696219035202086e-06,
+      "loss": 0.6549,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.370273794002608e-06,
+      "loss": 0.6285,
+      "step": 2500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.04432855280313e-06,
+      "loss": 0.6158,
+      "step": 3000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.71838331160365e-06,
+      "loss": 0.5714,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 7.392438070404173e-06,
+      "loss": 0.5606,
+      "step": 4000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 7.066492829204694e-06,
+      "loss": 0.555,
+      "step": 4500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 6.7405475880052155e-06,
+      "loss": 0.5472,
+      "step": 5000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 6.414602346805737e-06,
+      "loss": 0.5404,
+      "step": 5500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 6.088657105606258e-06,
+      "loss": 0.5337,
+      "step": 6000
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 5.7627118644067805e-06,
+      "loss": 0.5074,
+      "step": 6500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 5.436766623207301e-06,
+      "loss": 0.4867,
+      "step": 7000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 5.110821382007823e-06,
+      "loss": 0.4881,
+      "step": 7500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.784876140808345e-06,
+      "loss": 0.4887,
+      "step": 8000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 4.458930899608866e-06,
+      "loss": 0.4913,
+      "step": 8500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 4.1329856584093875e-06,
+      "loss": 0.4862,
+      "step": 9000
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 3.807040417209909e-06,
+      "loss": 0.466,
+      "step": 9500
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 3.4810951760104307e-06,
+      "loss": 0.4579,
+      "step": 10000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 3.155149934810952e-06,
+      "loss": 0.4516,
+      "step": 10500
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 2.829204693611474e-06,
+      "loss": 0.4553,
+      "step": 11000
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 2.5032594524119952e-06,
+      "loss": 0.4481,
+      "step": 11500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 2.1773142112125166e-06,
+      "loss": 0.4521,
+      "step": 12000
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 1.851368970013038e-06,
+      "loss": 0.4427,
+      "step": 12500
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 1.5254237288135596e-06,
+      "loss": 0.4286,
+      "step": 13000
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 1.199478487614081e-06,
+      "loss": 0.4282,
+      "step": 13500
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 8.735332464146024e-07,
+      "loss": 0.428,
+      "step": 14000
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 5.475880052151239e-07,
+      "loss": 0.4258,
+      "step": 14500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 2.216427640156454e-07,
+      "loss": 0.4309,
+      "step": 15000
+    },
+    {
+      "epoch": 5.0,
+      "step": 15340,
+      "total_flos": 1.9840077425143296e+17,
+      "train_runtime": 5823.0701,
+      "train_samples_per_second": 2.634
+    }
+  ],
+  "max_steps": 15340,
+  "num_train_epochs": 5,
+  "total_flos": 1.9840077425143296e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938f3800556083a4fae1177eba31d04ba8600dda0de051d728171727f9228a45
+size 2415