Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- autotrain-df1770/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.5543721318244934
+
+f1_macro: 0.7679742314070671
+
+f1_micro: 0.7777777777777778
+
+f1_weighted: 0.7707658289747842
+
+precision_macro: 0.7848406546080966
+
+precision_micro: 0.7777777777777778
+
+precision_weighted: 0.7778696525983347
+
+recall_macro: 0.7620894891084323
+
+recall_micro: 0.7777777777777778
+
+recall_weighted: 0.7777777777777778
+
+accuracy: 0.7777777777777778

checkpoint-358/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "oliverguhr/german-sentiment-bert",
+  "_num_labels": 3,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "germansentiment",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoint-358/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa35e386bcb6d05883882a045e9e5520d3b382d42a52bcb68d41f4cb4628cbc8
+size 436358132

checkpoint-358/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd4bae24da1f02b1b88674e62abbdf305d2dbfc88c7b25f02a578639ee8afa6
+size 872837370

checkpoint-358/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a91a1e219bba43507a1274dfd27d4d9a8bbd8422c54cafd6ede13bb9de2e25
+size 14244

checkpoint-358/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1044cd1233e65bcc195c80ba0eb84054070ff00b7f6a4d3bb6c667322091d1
+size 1064

checkpoint-358/trainer_state.json

@@ -0,0 +1,414 @@
+{
+  "best_metric": 0.5543721318244934,
+  "best_model_checkpoint": "autotrain-df1770/checkpoint-358",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 358,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03910614525139665,
+      "grad_norm": Infinity,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.7849,
+      "step": 7
+    },
+    {
+      "epoch": 0.0782122905027933,
+      "grad_norm": 26.998300552368164,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.7974,
+      "step": 14
+    },
+    {
+      "epoch": 0.11731843575418995,
+      "grad_norm": 72.14756774902344,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 1.3511,
+      "step": 21
+    },
+    {
+      "epoch": 0.1564245810055866,
+      "grad_norm": 40.11323165893555,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.2651,
+      "step": 28
+    },
+    {
+      "epoch": 0.19553072625698323,
+      "grad_norm": 34.13031768798828,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.65,
+      "step": 35
+    },
+    {
+      "epoch": 0.2346368715083799,
+      "grad_norm": 4.031013488769531,
+      "learning_rate": 3.425925925925926e-05,
+      "loss": 0.7898,
+      "step": 42
+    },
+    {
+      "epoch": 0.2737430167597765,
+      "grad_norm": 37.36408615112305,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.7657,
+      "step": 49
+    },
+    {
+      "epoch": 0.3128491620111732,
+      "grad_norm": 9.450926780700684,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.7868,
+      "step": 56
+    },
+    {
+      "epoch": 0.35195530726256985,
+      "grad_norm": 5.750401496887207,
+      "learning_rate": 4.958592132505176e-05,
+      "loss": 0.9469,
+      "step": 63
+    },
+    {
+      "epoch": 0.39106145251396646,
+      "grad_norm": 6.385225772857666,
+      "learning_rate": 4.886128364389234e-05,
+      "loss": 0.7381,
+      "step": 70
+    },
+    {
+      "epoch": 0.4301675977653631,
+      "grad_norm": 5.707835674285889,
+      "learning_rate": 4.8136645962732924e-05,
+      "loss": 0.7006,
+      "step": 77
+    },
+    {
+      "epoch": 0.4692737430167598,
+      "grad_norm": 14.439386367797852,
+      "learning_rate": 4.74120082815735e-05,
+      "loss": 0.6639,
+      "step": 84
+    },
+    {
+      "epoch": 0.5083798882681564,
+      "grad_norm": 26.590147018432617,
+      "learning_rate": 4.668737060041408e-05,
+      "loss": 0.7436,
+      "step": 91
+    },
+    {
+      "epoch": 0.547486033519553,
+      "grad_norm": 8.74451732635498,
+      "learning_rate": 4.5962732919254656e-05,
+      "loss": 0.6531,
+      "step": 98
+    },
+    {
+      "epoch": 0.5865921787709497,
+      "grad_norm": 14.613375663757324,
+      "learning_rate": 4.523809523809524e-05,
+      "loss": 0.5502,
+      "step": 105
+    },
+    {
+      "epoch": 0.6256983240223464,
+      "grad_norm": 18.908952713012695,
+      "learning_rate": 4.451345755693582e-05,
+      "loss": 0.578,
+      "step": 112
+    },
+    {
+      "epoch": 0.664804469273743,
+      "grad_norm": 7.9073333740234375,
+      "learning_rate": 4.3788819875776396e-05,
+      "loss": 0.6046,
+      "step": 119
+    },
+    {
+      "epoch": 0.7039106145251397,
+      "grad_norm": 13.5628080368042,
+      "learning_rate": 4.306418219461698e-05,
+      "loss": 0.6825,
+      "step": 126
+    },
+    {
+      "epoch": 0.7430167597765364,
+      "grad_norm": 21.76129913330078,
+      "learning_rate": 4.233954451345756e-05,
+      "loss": 0.6136,
+      "step": 133
+    },
+    {
+      "epoch": 0.7821229050279329,
+      "grad_norm": 8.919886589050293,
+      "learning_rate": 4.161490683229814e-05,
+      "loss": 0.7172,
+      "step": 140
+    },
+    {
+      "epoch": 0.8212290502793296,
+      "grad_norm": 17.3486270904541,
+      "learning_rate": 4.089026915113872e-05,
+      "loss": 0.6536,
+      "step": 147
+    },
+    {
+      "epoch": 0.8603351955307262,
+      "grad_norm": 5.042856693267822,
+      "learning_rate": 4.01656314699793e-05,
+      "loss": 0.5795,
+      "step": 154
+    },
+    {
+      "epoch": 0.8994413407821229,
+      "grad_norm": 10.089982032775879,
+      "learning_rate": 3.944099378881988e-05,
+      "loss": 0.4422,
+      "step": 161
+    },
+    {
+      "epoch": 0.9385474860335196,
+      "grad_norm": 8.185463905334473,
+      "learning_rate": 3.8716356107660456e-05,
+      "loss": 0.5781,
+      "step": 168
+    },
+    {
+      "epoch": 0.9776536312849162,
+      "grad_norm": 8.611544609069824,
+      "learning_rate": 3.799171842650104e-05,
+      "loss": 0.7085,
+      "step": 175
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6793650793650794,
+      "eval_f1_macro": 0.5782240623162028,
+      "eval_f1_micro": 0.6793650793650794,
+      "eval_f1_weighted": 0.6491507979511092,
+      "eval_loss": 0.7037036418914795,
+      "eval_precision_macro": 0.6092237192939769,
+      "eval_precision_micro": 0.6793650793650794,
+      "eval_precision_weighted": 0.7107957653290541,
+      "eval_recall_macro": 0.6734765400767394,
+      "eval_recall_micro": 0.6793650793650794,
+      "eval_recall_weighted": 0.6793650793650794,
+      "eval_runtime": 0.8316,
+      "eval_samples_per_second": 378.776,
+      "eval_steps_per_second": 24.049,
+      "step": 179
+    },
+    {
+      "epoch": 1.0167597765363128,
+      "grad_norm": 6.034320831298828,
+      "learning_rate": 3.7267080745341614e-05,
+      "loss": 0.5818,
+      "step": 182
+    },
+    {
+      "epoch": 1.0558659217877095,
+      "grad_norm": 4.3413405418396,
+      "learning_rate": 3.6542443064182196e-05,
+      "loss": 0.4607,
+      "step": 189
+    },
+    {
+      "epoch": 1.094972067039106,
+      "grad_norm": 7.182992935180664,
+      "learning_rate": 3.581780538302277e-05,
+      "loss": 0.5552,
+      "step": 196
+    },
+    {
+      "epoch": 1.1340782122905029,
+      "grad_norm": 25.679845809936523,
+      "learning_rate": 3.509316770186335e-05,
+      "loss": 0.357,
+      "step": 203
+    },
+    {
+      "epoch": 1.1731843575418994,
+      "grad_norm": 15.53803825378418,
+      "learning_rate": 3.4368530020703935e-05,
+      "loss": 0.5809,
+      "step": 210
+    },
+    {
+      "epoch": 1.2122905027932962,
+      "grad_norm": 17.502534866333008,
+      "learning_rate": 3.364389233954452e-05,
+      "loss": 0.5119,
+      "step": 217
+    },
+    {
+      "epoch": 1.2513966480446927,
+      "grad_norm": 20.31743621826172,
+      "learning_rate": 3.29192546583851e-05,
+      "loss": 0.5289,
+      "step": 224
+    },
+    {
+      "epoch": 1.2905027932960893,
+      "grad_norm": 46.659828186035156,
+      "learning_rate": 3.2194616977225674e-05,
+      "loss": 0.6035,
+      "step": 231
+    },
+    {
+      "epoch": 1.329608938547486,
+      "grad_norm": 20.15818214416504,
+      "learning_rate": 3.1469979296066256e-05,
+      "loss": 0.5148,
+      "step": 238
+    },
+    {
+      "epoch": 1.3687150837988826,
+      "grad_norm": 6.627427101135254,
+      "learning_rate": 3.074534161490684e-05,
+      "loss": 0.5968,
+      "step": 245
+    },
+    {
+      "epoch": 1.4078212290502794,
+      "grad_norm": 11.544679641723633,
+      "learning_rate": 3.0020703933747414e-05,
+      "loss": 0.2539,
+      "step": 252
+    },
+    {
+      "epoch": 1.446927374301676,
+      "grad_norm": 4.748214244842529,
+      "learning_rate": 2.9296066252587996e-05,
+      "loss": 0.4293,
+      "step": 259
+    },
+    {
+      "epoch": 1.4860335195530725,
+      "grad_norm": 28.907987594604492,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.5849,
+      "step": 266
+    },
+    {
+      "epoch": 1.5251396648044693,
+      "grad_norm": 12.41960334777832,
+      "learning_rate": 2.7846790890269153e-05,
+      "loss": 0.4464,
+      "step": 273
+    },
+    {
+      "epoch": 1.564245810055866,
+      "grad_norm": 22.844667434692383,
+      "learning_rate": 2.7122153209109728e-05,
+      "loss": 0.514,
+      "step": 280
+    },
+    {
+      "epoch": 1.6033519553072626,
+      "grad_norm": 16.901336669921875,
+      "learning_rate": 2.639751552795031e-05,
+      "loss": 0.4497,
+      "step": 287
+    },
+    {
+      "epoch": 1.6424581005586592,
+      "grad_norm": 23.846860885620117,
+      "learning_rate": 2.5672877846790892e-05,
+      "loss": 0.5861,
+      "step": 294
+    },
+    {
+      "epoch": 1.6815642458100557,
+      "grad_norm": 28.805133819580078,
+      "learning_rate": 2.494824016563147e-05,
+      "loss": 0.4996,
+      "step": 301
+    },
+    {
+      "epoch": 1.7206703910614525,
+      "grad_norm": 12.11324405670166,
+      "learning_rate": 2.4223602484472053e-05,
+      "loss": 0.487,
+      "step": 308
+    },
+    {
+      "epoch": 1.7597765363128492,
+      "grad_norm": 12.710243225097656,
+      "learning_rate": 2.349896480331263e-05,
+      "loss": 0.62,
+      "step": 315
+    },
+    {
+      "epoch": 1.7988826815642458,
+      "grad_norm": 16.51240348815918,
+      "learning_rate": 2.277432712215321e-05,
+      "loss": 0.3526,
+      "step": 322
+    },
+    {
+      "epoch": 1.8379888268156424,
+      "grad_norm": 13.733351707458496,
+      "learning_rate": 2.204968944099379e-05,
+      "loss": 0.3458,
+      "step": 329
+    },
+    {
+      "epoch": 1.8770949720670391,
+      "grad_norm": 6.4348344802856445,
+      "learning_rate": 2.1325051759834367e-05,
+      "loss": 0.3579,
+      "step": 336
+    },
+    {
+      "epoch": 1.916201117318436,
+      "grad_norm": 8.98593521118164,
+      "learning_rate": 2.060041407867495e-05,
+      "loss": 0.4135,
+      "step": 343
+    },
+    {
+      "epoch": 1.9553072625698324,
+      "grad_norm": 6.583544731140137,
+      "learning_rate": 1.9875776397515528e-05,
+      "loss": 0.2938,
+      "step": 350
+    },
+    {
+      "epoch": 1.994413407821229,
+      "grad_norm": 30.63981819152832,
+      "learning_rate": 1.915113871635611e-05,
+      "loss": 0.6931,
+      "step": 357
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_f1_macro": 0.7679742314070671,
+      "eval_f1_micro": 0.7777777777777778,
+      "eval_f1_weighted": 0.7707658289747842,
+      "eval_loss": 0.5543721318244934,
+      "eval_precision_macro": 0.7848406546080966,
+      "eval_precision_micro": 0.7777777777777778,
+      "eval_precision_weighted": 0.7778696525983347,
+      "eval_recall_macro": 0.7620894891084323,
+      "eval_recall_micro": 0.7777777777777778,
+      "eval_recall_weighted": 0.7777777777777778,
+      "eval_runtime": 0.8305,
+      "eval_samples_per_second": 379.305,
+      "eval_steps_per_second": 24.083,
+      "step": 358
+    }
+  ],
+  "logging_steps": 7,
+  "max_steps": 537,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 188389207093248.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-358/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4da452457ed00503c13dba9d376a486337df1bca4546c2e0622ebf2467c596c
+size 5048

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "oliverguhr/german-sentiment-bert",
+  "_num_labels": 3,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "germansentiment",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa35e386bcb6d05883882a045e9e5520d3b382d42a52bcb68d41f4cb4628cbc8
+size 436358132

runs/May09_20-59-32_r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu/events.out.tfevents.1715288373.r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu.61.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5d5e5e69c4dd45f4289eb6ace3421218512d772d922e390b64852b614e2e48b
-size 4905
+oid sha256:98c7f099faa3940d9838c53e0579978a9e24c6721860d20261a6dd0c54b359e7
+size 23722

runs/May09_20-59-32_r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu/events.out.tfevents.1715288436.r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu.61.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84172fd3c087028fd34a2456801eb2dda1c2f90effe4931f01366a61294b25a
+size 921

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "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]",
+  "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:b4da452457ed00503c13dba9d376a486337df1bca4546c2e0622ebf2467c596c
+size 5048

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "autotrain-df1770/autotrain-data",
+    "model": "oliverguhr/german-sentiment-bert",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "autotrain-df1770",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "Zerithas",
+    "log": "tensorboard"
+}