Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- autotrain-df1750/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.5988922119140625
+
+f1_macro: 0.7197485594552121
+
+f1_micro: 0.7444444444444445
+
+f1_weighted: 0.7445899540189744
+
+precision_macro: 0.8311385930760716
+
+precision_micro: 0.7444444444444445
+
+precision_weighted: 0.7729251752611423
+
+recall_macro: 0.6798505487345509
+
+recall_micro: 0.7444444444444445
+
+recall_weighted: 0.7444444444444445
+
+accuracy: 0.7444444444444445

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 sha256:24fba2b6ab75eb6802621bcdda26edaad8bb3513ace8d4f08cd25756e0317eac
+size 436358132

checkpoint-358/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d292337b8ca5fb78b7e8bc7d8b5761e43737d99405ee88bd376d1a0a415c0346
+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 sha256:4ad4a0db14e6b35369ed3a769d4643f789d6102896ccfb8b46d2a6f25646f335
+size 1064

checkpoint-358/trainer_state.json

@@ -0,0 +1,470 @@
+{
+  "best_metric": 0.5988922119140625,
+  "best_model_checkpoint": "autotrain-df1750/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": 0.0335195530726257,
+      "grad_norm": 73.59092712402344,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 2.6702,
+      "step": 6
+    },
+    {
+      "epoch": 0.0670391061452514,
+      "grad_norm": 73.304931640625,
+      "learning_rate": 4.444444444444445e-06,
+      "loss": 3.0755,
+      "step": 12
+    },
+    {
+      "epoch": 0.1005586592178771,
+      "grad_norm": 23.852195739746094,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 1.8661,
+      "step": 18
+    },
+    {
+      "epoch": 0.1340782122905028,
+      "grad_norm": 38.33709716796875,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 1.3438,
+      "step": 24
+    },
+    {
+      "epoch": 0.16759776536312848,
+      "grad_norm": 87.00068664550781,
+      "learning_rate": 1.4444444444444444e-05,
+      "loss": 1.4881,
+      "step": 30
+    },
+    {
+      "epoch": 0.2011173184357542,
+      "grad_norm": 46.23602294921875,
+      "learning_rate": 1.777777777777778e-05,
+      "loss": 1.8771,
+      "step": 36
+    },
+    {
+      "epoch": 0.2346368715083799,
+      "grad_norm": 18.535837173461914,
+      "learning_rate": 2.111111111111111e-05,
+      "loss": 1.0011,
+      "step": 42
+    },
+    {
+      "epoch": 0.2681564245810056,
+      "grad_norm": 11.598855018615723,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 1.0259,
+      "step": 48
+    },
+    {
+      "epoch": 0.3016759776536313,
+      "grad_norm": 3.8503451347351074,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.8544,
+      "step": 54
+    },
+    {
+      "epoch": 0.33519553072625696,
+      "grad_norm": 27.00203514099121,
+      "learning_rate": 3.111111111111111e-05,
+      "loss": 0.8838,
+      "step": 60
+    },
+    {
+      "epoch": 0.3687150837988827,
+      "grad_norm": 9.515172958374023,
+      "learning_rate": 3.444444444444445e-05,
+      "loss": 0.7537,
+      "step": 66
+    },
+    {
+      "epoch": 0.4022346368715084,
+      "grad_norm": 6.722465991973877,
+      "learning_rate": 3.777777777777778e-05,
+      "loss": 0.6945,
+      "step": 72
+    },
+    {
+      "epoch": 0.43575418994413406,
+      "grad_norm": 3.381333112716675,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 0.7916,
+      "step": 78
+    },
+    {
+      "epoch": 0.4692737430167598,
+      "grad_norm": 6.028005123138428,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7535,
+      "step": 84
+    },
+    {
+      "epoch": 0.5027932960893855,
+      "grad_norm": 2.521240234375,
+      "learning_rate": 4.7777777777777784e-05,
+      "loss": 0.6608,
+      "step": 90
+    },
+    {
+      "epoch": 0.5363128491620112,
+      "grad_norm": 11.346482276916504,
+      "learning_rate": 4.9875776397515526e-05,
+      "loss": 0.8989,
+      "step": 96
+    },
+    {
+      "epoch": 0.5698324022346368,
+      "grad_norm": 4.411192893981934,
+      "learning_rate": 4.9503105590062115e-05,
+      "loss": 0.6739,
+      "step": 102
+    },
+    {
+      "epoch": 0.6033519553072626,
+      "grad_norm": 7.383223533630371,
+      "learning_rate": 4.91304347826087e-05,
+      "loss": 0.6012,
+      "step": 108
+    },
+    {
+      "epoch": 0.6368715083798883,
+      "grad_norm": 22.263490676879883,
+      "learning_rate": 4.875776397515528e-05,
+      "loss": 0.6424,
+      "step": 114
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "grad_norm": 11.658171653747559,
+      "learning_rate": 4.8385093167701864e-05,
+      "loss": 0.6272,
+      "step": 120
+    },
+    {
+      "epoch": 0.7039106145251397,
+      "grad_norm": 12.783892631530762,
+      "learning_rate": 4.801242236024845e-05,
+      "loss": 0.6088,
+      "step": 126
+    },
+    {
+      "epoch": 0.7374301675977654,
+      "grad_norm": 33.83137893676758,
+      "learning_rate": 4.763975155279503e-05,
+      "loss": 0.7344,
+      "step": 132
+    },
+    {
+      "epoch": 0.770949720670391,
+      "grad_norm": 9.561176300048828,
+      "learning_rate": 4.726708074534162e-05,
+      "loss": 0.7418,
+      "step": 138
+    },
+    {
+      "epoch": 0.8044692737430168,
+      "grad_norm": 8.497224807739258,
+      "learning_rate": 4.68944099378882e-05,
+      "loss": 0.5052,
+      "step": 144
+    },
+    {
+      "epoch": 0.8379888268156425,
+      "grad_norm": 11.237218856811523,
+      "learning_rate": 4.6521739130434785e-05,
+      "loss": 0.7463,
+      "step": 150
+    },
+    {
+      "epoch": 0.8715083798882681,
+      "grad_norm": 5.342649459838867,
+      "learning_rate": 4.614906832298137e-05,
+      "loss": 0.5899,
+      "step": 156
+    },
+    {
+      "epoch": 0.9050279329608939,
+      "grad_norm": 9.221810340881348,
+      "learning_rate": 4.577639751552795e-05,
+      "loss": 0.6203,
+      "step": 162
+    },
+    {
+      "epoch": 0.9385474860335196,
+      "grad_norm": 8.265608787536621,
+      "learning_rate": 4.5403726708074534e-05,
+      "loss": 0.6055,
+      "step": 168
+    },
+    {
+      "epoch": 0.9720670391061452,
+      "grad_norm": 41.970157623291016,
+      "learning_rate": 4.5031055900621124e-05,
+      "loss": 0.76,
+      "step": 174
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6777777777777778,
+      "eval_f1_macro": 0.6235276146807568,
+      "eval_f1_micro": 0.6777777777777778,
+      "eval_f1_weighted": 0.6417678337751553,
+      "eval_loss": 0.6414533853530884,
+      "eval_precision_macro": 0.6587301587301587,
+      "eval_precision_micro": 0.6777777777777778,
+      "eval_precision_weighted": 0.7171075837742504,
+      "eval_recall_macro": 0.7109298963614522,
+      "eval_recall_micro": 0.6777777777777778,
+      "eval_recall_weighted": 0.6777777777777778,
+      "eval_runtime": 0.7181,
+      "eval_samples_per_second": 375.983,
+      "eval_steps_per_second": 23.673,
+      "step": 179
+    },
+    {
+      "epoch": 1.005586592178771,
+      "grad_norm": 19.538753509521484,
+      "learning_rate": 4.465838509316771e-05,
+      "loss": 0.6712,
+      "step": 180
+    },
+    {
+      "epoch": 1.0391061452513966,
+      "grad_norm": 3.879540205001831,
+      "learning_rate": 4.428571428571428e-05,
+      "loss": 0.5233,
+      "step": 186
+    },
+    {
+      "epoch": 1.0726256983240223,
+      "grad_norm": 3.905611515045166,
+      "learning_rate": 4.391304347826087e-05,
+      "loss": 0.5226,
+      "step": 192
+    },
+    {
+      "epoch": 1.106145251396648,
+      "grad_norm": 5.837283611297607,
+      "learning_rate": 4.3540372670807455e-05,
+      "loss": 0.5184,
+      "step": 198
+    },
+    {
+      "epoch": 1.1396648044692737,
+      "grad_norm": 13.354449272155762,
+      "learning_rate": 4.316770186335404e-05,
+      "loss": 0.4915,
+      "step": 204
+    },
+    {
+      "epoch": 1.1731843575418994,
+      "grad_norm": 14.286345481872559,
+      "learning_rate": 4.279503105590063e-05,
+      "loss": 0.6749,
+      "step": 210
+    },
+    {
+      "epoch": 1.2067039106145252,
+      "grad_norm": 18.75254249572754,
+      "learning_rate": 4.2422360248447204e-05,
+      "loss": 0.4622,
+      "step": 216
+    },
+    {
+      "epoch": 1.2402234636871508,
+      "grad_norm": 14.3436279296875,
+      "learning_rate": 4.204968944099379e-05,
+      "loss": 0.4796,
+      "step": 222
+    },
+    {
+      "epoch": 1.2737430167597765,
+      "grad_norm": 8.52850341796875,
+      "learning_rate": 4.167701863354038e-05,
+      "loss": 0.5933,
+      "step": 228
+    },
+    {
+      "epoch": 1.3072625698324023,
+      "grad_norm": 8.049199104309082,
+      "learning_rate": 4.130434782608696e-05,
+      "loss": 0.4508,
+      "step": 234
+    },
+    {
+      "epoch": 1.3407821229050279,
+      "grad_norm": 12.118001937866211,
+      "learning_rate": 4.093167701863354e-05,
+      "loss": 0.6934,
+      "step": 240
+    },
+    {
+      "epoch": 1.3743016759776536,
+      "grad_norm": 8.314793586730957,
+      "learning_rate": 4.0559006211180126e-05,
+      "loss": 0.6691,
+      "step": 246
+    },
+    {
+      "epoch": 1.4078212290502794,
+      "grad_norm": 48.661590576171875,
+      "learning_rate": 4.018633540372671e-05,
+      "loss": 0.3235,
+      "step": 252
+    },
+    {
+      "epoch": 1.441340782122905,
+      "grad_norm": 13.549777030944824,
+      "learning_rate": 3.981366459627329e-05,
+      "loss": 0.5038,
+      "step": 258
+    },
+    {
+      "epoch": 1.4748603351955307,
+      "grad_norm": 8.670489311218262,
+      "learning_rate": 3.944099378881988e-05,
+      "loss": 0.418,
+      "step": 264
+    },
+    {
+      "epoch": 1.5083798882681565,
+      "grad_norm": 31.06993865966797,
+      "learning_rate": 3.9068322981366464e-05,
+      "loss": 0.4584,
+      "step": 270
+    },
+    {
+      "epoch": 1.541899441340782,
+      "grad_norm": 10.52939510345459,
+      "learning_rate": 3.869565217391305e-05,
+      "loss": 0.5596,
+      "step": 276
+    },
+    {
+      "epoch": 1.5754189944134078,
+      "grad_norm": 12.9683198928833,
+      "learning_rate": 3.832298136645963e-05,
+      "loss": 0.4865,
+      "step": 282
+    },
+    {
+      "epoch": 1.6089385474860336,
+      "grad_norm": 8.783909797668457,
+      "learning_rate": 3.795031055900621e-05,
+      "loss": 0.5476,
+      "step": 288
+    },
+    {
+      "epoch": 1.6424581005586592,
+      "grad_norm": 18.032865524291992,
+      "learning_rate": 3.7577639751552796e-05,
+      "loss": 0.6996,
+      "step": 294
+    },
+    {
+      "epoch": 1.675977653631285,
+      "grad_norm": 5.003455638885498,
+      "learning_rate": 3.7204968944099385e-05,
+      "loss": 0.5503,
+      "step": 300
+    },
+    {
+      "epoch": 1.7094972067039107,
+      "grad_norm": 16.561975479125977,
+      "learning_rate": 3.683229813664597e-05,
+      "loss": 0.6051,
+      "step": 306
+    },
+    {
+      "epoch": 1.7430167597765363,
+      "grad_norm": 6.354936122894287,
+      "learning_rate": 3.6459627329192544e-05,
+      "loss": 0.6112,
+      "step": 312
+    },
+    {
+      "epoch": 1.776536312849162,
+      "grad_norm": 4.840208530426025,
+      "learning_rate": 3.6086956521739134e-05,
+      "loss": 0.429,
+      "step": 318
+    },
+    {
+      "epoch": 1.8100558659217878,
+      "grad_norm": 7.309473991394043,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.3584,
+      "step": 324
+    },
+    {
+      "epoch": 1.8435754189944134,
+      "grad_norm": 17.3754825592041,
+      "learning_rate": 3.53416149068323e-05,
+      "loss": 0.3328,
+      "step": 330
+    },
+    {
+      "epoch": 1.8770949720670391,
+      "grad_norm": 12.939613342285156,
+      "learning_rate": 3.496894409937889e-05,
+      "loss": 0.5574,
+      "step": 336
+    },
+    {
+      "epoch": 1.910614525139665,
+      "grad_norm": 10.317028999328613,
+      "learning_rate": 3.4596273291925466e-05,
+      "loss": 0.4618,
+      "step": 342
+    },
+    {
+      "epoch": 1.9441340782122905,
+      "grad_norm": 11.774768829345703,
+      "learning_rate": 3.422360248447205e-05,
+      "loss": 0.396,
+      "step": 348
+    },
+    {
+      "epoch": 1.9776536312849162,
+      "grad_norm": 12.681093215942383,
+      "learning_rate": 3.385093167701863e-05,
+      "loss": 0.5958,
+      "step": 354
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7444444444444445,
+      "eval_f1_macro": 0.7197485594552121,
+      "eval_f1_micro": 0.7444444444444445,
+      "eval_f1_weighted": 0.7445899540189744,
+      "eval_loss": 0.5988922119140625,
+      "eval_precision_macro": 0.8311385930760716,
+      "eval_precision_micro": 0.7444444444444445,
+      "eval_precision_weighted": 0.7729251752611423,
+      "eval_recall_macro": 0.6798505487345509,
+      "eval_recall_micro": 0.7444444444444445,
+      "eval_recall_weighted": 0.7444444444444445,
+      "eval_runtime": 0.7117,
+      "eval_samples_per_second": 379.359,
+      "eval_steps_per_second": 23.886,
+      "step": 358
+    }
+  ],
+  "logging_steps": 6,
+  "max_steps": 895,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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 sha256:31496e0cb13ad5d6cd9074a1fbc28a21d7d8aa565e741485a38edff9fdca5bec
+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 sha256:24fba2b6ab75eb6802621bcdda26edaad8bb3513ace8d4f08cd25756e0317eac
+size 436358132

runs/May09_20-25-11_r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt/events.out.tfevents.1715286311.r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt.59.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00dc6a0932535ed98df78fc6ad2c5aa0ca6aef72f90f08c20b7880f3e280fc88
-size 4905
+oid sha256:42e593421e2a92840180f23383229e6a282f4b4f12358dd8cb34b78818de9798
+size 40779

runs/May09_20-25-11_r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt/events.out.tfevents.1715286418.r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt.59.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e033d3b01be4ea96a5fc20d4c4175a8b0cc866f51bf32f7873edc795c781cf4
+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 sha256:31496e0cb13ad5d6cd9074a1fbc28a21d7d8aa565e741485a38edff9fdca5bec
+size 5048

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "autotrain-df1750/autotrain-data",
+    "model": "oliverguhr/german-sentiment-bert",
+    "lr": 5e-05,
+    "epochs": 5,
+    "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-df1750",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "Zerithas",
+    "log": "tensorboard"
+}