Training in progress, epoch 1

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "funnel-transformer/small-base",
+  "activation_dropout": 0.0,
+  "architectures": [
+    "FunnelForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "attention_type": "relative_shift",
+  "block_repeats": [
+    1,
+    1,
+    1
+  ],
+  "block_sizes": [
+    4,
+    4,
+    4
+  ],
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "hidden_act": "gelu_new",
+  "hidden_dropout": 0.1,
+  "id2label": {
+    "0": "low",
+    "1": "medium",
+    "2": "high"
+  },
+  "initializer_range": 0.1,
+  "initializer_std": null,
+  "label2id": {
+    "high": 2,
+    "low": 0,
+    "medium": 1
+  },
+  "layer_norm_eps": 1e-09,
+  "max_position_embeddings": 512,
+  "model_type": "funnel",
+  "n_head": 12,
+  "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": "4.39.3",
+  "truncate_seq": true,
+  "type_vocab_size": 3,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b103fe7e3bf7f0d7433e4230df069e39950835a1d64ede0e825a3f8e2483f5a8
+size 464847452

runs/May07_16-21-19_flycatch-Modern-15-B11M/events.out.tfevents.1715079079.flycatch-Modern-15-B11M.12128.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f46929fdef93ced6d575cdd5bc1891b4c739e60c1021ee47a68d57aff51bcc
+size 7986

runs/May07_17-51-28_flycatch-Modern-15-B11M/events.out.tfevents.1715084488.flycatch-Modern-15-B11M.13288.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39bbabdcc0e30bc841e1c02f01b608f66d276e0798021ea4a979953967170d9a
+size 5203

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<sep>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,75 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "97": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_text": true,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "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:b84e35af910707ef2b5328020c9487cb84fca00d28fc23fd248c7bb707a7a710
+size 4920