Initial commit

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.86948,
+    "eval_loss": 0.31286707520484924,
+    "eval_runtime": 110.08,
+    "eval_samples": 50000,
+    "eval_samples_per_second": 454.215,
+    "train_runtime": 2882.6525,
+    "train_samples": 150000,
+    "train_samples_per_second": 1.22
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.6.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.86948,
+    "eval_loss": 0.31286707520484924,
+    "eval_runtime": 110.08,
+    "eval_samples": 50000,
+    "eval_samples_per_second": 454.215
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56b6d2332c0a39e4beb1080b243e4bee1e9f54f8847082e271eb62f8b1fd536
+size 711506831

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": "bert-base-multilingual-cased"}

train_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 3.0,
+    "train_runtime": 2882.6525,
+    "train_samples": 150000,
+    "train_samples_per_second": 1.22
+}

trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 3516,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.85022,
+      "eval_loss": 0.33765363693237305,
+      "eval_runtime": 102.5233,
+      "eval_samples_per_second": 487.694,
+      "step": 1172
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0053050397877986e-05,
+      "loss": 0.38,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.86544,
+      "eval_loss": 0.3076673150062561,
+      "eval_runtime": 123.4792,
+      "eval_samples_per_second": 404.926,
+      "step": 2344
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.86948,
+      "eval_loss": 0.31286707520484924,
+      "eval_runtime": 123.9806,
+      "eval_samples_per_second": 403.289,
+      "step": 3516
+    },
+    {
+      "epoch": 3.0,
+      "step": 3516,
+      "total_flos": 0,
+      "train_runtime": 2882.6525,
+      "train_samples_per_second": 1.22
+    }
+  ],
+  "max_steps": 3516,
+  "num_train_epochs": 3,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992835abe5ab9b17241f38ccc1b4bfa1abcb8ddbae3397594858b365c48e8536
+size 2415