End of training

README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+base_model: dbmdz/bert-base-german-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: tc
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# tc
+
+This model is a fine-tuned version of [dbmdz/bert-base-german-cased](https://huggingface.co/dbmdz/bert-base-german-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5440
+- Accuracy: 0.9174
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0586        | 1.0   | 1835 | 0.6466          | 0.9073   |
+| 0.047         | 2.0   | 3670 | 0.6389          | 0.9122   |
+| 0.0724        | 3.0   | 5505 | 0.5440          | 0.9174   |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

best_model/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ft",
+    "1": "pkg",
+    "2": "ct",
+    "3": "mr",
+    "4": "ch",
+    "5": "cnc"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ch": 4,
+    "cnc": 5,
+    "ct": 2,
+    "ft": 0,
+    "mr": 3,
+    "pkg": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

best_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191a2f07ce067db18fa985bc8d054de16c3156bcc7e4c64b9f7cd020dd7d38d2
+size 439752712

best_model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2975041d2551f303cc96341eb0a139908c0e3a66a12c1d8b02ca6365d29caba3
+size 879626490

best_model/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3cc3d53538bfcf40d8f2ef6392b586bf2409f1bd066e569b43dc415a6262f7d
+size 14244

best_model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea313d83c88d6f4e65450b460b6dc3429c31c54001492563fb511152a490bb53
+size 1064

best_model/special_tokens_map.json

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

best_model/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

best_model/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.5440165400505066,
+  "best_model_checkpoint": "tc/checkpoint-5505",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5505,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.013308633118867874,
+      "learning_rate": 1.818346957311535e-05,
+      "loss": 0.0364,
+      "step": 500
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.7945733070373535,
+      "learning_rate": 1.63669391462307e-05,
+      "loss": 0.0487,
+      "step": 1000
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.0930397510528564,
+      "learning_rate": 1.455040871934605e-05,
+      "loss": 0.0586,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9073443248398965,
+      "eval_loss": 0.6466261148452759,
+      "eval_runtime": 6.3857,
+      "eval_samples_per_second": 1149.289,
+      "eval_steps_per_second": 71.88,
+      "step": 1835
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 2.8216397762298584,
+      "learning_rate": 1.27338782924614e-05,
+      "loss": 0.0427,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.025512950494885445,
+      "learning_rate": 1.0917347865576748e-05,
+      "loss": 0.0403,
+      "step": 2500
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.08174186199903488,
+      "learning_rate": 9.1008174386921e-06,
+      "loss": 0.0413,
+      "step": 3000
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.005288199055939913,
+      "learning_rate": 7.284287011807448e-06,
+      "loss": 0.047,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.912249625289549,
+      "eval_loss": 0.638913631439209,
+      "eval_runtime": 5.7905,
+      "eval_samples_per_second": 1267.423,
+      "eval_steps_per_second": 79.268,
+      "step": 3670
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 9.735889434814453,
+      "learning_rate": 5.467756584922798e-06,
+      "loss": 0.0728,
+      "step": 4000
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.02875600941479206,
+      "learning_rate": 3.6512261580381475e-06,
+      "loss": 0.0909,
+      "step": 4500
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 53.43143844604492,
+      "learning_rate": 1.8346957311534968e-06,
+      "loss": 0.0809,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 27.897287368774414,
+      "learning_rate": 1.8165304268846506e-08,
+      "loss": 0.0724,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9174274424308488,
+      "eval_loss": 0.5440165400505066,
+      "eval_runtime": 6.5035,
+      "eval_samples_per_second": 1128.468,
+      "eval_steps_per_second": 70.577,
+      "step": 5505
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5505,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 642673888681104.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

best_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb77bee910da7adbffe4e4bbfce76492938e9637a88123aeab82fe9bfed437a0
+size 4856

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ft",
+    "1": "pkg",
+    "2": "ct",
+    "3": "mr",
+    "4": "ch",
+    "5": "cnc"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ch": 4,
+    "cnc": 5,
+    "ct": 2,
+    "ft": 0,
+    "mr": 3,
+    "pkg": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191a2f07ce067db18fa985bc8d054de16c3156bcc7e4c64b9f7cd020dd7d38d2
+size 439752712

runs/Mar06_03-37-40_08f52ca9a3f5/events.out.tfevents.1709696261.08f52ca9a3f5.893.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26156bdb72a9d251d87ef98deaef9132d4851c48d54512a85ecce689b4fc8e8e
+size 8462

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb77bee910da7adbffe4e4bbfce76492938e9637a88123aeab82fe9bfed437a0
+size 4856