Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- GeoBert-v99/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.9684362411499023
+
+f1_macro: 0.3717510031517435
+
+f1_micro: 0.6171548117154811
+
+f1_weighted: 0.5667452948322756
+
+precision_macro: 0.7171713517359477
+
+precision_micro: 0.6171548117154811
+
+precision_weighted: 0.6710608475463727
+
+recall_macro: 0.39586606053896595
+
+recall_micro: 0.6171548117154811
+
+recall_weighted: 0.6171548117154811
+
+accuracy: 0.6171548117154811

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

checkpoint-500/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "MoritzLaurer/deberta-v3-large-zeroshot-v2.0",
+  "_num_labels": 4,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e96ad72c5f99aea04caa19477ce4b13adceb1dc8d4c2ac2085bae09d44d25c1
+size 1740312648

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03b6205de18b89a5b8cb53464724f1df9adc4849d933e2560319a66eb48f40e
+size 3480856624

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae71559db441d93c81e219693425b26d9c4508f15d0ce7c24fd04daf8817a6b
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e287e607f659e585c1aac9383187ae627ebb501de6ca85dc67ba0dd1f271713
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,372 @@
+{
+  "best_metric": 0.9684362411499023,
+  "best_model_checkpoint": "GeoBert-v99/checkpoint-500",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044,
+      "grad_norm": 9.120949745178223,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.3883,
+      "step": 11
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 8.59699821472168,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 1.2143,
+      "step": 22
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 5.048985481262207,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 1.2137,
+      "step": 33
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 4.359477519989014,
+      "learning_rate": 1.7199999999999998e-05,
+      "loss": 1.0919,
+      "step": 44
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 11.259472846984863,
+      "learning_rate": 2.16e-05,
+      "loss": 0.9772,
+      "step": 55
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 6.3205742835998535,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.9886,
+      "step": 66
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 4.882684707641602,
+      "learning_rate": 3.04e-05,
+      "loss": 1.0988,
+      "step": 77
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 8.879051208496094,
+      "learning_rate": 3.48e-05,
+      "loss": 1.2254,
+      "step": 88
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 8.254974365234375,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 1.0403,
+      "step": 99
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.678905487060547,
+      "learning_rate": 4.36e-05,
+      "loss": 1.0453,
+      "step": 110
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 3.1227095127105713,
+      "learning_rate": 4.8e-05,
+      "loss": 0.969,
+      "step": 121
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 7.453991889953613,
+      "learning_rate": 4.973333333333334e-05,
+      "loss": 1.0525,
+      "step": 132
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 3.7758021354675293,
+      "learning_rate": 4.924444444444445e-05,
+      "loss": 0.8685,
+      "step": 143
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 4.926486015319824,
+      "learning_rate": 4.875555555555556e-05,
+      "loss": 1.021,
+      "step": 154
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 6.476828575134277,
+      "learning_rate": 4.826666666666667e-05,
+      "loss": 1.1108,
+      "step": 165
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 4.90401029586792,
+      "learning_rate": 4.7777777777777784e-05,
+      "loss": 1.1262,
+      "step": 176
+    },
+    {
+      "epoch": 0.748,
+      "grad_norm": 4.311936855316162,
+      "learning_rate": 4.728888888888889e-05,
+      "loss": 1.0333,
+      "step": 187
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 7.447878837585449,
+      "learning_rate": 4.6800000000000006e-05,
+      "loss": 1.0441,
+      "step": 198
+    },
+    {
+      "epoch": 0.836,
+      "grad_norm": 16.409482955932617,
+      "learning_rate": 4.6311111111111113e-05,
+      "loss": 1.0684,
+      "step": 209
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.9251773357391357,
+      "learning_rate": 4.582222222222222e-05,
+      "loss": 1.1385,
+      "step": 220
+    },
+    {
+      "epoch": 0.924,
+      "grad_norm": 10.975476264953613,
+      "learning_rate": 4.5333333333333335e-05,
+      "loss": 1.0061,
+      "step": 231
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 3.9190518856048584,
+      "learning_rate": 4.484444444444444e-05,
+      "loss": 1.0152,
+      "step": 242
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5523012552301255,
+      "eval_f1_macro": 0.30835553822490847,
+      "eval_f1_micro": 0.5523012552301255,
+      "eval_f1_weighted": 0.5083570066165547,
+      "eval_loss": 1.0527703762054443,
+      "eval_precision_macro": 0.3058277267127831,
+      "eval_precision_micro": 0.5523012552301255,
+      "eval_precision_weighted": 0.5337778188359454,
+      "eval_recall_macro": 0.36287925605485416,
+      "eval_recall_micro": 0.5523012552301255,
+      "eval_recall_weighted": 0.5523012552301255,
+      "eval_runtime": 11.825,
+      "eval_samples_per_second": 40.423,
+      "eval_steps_per_second": 2.537,
+      "step": 250
+    },
+    {
+      "epoch": 1.012,
+      "grad_norm": 5.0201096534729,
+      "learning_rate": 4.435555555555556e-05,
+      "loss": 1.0795,
+      "step": 253
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 3.410573959350586,
+      "learning_rate": 4.3866666666666665e-05,
+      "loss": 0.9942,
+      "step": 264
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 5.521871089935303,
+      "learning_rate": 4.337777777777778e-05,
+      "loss": 1.0161,
+      "step": 275
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 4.084682941436768,
+      "learning_rate": 4.2888888888888886e-05,
+      "loss": 1.1293,
+      "step": 286
+    },
+    {
+      "epoch": 1.188,
+      "grad_norm": 3.9275074005126953,
+      "learning_rate": 4.24e-05,
+      "loss": 1.014,
+      "step": 297
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 5.21203088760376,
+      "learning_rate": 4.1911111111111115e-05,
+      "loss": 1.0245,
+      "step": 308
+    },
+    {
+      "epoch": 1.276,
+      "grad_norm": 5.1290178298950195,
+      "learning_rate": 4.142222222222222e-05,
+      "loss": 1.0086,
+      "step": 319
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 10.097797393798828,
+      "learning_rate": 4.093333333333334e-05,
+      "loss": 0.9484,
+      "step": 330
+    },
+    {
+      "epoch": 1.3639999999999999,
+      "grad_norm": 6.209000110626221,
+      "learning_rate": 4.0444444444444444e-05,
+      "loss": 0.9501,
+      "step": 341
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 10.992793083190918,
+      "learning_rate": 3.995555555555556e-05,
+      "loss": 0.9395,
+      "step": 352
+    },
+    {
+      "epoch": 1.452,
+      "grad_norm": Infinity,
+      "learning_rate": 3.951111111111112e-05,
+      "loss": 0.8798,
+      "step": 363
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 3.217618942260742,
+      "learning_rate": 3.9022222222222225e-05,
+      "loss": 0.8513,
+      "step": 374
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 16.073089599609375,
+      "learning_rate": 3.853333333333334e-05,
+      "loss": 0.7959,
+      "step": 385
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 6.815459251403809,
+      "learning_rate": 3.804444444444445e-05,
+      "loss": 0.863,
+      "step": 396
+    },
+    {
+      "epoch": 1.6280000000000001,
+      "grad_norm": 23.98370933532715,
+      "learning_rate": 3.7555555555555554e-05,
+      "loss": 1.1277,
+      "step": 407
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 3.0591015815734863,
+      "learning_rate": 3.706666666666667e-05,
+      "loss": 0.7982,
+      "step": 418
+    },
+    {
+      "epoch": 1.716,
+      "grad_norm": 7.592540740966797,
+      "learning_rate": 3.6577777777777776e-05,
+      "loss": 1.0458,
+      "step": 429
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 6.782195568084717,
+      "learning_rate": 3.608888888888889e-05,
+      "loss": 1.0052,
+      "step": 440
+    },
+    {
+      "epoch": 1.804,
+      "grad_norm": 14.11833667755127,
+      "learning_rate": 3.56e-05,
+      "loss": 0.9708,
+      "step": 451
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 7.396513938903809,
+      "learning_rate": 3.511111111111111e-05,
+      "loss": 0.8951,
+      "step": 462
+    },
+    {
+      "epoch": 1.892,
+      "grad_norm": 30.197269439697266,
+      "learning_rate": 3.462222222222222e-05,
+      "loss": 0.8362,
+      "step": 473
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 5.634238243103027,
+      "learning_rate": 3.4133333333333334e-05,
+      "loss": 1.0819,
+      "step": 484
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 6.667699813842773,
+      "learning_rate": 3.364444444444445e-05,
+      "loss": 0.7989,
+      "step": 495
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6171548117154811,
+      "eval_f1_macro": 0.3717510031517435,
+      "eval_f1_micro": 0.6171548117154811,
+      "eval_f1_weighted": 0.5667452948322756,
+      "eval_loss": 0.9684362411499023,
+      "eval_precision_macro": 0.7171713517359477,
+      "eval_precision_micro": 0.6171548117154811,
+      "eval_precision_weighted": 0.6710608475463727,
+      "eval_recall_macro": 0.39586606053896595,
+      "eval_recall_micro": 0.6171548117154811,
+      "eval_recall_weighted": 0.6171548117154811,
+      "eval_runtime": 11.824,
+      "eval_samples_per_second": 40.426,
+      "eval_steps_per_second": 2.537,
+      "step": 500
+    }
+  ],
+  "logging_steps": 11,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3725911921631232.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48eec2c685bebfd3ceddda03d0e60ddf9dc536d4edc187c88e8824be548ab5a
+size 4984

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "MoritzLaurer/deberta-v3-large-zeroshot-v2.0",
+  "_num_labels": 4,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e96ad72c5f99aea04caa19477ce4b13adceb1dc8d4c2ac2085bae09d44d25c1
+size 1740312648

runs/Apr24_09-17-52_r-luukschmitz-ggg-0s40bivo-e3d80-lkihm/events.out.tfevents.1713950272.r-luukschmitz-ggg-0s40bivo-e3d80-lkihm.149.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c488de7d17f2322f0615c9384979e637cad97d899ab0554d60967e8d12b5fdb6
-size 22324
+oid sha256:94af033313e0238966ea8469ac7775457a6f611550011d29568e8a6a765c57f2
+size 33417

runs/Apr24_09-17-52_r-luukschmitz-ggg-0s40bivo-e3d80-lkihm/events.out.tfevents.1713951267.r-luukschmitz-ggg-0s40bivo-e3d80-lkihm.149.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250026756c8f0390c1972c0749ad1590608ff86aa8687eb62d2436db955d87f6
+size 921

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48eec2c685bebfd3ceddda03d0e60ddf9dc536d4edc187c88e8824be548ab5a
+size 4984

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "GeoBert-v99/autotrain-data",
+    "model": "MoritzLaurer/deberta-v3-large-zeroshot-v2.0",
+    "lr": 5e-05,
+    "epochs": 5,
+    "max_seq_length": 512,
+    "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": "GeoBert-v99",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "push_to_hub": true,
+    "repo_id": "luukschmitz/GeoBert-v99",
+    "evaluation_strategy": "epoch",
+    "username": "luukschmitz",
+    "log": "tensorboard"
+}