Upload folder using huggingface_hub

checkpoint-4452/config.json

@@ -0,0 +1,29 @@
+{
+ "_name_or_path": "xlm-roberta-base",
+ "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": 768,
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 514,
+ "model_type": "xlm-roberta",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "output_past": true,
+ "pad_token_id": 1,
+ "position_embedding_type": "absolute",
+ "problem_type": "multi_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.45.2",
+ "type_vocab_size": 1,
+ "use_cache": true,
+ "vocab_size": 250002
+}

checkpoint-4452/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88741b0f87b730216fef92fffd20f0aa842b2dab67cb3cb4f8cf5e4451cc1d08
+size 1112205008

checkpoint-4452/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca9d2319bf61c46ca77cfebad79a8e400618752dbbda6075da8193ae86a68ab
+size 2224529658

checkpoint-4452/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9d8bd3a74e25c778856e7a78b9e9ec0618323b8f309673645f4c9d390f9711
+size 14244

checkpoint-4452/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3d832d51f43cd5d3835fdf31f0538a2455743a8985ef0eaf0c7f51e0f690f3
+size 1064

checkpoint-4452/trainer_state.json

@@ -0,0 +1,118 @@
+{
+ "best_metric": 0.6224449276924133,
+ "best_model_checkpoint": "/content/drive/MyDrive/XLM-RoBERTa/checkpoint-4452",
+ "epoch": 4.0,
+ "eval_steps": 100,
+ "global_step": 4452,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 1.0,
+ "grad_norm": 8.267438888549805,
+ "learning_rate": 4.5e-06,
+ "loss": 0.6879,
+ "step": 1113
+ },
+ {
+ "epoch": 1.0,
+ "eval_accuracy": 0.6130337078651685,
+ "eval_f1": 0.674233825198638,
+ "eval_loss": 0.6553897857666016,
+ "eval_precision": 0.5920265780730897,
+ "eval_recall": 0.7829525483304042,
+ "eval_runtime": 16.6298,
+ "eval_samples_per_second": 133.796,
+ "eval_steps_per_second": 8.419,
+ "step": 1113
+ },
+ {
+ "epoch": 2.0,
+ "grad_norm": 11.426044464111328,
+ "learning_rate": 4.000000000000001e-06,
+ "loss": 0.6446,
+ "step": 2226
+ },
+ {
+ "epoch": 2.0,
+ "eval_accuracy": 0.6449438202247191,
+ "eval_f1": 0.6786004882017901,
+ "eval_loss": 0.6413919925689697,
+ "eval_precision": 0.6318181818181818,
+ "eval_recall": 0.7328646748681898,
+ "eval_runtime": 16.2984,
+ "eval_samples_per_second": 136.517,
+ "eval_steps_per_second": 8.59,
+ "step": 2226
+ },
+ {
+ "epoch": 3.0,
+ "grad_norm": 34.342185974121094,
+ "learning_rate": 3.5e-06,
+ "loss": 0.62,
+ "step": 3339
+ },
+ {
+ "epoch": 3.0,
+ "eval_accuracy": 0.6494382022471911,
+ "eval_f1": 0.6758104738154613,
+ "eval_loss": 0.6359991431236267,
+ "eval_precision": 0.6411671924290221,
+ "eval_recall": 0.7144112478031635,
+ "eval_runtime": 16.3309,
+ "eval_samples_per_second": 136.245,
+ "eval_steps_per_second": 8.573,
+ "step": 3339
+ },
+ {
+ "epoch": 4.0,
+ "grad_norm": 15.571684837341309,
+ "learning_rate": 3e-06,
+ "loss": 0.5939,
+ "step": 4452
+ },
+ {
+ "epoch": 4.0,
+ "eval_accuracy": 0.6548314606741573,
+ "eval_f1": 0.7009345794392523,
+ "eval_loss": 0.6224449276924133,
+ "eval_precision": 0.6293706293706294,
+ "eval_recall": 0.7908611599297012,
+ "eval_runtime": 16.3616,
+ "eval_samples_per_second": 135.99,
+ "eval_steps_per_second": 8.557,
+ "step": 4452
+ }
+ ],
+ "logging_steps": 100,
+ "max_steps": 11130,
+ "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": 1.872929736474624e+16,
+ "train_batch_size": 16,
+ "trial_name": null,
+ "trial_params": null
+}

checkpoint-4452/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff238aadf09bba908ff3dfad1141ff451e76dde0b91b1ef88bb5f1889cd5372
+size 5176

config.json

@@ -0,0 +1,29 @@
+{
+ "_name_or_path": "xlm-roberta-base",
+ "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": 768,
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 514,
+ "model_type": "xlm-roberta",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "output_past": true,
+ "pad_token_id": 1,
+ "position_embedding_type": "absolute",
+ "problem_type": "multi_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.45.2",
+ "type_vocab_size": 1,
+ "use_cache": true,
+ "vocab_size": 250002
+}

events.out.tfevents.1728743175.1edb6b62aae0.1000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f261297030e07ec31596e3f7ab7e5d5b941003a22057e0fc3bbdbc5395142c
+size 9441

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88741b0f87b730216fef92fffd20f0aa842b2dab67cb3cb4f8cf5e4451cc1d08
+size 1112205008

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff238aadf09bba908ff3dfad1141ff451e76dde0b91b1ef88bb5f1889cd5372
+size 5176