initial commit

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8206875508543532,
+    "eval_loss": 0.5114499926567078,
+    "eval_mem_cpu_alloc_delta": 155648,
+    "eval_mem_cpu_peaked_delta": 77824,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 94678016,
+    "eval_runtime": 44.0609,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 223.146,
+    "init_mem_cpu_alloc_delta": 2353512448,
+    "init_mem_cpu_peaked_delta": 261173248,
+    "init_mem_gpu_alloc_delta": 268956160,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 3074768896,
+    "train_mem_cpu_peaked_delta": 7049216,
+    "train_mem_gpu_alloc_delta": 814749184,
+    "train_mem_gpu_peaked_delta": 9148695040,
+    "train_runtime": 9244.0598,
+    "train_samples": 392702,
+    "train_samples_per_second": 1.659
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "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,
+  "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": 30522
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8206875508543532,
+    "eval_loss": 0.5114499926567078,
+    "eval_mem_cpu_alloc_delta": 155648,
+    "eval_mem_cpu_peaked_delta": 77824,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 94678016,
+    "eval_runtime": 44.0609,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 223.146
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d7d7ecd90f379a15d91851873d35fb2de0041c37107d2801f4846796a97ac3
+size 267866263

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"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "init_mem_cpu_alloc_delta": 2353512448,
+    "init_mem_cpu_peaked_delta": 261173248,
+    "init_mem_gpu_alloc_delta": 268956160,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 3074768896,
+    "train_mem_cpu_peaked_delta": 7049216,
+    "train_mem_gpu_alloc_delta": 814749184,
+    "train_mem_gpu_peaked_delta": 9148695040,
+    "train_runtime": 9244.0598,
+    "train_samples": 392702,
+    "train_samples_per_second": 1.659
+}

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": 1.9348109517601044e-05,
+      "loss": 0.8074,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8696219035202087e-05,
+      "loss": 0.6682,
+      "step": 1000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.804432855280313e-05,
+      "loss": 0.611,
+      "step": 1500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7392438070404173e-05,
+      "loss": 0.5862,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6740547588005215e-05,
+      "loss": 0.5626,
+      "step": 2500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.608865710560626e-05,
+      "loss": 0.5506,
+      "step": 3000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.54367666232073e-05,
+      "loss": 0.4885,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.4784876140808346e-05,
+      "loss": 0.4766,
+      "step": 4000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.4132985658409388e-05,
+      "loss": 0.476,
+      "step": 4500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.3481095176010431e-05,
+      "loss": 0.4706,
+      "step": 5000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.2829204693611474e-05,
+      "loss": 0.4649,
+      "step": 5500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.2177314211212517e-05,
+      "loss": 0.4578,
+      "step": 6000
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.1525423728813561e-05,
+      "loss": 0.4158,
+      "step": 6500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.0873533246414602e-05,
+      "loss": 0.3907,
+      "step": 7000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.0221642764015647e-05,
+      "loss": 0.3917,
+      "step": 7500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 9.56975228161669e-06,
+      "loss": 0.3958,
+      "step": 8000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 8.917861799217732e-06,
+      "loss": 0.3962,
+      "step": 8500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 8.265971316818775e-06,
+      "loss": 0.3947,
+      "step": 9000
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 7.614080834419818e-06,
+      "loss": 0.3621,
+      "step": 9500
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 6.962190352020861e-06,
+      "loss": 0.3429,
+      "step": 10000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 6.310299869621904e-06,
+      "loss": 0.3391,
+      "step": 10500
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 5.658409387222948e-06,
+      "loss": 0.3437,
+      "step": 11000
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 5.0065189048239905e-06,
+      "loss": 0.3356,
+      "step": 11500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 4.354628422425033e-06,
+      "loss": 0.3387,
+      "step": 12000
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 3.702737940026076e-06,
+      "loss": 0.3183,
+      "step": 12500
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 3.0508474576271192e-06,
+      "loss": 0.3044,
+      "step": 13000
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 2.398956975228162e-06,
+      "loss": 0.3057,
+      "step": 13500
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 1.7470664928292048e-06,
+      "loss": 0.3049,
+      "step": 14000
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 1.0951760104302478e-06,
+      "loss": 0.2996,
+      "step": 14500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 4.432855280312908e-07,
+      "loss": 0.3059,
+      "step": 15000
+    },
+    {
+      "epoch": 5.0,
+      "step": 15340,
+      "total_flos": 2.0193537273490944e+17,
+      "train_runtime": 9244.0598,
+      "train_samples_per_second": 1.659
+    }
+  ],
+  "max_steps": 15340,
+  "num_train_epochs": 5,
+  "total_flos": 2.0193537273490944e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4affb7533232ac7532aceb3a7b2e0dee1dcc85eb1b3b5ee752a742d0bd3f2c
+size 2479