model version

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9013761467889908,
+    "eval_loss": 0.3691919445991516,
+    "eval_mem_cpu_alloc_delta": 1605632,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 25477120,
+    "eval_runtime": 3.9152,
+    "eval_samples": 872,
+    "eval_samples_per_second": 222.719,
+    "init_mem_cpu_alloc_delta": 1199738880,
+    "init_mem_cpu_peaked_delta": 74649600,
+    "init_mem_gpu_alloc_delta": 90860544,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 434720768,
+    "train_mem_cpu_peaked_delta": 141451264,
+    "train_mem_gpu_alloc_delta": 274994176,
+    "train_mem_gpu_peaked_delta": 1159366656,
+    "train_runtime": 1085.2317,
+    "train_samples": 67349,
+    "train_samples_per_second": 5.819
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "nreimers/MiniLM-L6-H384-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": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9013761467889908,
+    "eval_loss": 0.3691919445991516,
+    "eval_mem_cpu_alloc_delta": 1605632,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 25477120,
+    "eval_runtime": 3.9152,
+    "eval_samples": 872,
+    "eval_samples_per_second": 222.719
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51107694bb6266b86e5951871995895b1c95438fc35b292e4c06e113196018f7
+size 90904553

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, "name_or_path": "nreimers/MiniLM-L6-H384-uncased", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/4bab06d0845c01b218fc031866e62ccf55a15d3f649549f76c89e002ba24d5d9.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 1199738880,
+    "init_mem_cpu_peaked_delta": 74649600,
+    "init_mem_gpu_alloc_delta": 90860544,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 434720768,
+    "train_mem_cpu_peaked_delta": 141451264,
+    "train_mem_gpu_alloc_delta": 274994176,
+    "train_mem_gpu_peaked_delta": 1159366656,
+    "train_runtime": 1085.2317,
+    "train_samples": 67349,
+    "train_samples_per_second": 5.819
+}