Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "allegro/herbert-base-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "HerbertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d655f411a06fbecbbc71188176642c04f3f18fd7ecbc49c87b3b2537733c562
+size 495498737

runs/Jan20_12-34-32_5ec4d896b877/1642682111.6865454/events.out.tfevents.1642682111.5ec4d896b877.72.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3a74408ef5bb734cf88311acdad1f508ac0ca87e346c65469f6359bdaf41e7
+size 4779

runs/Jan20_12-34-32_5ec4d896b877/events.out.tfevents.1642682111.5ec4d896b877.72.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:740c61b64e59f29fb1890dae5395240926c8f83dcaaf732fe22ade770190df3d
+size 4034

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "sep_token": "</s>", "do_lowercase_and_remove_accent": false, "bos_token": "<s>", "additional_special_tokens": [], "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/a77c29d6c21e653166565b0d51ea0a46b918191512e0ae894422060267a0f436.b8e113717eb1828d09e47de853cf49c8fad05ebdce24df2614cd942dc23e2a77", "name_or_path": "allegro/herbert-base-cased", "lang2id": null, "id2lang": null, "tokenizer_class": "HerbertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0979f01b6f084176da14399e0f6f7cdb574772c1c1c323ffbdcab13c96841ed4
+size 2991