Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- geotrain-final/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.9777308702468872
+
+f1_macro: 0.5687536311381957
+
+f1_micro: 0.6317991631799164
+
+f1_weighted: 0.6338876929966345
+
+precision_macro: 0.6188229771753799
+
+precision_micro: 0.6317991631799164
+
+precision_weighted: 0.6676941440515829
+
+recall_macro: 0.570025126085866
+
+recall_micro: 0.6317991631799164
+
+recall_weighted: 0.6317991631799164
+
+accuracy: 0.6317991631799164

checkpoint-500/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_num_labels": 4,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee757bbefa963f7c8cc04b0125973a7d1fb7b58aecb024f6f902b08b66c6f587
+size 498618976

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828d09542cf2ec1fba127e354850a41ca4280d3ca82e9264dc2d9426a611475a
+size 997357818

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f131c06f59ad91f627a5655473001184f55b5ed02600ba83edb76cb196471cf8
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c133e7e2d9c3eba5443128ed31a095ddedda08531ab3529dc1ebcbbdb9546f
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,372 @@
+{
+  "best_metric": 0.9777308702468872,
+  "best_model_checkpoint": "geotrain-final/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": 0.04,
+      "grad_norm": 5.933391571044922,
+      "learning_rate": 4.4e-06,
+      "loss": 1.4171,
+      "step": 11
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 5.440005302429199,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3601,
+      "step": 22
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.915931463241577,
+      "learning_rate": 1.32e-05,
+      "loss": 1.2749,
+      "step": 33
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 9.6021728515625,
+      "learning_rate": 1.76e-05,
+      "loss": 1.1684,
+      "step": 44
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 8.488694190979004,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.0029,
+      "step": 55
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 8.59380054473877,
+      "learning_rate": 2.5600000000000002e-05,
+      "loss": 1.0009,
+      "step": 66
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.843475818634033,
+      "learning_rate": 3e-05,
+      "loss": 1.1119,
+      "step": 77
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 14.342958450317383,
+      "learning_rate": 3.4399999999999996e-05,
+      "loss": 1.1722,
+      "step": 88
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 9.782418251037598,
+      "learning_rate": 3.88e-05,
+      "loss": 1.0234,
+      "step": 99
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.94428014755249,
+      "learning_rate": 4.32e-05,
+      "loss": 1.033,
+      "step": 110
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 9.49178409576416,
+      "learning_rate": 4.76e-05,
+      "loss": 0.9003,
+      "step": 121
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 6.47744083404541,
+      "learning_rate": 4.977777777777778e-05,
+      "loss": 0.9477,
+      "step": 132
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 5.685667514801025,
+      "learning_rate": 4.928888888888889e-05,
+      "loss": 0.9732,
+      "step": 143
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 7.3716721534729,
+      "learning_rate": 4.88e-05,
+      "loss": 1.0821,
+      "step": 154
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 30.543617248535156,
+      "learning_rate": 4.8311111111111115e-05,
+      "loss": 1.1229,
+      "step": 165
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 10.218334197998047,
+      "learning_rate": 4.7866666666666674e-05,
+      "loss": 1.0504,
+      "step": 176
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 18.54749870300293,
+      "learning_rate": 4.7422222222222226e-05,
+      "loss": 0.9134,
+      "step": 187
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 9.140128135681152,
+      "learning_rate": 4.6933333333333333e-05,
+      "loss": 1.0257,
+      "step": 198
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 23.933828353881836,
+      "learning_rate": 4.644444444444445e-05,
+      "loss": 1.0076,
+      "step": 209
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 13.24459171295166,
+      "learning_rate": 4.5955555555555555e-05,
+      "loss": 1.1043,
+      "step": 220
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 7.963653564453125,
+      "learning_rate": 4.546666666666667e-05,
+      "loss": 0.903,
+      "step": 231
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 23.737497329711914,
+      "learning_rate": 4.497777777777778e-05,
+      "loss": 0.8935,
+      "step": 242
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5690376569037657,
+      "eval_f1_macro": 0.31564341009786256,
+      "eval_f1_micro": 0.5690376569037657,
+      "eval_f1_weighted": 0.5208391179878019,
+      "eval_loss": 1.0426007509231567,
+      "eval_precision_macro": 0.3014274858879722,
+      "eval_precision_micro": 0.5690376569037657,
+      "eval_precision_weighted": 0.521101955426522,
+      "eval_recall_macro": 0.3682351902533769,
+      "eval_recall_micro": 0.5690376569037657,
+      "eval_recall_weighted": 0.5690376569037657,
+      "eval_runtime": 5.685,
+      "eval_samples_per_second": 84.08,
+      "eval_steps_per_second": 5.277,
+      "step": 250
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 7.589027404785156,
+      "learning_rate": 4.448888888888889e-05,
+      "loss": 1.0416,
+      "step": 253
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 8.25841236114502,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.8833,
+      "step": 264
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 21.911312103271484,
+      "learning_rate": 4.351111111111111e-05,
+      "loss": 0.896,
+      "step": 275
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 14.147982597351074,
+      "learning_rate": 4.302222222222223e-05,
+      "loss": 0.8851,
+      "step": 286
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 7.773700714111328,
+      "learning_rate": 4.2533333333333335e-05,
+      "loss": 0.7532,
+      "step": 297
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 12.937735557556152,
+      "learning_rate": 4.204444444444445e-05,
+      "loss": 0.8913,
+      "step": 308
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 11.531375885009766,
+      "learning_rate": 4.155555555555556e-05,
+      "loss": 0.9013,
+      "step": 319
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 27.248319625854492,
+      "learning_rate": 4.106666666666667e-05,
+      "loss": 0.8177,
+      "step": 330
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 4.805572509765625,
+      "learning_rate": 4.057777777777778e-05,
+      "loss": 0.6482,
+      "step": 341
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 6.928028106689453,
+      "learning_rate": 4.008888888888889e-05,
+      "loss": 0.8228,
+      "step": 352
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 9.062151908874512,
+      "learning_rate": 3.960000000000001e-05,
+      "loss": 0.6904,
+      "step": 363
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 8.66677188873291,
+      "learning_rate": 3.9111111111111115e-05,
+      "loss": 0.674,
+      "step": 374
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 23.796768188476562,
+      "learning_rate": 3.862222222222223e-05,
+      "loss": 0.8199,
+      "step": 385
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 23.471160888671875,
+      "learning_rate": 3.8133333333333336e-05,
+      "loss": 0.6972,
+      "step": 396
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 22.039318084716797,
+      "learning_rate": 3.764444444444445e-05,
+      "loss": 0.7157,
+      "step": 407
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 8.368902206420898,
+      "learning_rate": 3.715555555555555e-05,
+      "loss": 0.5485,
+      "step": 418
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 74.74139404296875,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.9077,
+      "step": 429
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 13.330643653869629,
+      "learning_rate": 3.617777777777778e-05,
+      "loss": 0.6749,
+      "step": 440
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 20.54056167602539,
+      "learning_rate": 3.568888888888889e-05,
+      "loss": 0.8685,
+      "step": 451
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 23.1694393157959,
+      "learning_rate": 3.52e-05,
+      "loss": 0.68,
+      "step": 462
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 9.058493614196777,
+      "learning_rate": 3.471111111111111e-05,
+      "loss": 0.72,
+      "step": 473
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 15.88407039642334,
+      "learning_rate": 3.4222222222222224e-05,
+      "loss": 0.7689,
+      "step": 484
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 12.588656425476074,
+      "learning_rate": 3.373333333333333e-05,
+      "loss": 0.6218,
+      "step": 495
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6317991631799164,
+      "eval_f1_macro": 0.5687536311381957,
+      "eval_f1_micro": 0.6317991631799164,
+      "eval_f1_weighted": 0.6338876929966345,
+      "eval_loss": 0.9777308702468872,
+      "eval_precision_macro": 0.6188229771753799,
+      "eval_precision_micro": 0.6317991631799164,
+      "eval_precision_weighted": 0.6676941440515829,
+      "eval_recall_macro": 0.570025126085866,
+      "eval_recall_micro": 0.6317991631799164,
+      "eval_recall_weighted": 0.6317991631799164,
+      "eval_runtime": 5.8049,
+      "eval_samples_per_second": 82.344,
+      "eval_steps_per_second": 5.168,
+      "step": 500
+    }
+  ],
+  "logging_steps": 11,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 525968444411904.0,
+  "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 sha256:7351c7368774ddfdbdffbd81891c5c96c1dfde9cf862bf2cea1646475856450a
+size 4984

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_num_labels": 4,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee757bbefa963f7c8cc04b0125973a7d1fb7b58aecb024f6f902b08b66c6f587
+size 498618976

runs/Apr08_14-40-47_r-luukschmitz-geotrain-py01etai-85f32-0zq98/events.out.tfevents.1712587248.r-luukschmitz-geotrain-py01etai-85f32-0zq98.113.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676f6cbf0154ae94188998945c30e35d4608adbc9d6b0cbb55b161f1583516eb
-size 31704
+oid sha256:7bff7ada9ec95a02ba637e45b445629ddcb8c55786d43578187c56abfa5c5e16
+size 33102

runs/Apr08_14-40-47_r-luukschmitz-geotrain-py01etai-85f32-0zq98/events.out.tfevents.1712587550.r-luukschmitz-geotrain-py01etai-85f32-0zq98.113.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5561ee5c6745192759ddea7bbede99275decd2a5925a7d8005a38aa5eef3af
+size 921

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7351c7368774ddfdbdffbd81891c5c96c1dfde9cf862bf2cea1646475856450a
+size 4984

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "geotrain-final/autotrain-data",
+    "model": "FacebookAI/roberta-base",
+    "lr": 5e-05,
+    "epochs": 5,
+    "max_seq_length": 256,
+    "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": "geotrain-final",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "push_to_hub": true,
+    "repo_id": "luukschmitz/geotrain-final",
+    "evaluation_strategy": "epoch",
+    "username": "luukschmitz",
+    "log": "tensorboard"
+}