init

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 2137276416,
+    "init_mem_cpu_peaked_delta": 0,
+    "init_mem_gpu_alloc_delta": 70744576,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 2395598848,
+    "train_mem_cpu_peaked_delta": 7942144,
+    "train_mem_gpu_alloc_delta": 212932096,
+    "train_mem_gpu_peaked_delta": 18954537472,
+    "train_runtime": 6417.4773,
+    "train_samples_per_second": 1.224
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "albert-large-v2",
+  "architectures": [
+    "AlbertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 16,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 24,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.5.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebe3e1ad6085b09be7a1fc71972f9b62b103847b20aa6bcd4b855d0dad99b2d
+size 70755932

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-large-v2"}

train_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 2137276416,
+    "init_mem_cpu_peaked_delta": 0,
+    "init_mem_gpu_alloc_delta": 70744576,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 2395598848,
+    "train_mem_cpu_peaked_delta": 7942144,
+    "train_mem_gpu_alloc_delta": 212932096,
+    "train_mem_gpu_peaked_delta": 18954537472,
+    "train_runtime": 6417.4773,
+    "train_samples_per_second": 1.224
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e40ad43d54f50a001d481aad07b8d814a24f985597b0416d6a12425f9c2cb7b
+size 2415