clip_softmax_bert_base

all_results.json

@@ -0,0 +1 @@
+{"perplexity": 6.121930506920037, "ffn_inf_norm": null}

checkpoints/checkpoint_39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b039433172bd58f0178a820c478e3755d2e7f14baabe654cbbb3d4e81d9b1c01
+size 438080896

checkpoints/checkpoint_39/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df3e62068d0c6adbdb1a6a358168976f1130e818131a3058e7cad3f4233bb1b
+size 876283258

checkpoints/checkpoint_39/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:774957800e74346d5ef796243e472d782cd07d2593b50ae97cb14b784f18d03c
+size 14540

checkpoints/checkpoint_39/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e9505a58b331f070b8ae707fe26088d7d942535db378750331306b7b8fccea5
+size 988

checkpoints/checkpoint_39/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce1a5dcd2c892b53958c28251e7c1b5e2332b38fe2990e0031e51182eb102c6
+size 1064

checkpoints/step_95000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1727fdfaed9f1c334cbc9671f8121fd5185d2fdd302064362b5b8dfd915f34
+size 438080896

checkpoints/step_95000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d129b15c3b2a4b1ae352764ebccc5141f96ee2d7127d41f9925a1d2a5100d3
+size 876283258

checkpoints/step_95000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd322b94168aef38ea147009365c5c1586d0ebdd371c32c6b9f9aab1a7ccb151
+size 14540

checkpoints/step_95000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c67ed5f499d2d794733f85b4c9bd62842208a0e82dc7319329fa3837dad44c
+size 988

checkpoints/step_95000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f7985708517a2f95c19d3a217fb1157d77189c726d496fbccb7967468dc1e33
+size 1064

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca88a31292dbb825d01136bceb99e0ae816f83fc7d75a67722e1f379703a4a2
+size 438126578

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}