Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "funnel-transformer/xlarge",
+  "activation_dropout": 0.0,
+  "architectures": [
+    "FunnelForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "attention_type": "relative_shift",
+  "block_repeats": [
+    1,
+    1,
+    1
+  ],
+  "block_sizes": [
+    10,
+    10,
+    10
+  ],
+  "d_head": 64,
+  "d_inner": 4096,
+  "d_model": 1024,
+  "hidden_act": "gelu_new",
+  "hidden_dropout": 0.1,
+  "initializer_range": 0.1,
+  "initializer_std": null,
+  "layer_norm_eps": 1e-09,
+  "max_position_embeddings": 512,
+  "model_type": "funnel",
+  "n_head": 16,
+  "num_decoder_layers": 2,
+  "pool_q_only": true,
+  "pooling_type": "mean",
+  "problem_type": "single_label_classification",
+  "rel_attn_type": "factorized",
+  "separate_cls": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "truncate_seq": true,
+  "type_vocab_size": 3,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9739b4b54ea77a600ae79760b30cec5db2592ad8e57ddd3b1b1fb3568e46e5e
+size 1767309001

runs/Dec13_17-07-42_075fc617ac43/1670951272.1928294/events.out.tfevents.1670951272.075fc617ac43.76.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05e0aa47ae29aad3d3a27811c42d75fd2adc8b55b191bf0a16b0c92e62f0c40
+size 5603

runs/Dec13_17-07-42_075fc617ac43/events.out.tfevents.1670951272.075fc617ac43.76.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d194006dfc429e3bce23d0fed40940847c8d0f4aa20a81faf1918805f7ebcd9c
+size 4285

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": "<s>",
+  "clean_text": true,
+  "cls_token": "<cls>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "funnel-transformer/xlarge",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--funnel-transformer--xlarge/snapshots/a57ed38432204c958ec9df4b8fc999176d10005e/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "FunnelTokenizer",
+  "unk_token": "<unk>",
+  "wordpieces_prefix": "##"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d0ab0278efebce4c6d4e45c390c482fe0f2c2c227603bc0778ae2f6b894c49
+size 3579