initial update

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.930045871559633,
+    "eval_loss": 0.2815348505973816,
+    "eval_runtime": 6.102,
+    "eval_samples": 872,
+    "eval_samples_per_second": 142.903,
+    "eval_steps_per_second": 17.863,
+    "train_runtime": 3803.621,
+    "train_samples": 67349,
+    "train_samples_per_second": 53.12,
+    "train_steps_per_second": 1.66
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.930045871559633,
+    "eval_loss": 0.2815348505973816,
+    "eval_runtime": 6.102,
+    "eval_samples": 872,
+    "eval_samples_per_second": 142.903,
+    "eval_steps_per_second": 17.863
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db4c5757a1bdbf2dcd4c1074b2b33e4f70aa18d28e406c4d96fe28f73db3206
+size 438022419

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": "bert-base-uncased"}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_runtime": 3803.621,
+    "train_samples": 67349,
+    "train_samples_per_second": 53.12,
+    "train_steps_per_second": 1.66
+}

trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6315,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.8416468725257326e-05,
+      "loss": 0.2907,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6832937450514647e-05,
+      "loss": 0.2119,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5249406175771972e-05,
+      "loss": 0.177,
+      "step": 1500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3665874901029297e-05,
+      "loss": 0.1662,
+      "step": 2000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.208234362628662e-05,
+      "loss": 0.1205,
+      "step": 2500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.0498812351543943e-05,
+      "loss": 0.1084,
+      "step": 3000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.915281076801267e-06,
+      "loss": 0.1129,
+      "step": 3500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.331749802058591e-06,
+      "loss": 0.107,
+      "step": 4000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 5.748218527315916e-06,
+      "loss": 0.0804,
+      "step": 4500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 4.164687252573238e-06,
+      "loss": 0.0691,
+      "step": 5000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 2.581155977830562e-06,
+      "loss": 0.0643,
+      "step": 5500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 9.976247030878861e-07,
+      "loss": 0.0733,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "step": 6315,
+      "total_flos": 1.6988827310258688e+16,
+      "train_runtime": 3803.621,
+      "train_samples_per_second": 53.12,
+      "train_steps_per_second": 1.66
+    }
+  ],
+  "max_steps": 6315,
+  "num_train_epochs": 3,
+  "total_flos": 1.6988827310258688e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2987be78eca33880309cb9273bac03f6cfc5eb4644398f2c3a7f3c38f811126
+size 2415