Upload 4 files

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8094187154165773,
+    "eval_loss": 0.8141809105873108,
+    "eval_runtime": 4409.0569,
+    "eval_samples": 700409,
+    "eval_samples_per_second": 158.857,
+    "eval_steps_per_second": 4.964,
+    "perplexity": 2.2573259631171148,
+    "total_flos": 1.4697804058526134e+19,
+    "train_loss": 0.807495192525475,
+    "train_runtime": 715284.2162,
+    "train_samples": 18594579,
+    "train_samples_per_second": 77.988,
+    "train_steps_per_second": 2.437
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "../google-bert/bert-base-multilingual-cased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8094187154165773,
+    "eval_loss": 0.8141809105873108,
+    "eval_runtime": 4409.0569,
+    "eval_samples": 700409,
+    "eval_samples_per_second": 158.857,
+    "eval_steps_per_second": 4.964,
+    "perplexity": 2.2573259631171148
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0.dev0"
+}