uvegesistvan commited on Jun 20, 2025

Commit

6fe491e

verified ·

1 Parent(s): d98d7d9

Upload folder using huggingface_hub

Browse files

Files changed (25) hide show

.gitattributes +6 -0
PL_augmented_100_train.xlsx +3 -0
PL_augmented_100_validation.xlsx +0 -0
PL_augmented_10_train.xlsx +3 -0
PL_augmented_10_validation.xlsx +0 -0
PL_augmented_25_train.xlsx +3 -0
PL_augmented_25_validation.xlsx +0 -0
PL_augmented_5_train.xlsx +3 -0
PL_augmented_5_validation.xlsx +0 -0
XLM-RoBERTa_large_Plain_predictions.xlsx +0 -0
checkpoint-4056/config.json +28 -0
checkpoint-4056/model.safetensors +3 -0
checkpoint-4056/optimizer.pt +3 -0
checkpoint-4056/rng_state.pth +3 -0
checkpoint-4056/scheduler.pt +3 -0
checkpoint-4056/trainer_state.json +195 -0
checkpoint-4056/training_args.bin +3 -0
config.json +28 -0
model.safetensors +3 -0
test.xlsx +3 -0
test_dataset.xlsx +0 -0
train_dataset.xlsx +3 -0
training_args.bin +3 -0
val_dataset.xlsx +0 -0
xlm-roberta-large_predictions.xlsx +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+PL_augmented_100_train.xlsx filter=lfs diff=lfs merge=lfs -text
+PL_augmented_10_train.xlsx filter=lfs diff=lfs merge=lfs -text
+PL_augmented_25_train.xlsx filter=lfs diff=lfs merge=lfs -text
+PL_augmented_5_train.xlsx filter=lfs diff=lfs merge=lfs -text
+test.xlsx filter=lfs diff=lfs merge=lfs -text
+train_dataset.xlsx filter=lfs diff=lfs merge=lfs -text

PL_augmented_100_train.xlsx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5042d64ea1adcbce28c1460bf705f6d75906e9323f181df3248fdc46bf0aeec4
+size 619017

PL_augmented_100_validation.xlsx ADDED Viewed

Binary file (94.5 kB). View file

PL_augmented_10_train.xlsx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c35e51e76dca0aa7ffb8abd530f65b56b5f012601e9e086625fa2b288cf947dd
+size 564079

PL_augmented_10_validation.xlsx ADDED Viewed

Binary file (82.2 kB). View file

PL_augmented_25_train.xlsx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:849a27540ba2bf8ed3070b088bb83f44f597d174c80b720fb120917c4dccb68d
+size 572219

PL_augmented_25_validation.xlsx ADDED Viewed

Binary file (84.6 kB). View file

PL_augmented_5_train.xlsx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ae17901a95916cf8c6a8400f70b971c7fe90bc225904d710c3e61d81a05c6c
+size 561105

PL_augmented_5_validation.xlsx ADDED Viewed

Binary file (82 kB). View file

XLM-RoBERTa_large_Plain_predictions.xlsx ADDED Viewed

Binary file (99.7 kB). View file

checkpoint-4056/config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-4056/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b119900965cd09d2d4a86a32e9aaa4dfb5a289a89531741cc6d1e051738e6958
+size 2239618672

checkpoint-4056/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:51bf7c6cdf7624ffb70ce5ce0bfd5c8402e186fd1e48655529985ad799989b4f
+size 4479472785

checkpoint-4056/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6c28a2b96cba4cd211071bccf89a6633102eb380e2660a39fa9571ed5ae1d735
+size 14244

checkpoint-4056/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8077df19a23d8db0075c1144f6976a13f484a513bf4807f4a804456418a2bd16
+size 1064

checkpoint-4056/trainer_state.json ADDED Viewed

	@@ -0,0 +1,195 @@

+{
+  "best_global_step": 4056,
+  "best_metric": 0.5722504258155823,
+  "best_model_checkpoint": "/content/drive/MyDrive/modeling_data/checkpoint-4056",
+  "epoch": 8.0,
+  "eval_steps": 100,
+  "global_step": 4056,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 126.80809020996094,
+      "learning_rate": 4.500986193293886e-06,
+      "loss": 0.7009,
+      "step": 507
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5757290686735654,
+      "eval_f1": 0.6522744795682344,
+      "eval_loss": 0.68278568983078,
+      "eval_precision": 0.6060171919770774,
+      "eval_recall": 0.7061769616026711,
+      "eval_runtime": 22.1627,
+      "eval_samples_per_second": 47.963,
+      "eval_steps_per_second": 3.023,
+      "step": 507
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 50.67797088623047,
+      "learning_rate": 4.000986193293886e-06,
+      "loss": 0.6876,
+      "step": 1014
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5738476011288806,
+      "eval_f1": 0.7215734480639213,
+      "eval_loss": 0.6826612949371338,
+      "eval_precision": 0.5710116731517509,
+      "eval_recall": 0.9799666110183639,
+      "eval_runtime": 21.7537,
+      "eval_samples_per_second": 48.865,
+      "eval_steps_per_second": 3.08,
+      "step": 1014
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 13.058858871459961,
+      "learning_rate": 3.500986193293886e-06,
+      "loss": 0.6913,
+      "step": 1521
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5644402634054563,
+      "eval_f1": 0.7212522576760987,
+      "eval_loss": 0.6816943883895874,
+      "eval_precision": 0.564030131826742,
+      "eval_recall": 1.0,
+      "eval_runtime": 21.7794,
+      "eval_samples_per_second": 48.808,
+      "eval_steps_per_second": 3.076,
+      "step": 1521
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.942716598510742,
+      "learning_rate": 3.000986193293886e-06,
+      "loss": 0.6912,
+      "step": 2028
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6086547507055503,
+      "eval_f1": 0.7011494252873564,
+      "eval_loss": 0.6769229173660278,
+      "eval_precision": 0.6153846153846154,
+      "eval_recall": 0.8146911519198664,
+      "eval_runtime": 21.7612,
+      "eval_samples_per_second": 48.848,
+      "eval_steps_per_second": 3.079,
+      "step": 2028
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 24.372453689575195,
+      "learning_rate": 2.5009861932938858e-06,
+      "loss": 0.6505,
+      "step": 2535
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6472248353715898,
+      "eval_f1": 0.6851385390428212,
+      "eval_loss": 0.6314842104911804,
+      "eval_precision": 0.6891891891891891,
+      "eval_recall": 0.6811352253756261,
+      "eval_runtime": 21.7741,
+      "eval_samples_per_second": 48.819,
+      "eval_steps_per_second": 3.077,
+      "step": 2535
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 104.81901550292969,
+      "learning_rate": 2.0009861932938855e-06,
+      "loss": 0.5952,
+      "step": 3042
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6820319849482597,
+      "eval_f1": 0.7045454545454546,
+      "eval_loss": 0.6093751192092896,
+      "eval_precision": 0.7394495412844037,
+      "eval_recall": 0.672787979966611,
+      "eval_runtime": 21.9051,
+      "eval_samples_per_second": 48.528,
+      "eval_steps_per_second": 3.059,
+      "step": 3042
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 57.38035202026367,
+      "learning_rate": 1.5009861932938858e-06,
+      "loss": 0.5533,
+      "step": 3549
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6999059266227657,
+      "eval_f1": 0.7387387387387387,
+      "eval_loss": 0.5739162564277649,
+      "eval_precision": 0.72508038585209,
+      "eval_recall": 0.7529215358931552,
+      "eval_runtime": 21.7462,
+      "eval_samples_per_second": 48.882,
+      "eval_steps_per_second": 3.081,
+      "step": 3549
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 24.121244430541992,
+      "learning_rate": 1.0009861932938857e-06,
+      "loss": 0.5255,
+      "step": 4056
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6999059266227657,
+      "eval_f1": 0.7242869490060502,
+      "eval_loss": 0.5722504258155823,
+      "eval_precision": 0.7508960573476703,
+      "eval_recall": 0.6994991652754591,
+      "eval_runtime": 22.6494,
+      "eval_samples_per_second": 46.933,
+      "eval_steps_per_second": 2.958,
+      "step": 4056
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.038169689274778e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4056/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef18b36dc40694b1fb933f2cf0b5dc9b5d01bbf66e05c7f6cebe9771f19cb0f
+size 5240

config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b119900965cd09d2d4a86a32e9aaa4dfb5a289a89531741cc6d1e051738e6958
+size 2239618672

test.xlsx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:62b2e0f7a95ffcc92d1f8020d493e3990763ad4b4936da8a89a5e9c7afc2bc11
+size 834983

test_dataset.xlsx ADDED Viewed

Binary file (81.1 kB). View file

train_dataset.xlsx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f78f961c46f193176e10b6c123a1180005c0e9981368636550e9a15278ebb4b1
+size 561225

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef18b36dc40694b1fb933f2cf0b5dc9b5d01bbf66e05c7f6cebe9771f19cb0f
+size 5240

val_dataset.xlsx ADDED Viewed

Binary file (81.4 kB). View file

xlm-roberta-large_predictions.xlsx ADDED Viewed

Binary file (94 kB). View file