Delete folder checkpoint-645 with huggingface_hub

checkpoint-645/config.json

@@ -1,47 +0,0 @@
-{
-  "architectures": [
-    "DebertaV2ForTokenClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": null,
-  "dtype": "float32",
-  "eos_token_id": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
-  "id2label": {
-    "0": "O",
-    "1": "TRIGGER"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "O": 0,
-    "TRIGGER": 1
-  },
-  "layer_norm_eps": 1e-07,
-  "legacy": true,
-  "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta-v2",
-  "norm_rel_ebd": "layer_norm",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 0,
-  "pooler_dropout": 0.0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 1024,
-  "pos_att_type": [
-    "p2c",
-    "c2p"
-  ],
-  "position_biased_input": false,
-  "position_buckets": 256,
-  "relative_attention": true,
-  "share_att_key": true,
-  "tie_word_embeddings": true,
-  "transformers_version": "5.12.1",
-  "type_vocab_size": 0,
-  "use_cache": false,
-  "vocab_size": 128100
-}

checkpoint-645/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:725fdb789a8fd22ad6c8d711eaec78b7e568694ee45fc31ab593063f133b7aa0
-size 1736105856

checkpoint-645/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b9195306a905e59e5916a1ce430da22299ad4a02b24d55e0515c93b56634f3f1
-size 3472447675

checkpoint-645/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:675afdb065308f66ff44bcbcf122f8b621bf37cbfbc2a1c2476db1529fb6be71
-size 14645

checkpoint-645/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4d9e71125fde45151f6dea67ddbb624952bcaa5a666d91168191909473bc1e72
-size 1465

checkpoint-645/tokenizer_config.json

@@ -1,24 +0,0 @@
-{
-  "add_prefix_space": true,
-  "backend": "tokenizers",
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "extra_special_tokens": [
-    "[PAD]",
-    "[CLS]",
-    "[SEP]"
-  ],
-  "is_local": false,
-  "local_files_only": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_id": 3,
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
-}

checkpoint-645/trainer_state.json

@@ -1,151 +0,0 @@
-{
-  "best_global_step": 645,
-  "best_metric": 0.794392523364486,
-  "best_model_checkpoint": "outputs/trigger/checkpoint-645",
-  "epoch": 3.0,
-  "eval_steps": 500,
-  "global_step": 645,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.23255813953488372,
-      "grad_norm": 2.8601179122924805,
-      "learning_rate": 7.538461538461539e-06,
-      "loss": 0.4856879425048828,
-      "step": 50
-    },
-    {
-      "epoch": 0.46511627906976744,
-      "grad_norm": 1.5334198474884033,
-      "learning_rate": 9.663366336633663e-06,
-      "loss": 0.3592271423339844,
-      "step": 100
-    },
-    {
-      "epoch": 0.6976744186046512,
-      "grad_norm": 1.665016531944275,
-      "learning_rate": 9.168316831683169e-06,
-      "loss": 0.30700958251953125,
-      "step": 150
-    },
-    {
-      "epoch": 0.9302325581395349,
-      "grad_norm": 2.089900255203247,
-      "learning_rate": 8.673267326732673e-06,
-      "loss": 0.280797061920166,
-      "step": 200
-    },
-    {
-      "epoch": 1.0,
-      "eval_loss": 0.2680956721305847,
-      "eval_runtime": 1.3365,
-      "eval_samples_per_second": 245.416,
-      "eval_steps_per_second": 15.713,
-      "eval_token_f1": 0.7571644042232278,
-      "eval_token_precision": 0.7854269110415736,
-      "eval_token_recall": 0.730865224625624,
-      "step": 215
-    },
-    {
-      "epoch": 1.1627906976744187,
-      "grad_norm": 2.0754435062408447,
-      "learning_rate": 8.178217821782179e-06,
-      "loss": 0.265327205657959,
-      "step": 250
-    },
-    {
-      "epoch": 1.3953488372093024,
-      "grad_norm": 1.4235446453094482,
-      "learning_rate": 7.683168316831683e-06,
-      "loss": 0.22734785079956055,
-      "step": 300
-    },
-    {
-      "epoch": 1.627906976744186,
-      "grad_norm": 1.9681403636932373,
-      "learning_rate": 7.188118811881188e-06,
-      "loss": 0.22995534896850586,
-      "step": 350
-    },
-    {
-      "epoch": 1.8604651162790697,
-      "grad_norm": 1.9590110778808594,
-      "learning_rate": 6.693069306930694e-06,
-      "loss": 0.22398286819458008,
-      "step": 400
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.2507256269454956,
-      "eval_runtime": 1.3396,
-      "eval_samples_per_second": 244.857,
-      "eval_steps_per_second": 15.677,
-      "eval_token_f1": 0.791769547325103,
-      "eval_token_precision": 0.7833876221498371,
-      "eval_token_recall": 0.800332778702163,
-      "step": 430
-    },
-    {
-      "epoch": 2.0930232558139537,
-      "grad_norm": 1.8518685102462769,
-      "learning_rate": 6.198019801980198e-06,
-      "loss": 0.20480815887451173,
-      "step": 450
-    },
-    {
-      "epoch": 2.3255813953488373,
-      "grad_norm": 1.9515743255615234,
-      "learning_rate": 5.702970297029703e-06,
-      "loss": 0.17671422958374022,
-      "step": 500
-    },
-    {
-      "epoch": 2.558139534883721,
-      "grad_norm": 1.5809895992279053,
-      "learning_rate": 5.207920792079208e-06,
-      "loss": 0.17426620483398436,
-      "step": 550
-    },
-    {
-      "epoch": 2.7906976744186047,
-      "grad_norm": 2.1711745262145996,
-      "learning_rate": 4.712871287128713e-06,
-      "loss": 0.1732681655883789,
-      "step": 600
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 0.258331298828125,
-      "eval_runtime": 1.3037,
-      "eval_samples_per_second": 251.601,
-      "eval_steps_per_second": 16.109,
-      "eval_token_f1": 0.794392523364486,
-      "eval_token_precision": 0.8116319444444444,
-      "eval_token_recall": 0.7778702163061564,
-      "step": 645
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 1075,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1078591645294896.0,
-  "train_batch_size": 16,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-645/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d99ad9ede6f23bd47d75def4b8715070853c39f3049288ced5ba8a8c320138f2
-size 5201