Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- autotrain-df-1000/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.7126067876815796
+
+f1_macro: 0.4477682811016144
+
+f1_micro: 0.685
+
+f1_weighted: 0.6707122507122506
+
+precision_macro: 0.47539682539682543
+
+precision_micro: 0.685
+
+precision_weighted: 0.7070714285714286
+
+recall_macro: 0.45445658036677455
+
+recall_micro: 0.685
+
+recall_weighted: 0.685
+
+accuracy: 0.685

checkpoint-100/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-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:184d67361c023aacb18a503fc081e674bec355b386c3896a4a95292a7906881f
+size 436358132

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11045affabb381aa6baa33b3e27805eed586d959d7040653982530981b7eafd
+size 872837370

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4811897f7bdb295f63817a49880dea0c54680952bd8c941c2cc428a0ee303210
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f4152fd574fabc2bd324c9539ff61a96b4f4ac89c81e8a13e7bacc3f15c4cf
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.7126067876815796,
+  "best_model_checkpoint": "autotrain-df-1000/checkpoint-100",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 54.78703308105469,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.1531,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 76.31970977783203,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 2.8551,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 40.00764083862305,
+      "learning_rate": 1.2e-05,
+      "loss": 2.384,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 28.42409324645996,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 1.4925,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 55.30701446533203,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.146,
+      "step": 25
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 43.73154830932617,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.973,
+      "step": 30
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 12.502547264099121,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.9347,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 9.767241477966309,
+      "learning_rate": 3.7e-05,
+      "loss": 0.6364,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 23.53659439086914,
+      "learning_rate": 4.2e-05,
+      "loss": 0.7147,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 10.964140892028809,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5756,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 18.788103103637695,
+      "learning_rate": 4.977777777777778e-05,
+      "loss": 0.5457,
+      "step": 55
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 20.568147659301758,
+      "learning_rate": 4.922222222222222e-05,
+      "loss": 0.5995,
+      "step": 60
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 24.061555862426758,
+      "learning_rate": 4.866666666666667e-05,
+      "loss": 0.6308,
+      "step": 65
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 13.831650733947754,
+      "learning_rate": 4.811111111111111e-05,
+      "loss": 0.6019,
+      "step": 70
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 6.616458892822266,
+      "learning_rate": 4.755555555555556e-05,
+      "loss": 0.4697,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 31.620847702026367,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3965,
+      "step": 80
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 20.271053314208984,
+      "learning_rate": 4.644444444444445e-05,
+      "loss": 0.5298,
+      "step": 85
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 17.555654525756836,
+      "learning_rate": 4.588888888888889e-05,
+      "loss": 0.8049,
+      "step": 90
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": Infinity,
+      "learning_rate": 4.5444444444444444e-05,
+      "loss": 0.8184,
+      "step": 95
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.824897766113281,
+      "learning_rate": 4.4888888888888894e-05,
+      "loss": 1.0717,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.685,
+      "eval_f1_macro": 0.4477682811016144,
+      "eval_f1_micro": 0.685,
+      "eval_f1_weighted": 0.6707122507122506,
+      "eval_loss": 0.7126067876815796,
+      "eval_precision_macro": 0.47539682539682543,
+      "eval_precision_micro": 0.685,
+      "eval_precision_weighted": 0.7070714285714286,
+      "eval_recall_macro": 0.45445658036677455,
+      "eval_recall_micro": 0.685,
+      "eval_recall_weighted": 0.685,
+      "eval_runtime": 0.5369,
+      "eval_samples_per_second": 372.54,
+      "eval_steps_per_second": 24.215,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 52622683545600.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3db12c93cb1810f4ff6a15a379f10f7e6a18189f73ac9ead64b10c6fa8fe19
+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 sha256:184d67361c023aacb18a503fc081e674bec355b386c3896a4a95292a7906881f
+size 436358132

runs/May11_09-00-31_r-zerithas-myownmodels-v1-249bpdw0-f95cc-evbm8/events.out.tfevents.1715418032.r-zerithas-myownmodels-v1-249bpdw0-f95cc-evbm8.66.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cfc5628863fe5366a73427e7949ab14cfcd7455fcc3a0ee6141bbc0c022b65e
-size 4908
+oid sha256:c1dd996d78dacd6786a45df5eb7085b0e04a0b3c83ca7fa349c9ff381cf0659e
+size 25359

runs/May11_09-00-31_r-zerithas-myownmodels-v1-249bpdw0-f95cc-evbm8/events.out.tfevents.1715418084.r-zerithas-myownmodels-v1-249bpdw0-f95cc-evbm8.66.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50fb64e05b88ddccdda87e811371bb0b6329018c1293449741d3fcc64d5a9601
+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:ea3db12c93cb1810f4ff6a15a379f10f7e6a18189f73ac9ead64b10c6fa8fe19
+size 5048

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "autotrain-df-1000/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-df-1000",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "Zerithas",
+    "log": "tensorboard"
+}