Upload folder using huggingface_hub

checkpoint-57/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert-base-german-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "vocab_size": 31102
+}

checkpoint-57/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0490ea791eee709cfa90580edf9401e3b5d91daf9d3f331b500d2c2ca76908dc
+size 269632784

checkpoint-57/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b2a2a39c92f9081439e7373f24d16737f9186a34c00a2d8ca4352bda5ca267
+size 539324794

checkpoint-57/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452ae5df6d94929c32f06495ab2a616b0235e158367af78a3ba7ec832c976be8
+size 13990

checkpoint-57/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfea2d0623d4619f5b721436255537bdae081135d448923b1da0c0ffb756523d
+size 1064

checkpoint-57/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-57/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-57/trainer_state.json

@@ -0,0 +1,80 @@
+{
+  "best_metric": 0.6608869433403015,
+  "best_model_checkpoint": "./results/checkpoint-57",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 57,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 2.8433685302734375,
+      "learning_rate": 3.75e-07,
+      "loss": 0.6995,
+      "step": 10
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 2.7660646438598633,
+      "learning_rate": 7.5e-07,
+      "loss": 0.6938,
+      "step": 20
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 2.792910575866699,
+      "learning_rate": 1.125e-06,
+      "loss": 0.6891,
+      "step": 30
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 2.688732862472534,
+      "learning_rate": 1.5e-06,
+      "loss": 0.6842,
+      "step": 40
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 2.6673007011413574,
+      "learning_rate": 1.875e-06,
+      "loss": 0.675,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5925110132158591,
+      "eval_f1": 0.6588560018792577,
+      "eval_loss": 0.6608869433403015,
+      "eval_precision": 0.7633276311730559,
+      "eval_recall": 0.5925110132158591,
+      "eval_runtime": 13.8722,
+      "eval_samples_per_second": 16.364,
+      "eval_steps_per_second": 2.091,
+      "step": 57
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 57,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6798478213728.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-57/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d841b30f5915d5690546072525d97ca366b4eb12ce029837897a67cc875177
+size 5304