init push

text-tag-classification model based on roberta model

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "cardiffnlp/tweet-topic-19-multi",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb39eb62e3e975e942b7e20d5257d4f1c16a33d4cca9fdcf922a6ee3b8711e8
+size 997363962

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c508dd1a0cdeea48fe40f2a08b47a1ed4101d0bb76537d07c31bb1c32d197c
+size 498667310

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9640a91e7e6753cf95b5f60260001414d9aa57a773571f3208074e088eaf14f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a433bae3653fac61f70f11ea3218b5b35f3f2bca8fae57191391d837dcf89ae
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.658385093167702,
+  "eval_steps": 500,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7929606625258798e-05,
+      "loss": 0.3435,
+      "step": 500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.58592132505176e-05,
+      "loss": 0.2441,
+      "step": 1000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.3788819875776398e-05,
+      "loss": 0.2039,
+      "step": 1500
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.1718426501035198e-05,
+      "loss": 0.1928,
+      "step": 2000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.648033126293997e-06,
+      "loss": 0.1636,
+      "step": 2500
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 7.577639751552796e-06,
+      "loss": 0.1526,
+      "step": 3000
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 5.507246376811595e-06,
+      "loss": 0.1317,
+      "step": 3500
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 3.436853002070394e-06,
+      "loss": 0.1307,
+      "step": 4000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 1.3664596273291927e-06,
+      "loss": 0.1115,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4830,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.893924389455872e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945b6422c5ef135c2891c247ee65e816ec44f9d03a5d1f2668c86082c5facb45
+size 4472