Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,4 @@ results_xlmr/predictions_seed_202.csv filter=lfs diff=lfs merge=lfs -text
 results_xlmr/predictions_seed_22.csv filter=lfs diff=lfs merge=lfs -text
 results_xlmr/predictions_seed_42.csv filter=lfs diff=lfs merge=lfs -text
 xlmr_checkpoints_seed_42/checkpoint-8877/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+xlmr_checkpoints_seed_22/checkpoint-8877/tokenizer.json filter=lfs diff=lfs merge=lfs -text

xlmr_checkpoints_seed_22/checkpoint-8877/config.json

@@ -0,0 +1,55 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.1",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

xlmr_checkpoints_seed_22/checkpoint-8877/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21fe2fa7431497ca43b6c9cf46dbbbd3d1621ecc5304d289faf976bbeb8a1de8
+size 1112229616

xlmr_checkpoints_seed_22/checkpoint-8877/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9285e164086165e82beec3ced9eddcfa1fe59abff567cf298b647c8938488542
+size 2224582027

xlmr_checkpoints_seed_22/checkpoint-8877/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9be2909411343905729aae272937eaead231a97904004e4fe330549917181e
+size 14645

xlmr_checkpoints_seed_22/checkpoint-8877/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54ba3662afbad5e96671f8aaa93fb445806ea62c3222f4c44d2cf8b06f93dcb
+size 1465

xlmr_checkpoints_seed_22/checkpoint-8877/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acbd420e2269cdc1ef45332d3d5c418be4aef6b8cb5a0b7ccae0893485307153
+size 17098086

xlmr_checkpoints_seed_22/checkpoint-8877/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

xlmr_checkpoints_seed_22/checkpoint-8877/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_global_step": 8877,
+  "best_metric": 0.9416269933164496,
+  "best_model_checkpoint": "./xlmr_checkpoints_seed_22/checkpoint-8877",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 8877,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16897600540723218,
+      "grad_norm": 4.067020893096924,
+      "learning_rate": 4.681050656660413e-05,
+      "loss": 0.74340771484375,
+      "step": 500
+    },
+    {
+      "epoch": 0.33795201081446435,
+      "grad_norm": 2.632394313812256,
+      "learning_rate": 4.720757430488975e-05,
+      "loss": 0.2822638244628906,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5069280162216965,
+      "grad_norm": 2.726809501647949,
+      "learning_rate": 4.421140939597316e-05,
+      "loss": 0.24365966796875,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6759040216289287,
+      "grad_norm": 2.1524641513824463,
+      "learning_rate": 4.121524448705657e-05,
+      "loss": 0.22103640747070313,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8448800270361608,
+      "grad_norm": 3.1224212646484375,
+      "learning_rate": 3.8219079578139984e-05,
+      "loss": 0.21051376342773437,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9303475229745432,
+      "eval_loss": 0.1935378760099411,
+      "eval_macro_auc": 0.9965505251760692,
+      "eval_macro_f1": 0.923622870392869,
+      "eval_macro_precision": 0.9246085548547729,
+      "eval_macro_recall": 0.9230841797424775,
+      "eval_runtime": 36.6645,
+      "eval_samples_per_second": 2582.062,
+      "eval_steps_per_second": 10.092,
+      "step": 2959
+    },
+    {
+      "epoch": 1.013856032443393,
+      "grad_norm": 1.8284794092178345,
+      "learning_rate": 3.5222914669223394e-05,
+      "loss": 0.20010812377929688,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1828320378506252,
+      "grad_norm": 1.9382073879241943,
+      "learning_rate": 3.2226749760306804e-05,
+      "loss": 0.17265153503417968,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3518080432578574,
+      "grad_norm": 2.3385143280029297,
+      "learning_rate": 2.923058485139022e-05,
+      "loss": 0.16743768310546875,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5207840486650896,
+      "grad_norm": 1.865295171737671,
+      "learning_rate": 2.6234419942473638e-05,
+      "loss": 0.16153562927246093,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6897600540723219,
+      "grad_norm": 2.381648063659668,
+      "learning_rate": 2.3238255033557048e-05,
+      "loss": 0.1572110595703125,
+      "step": 5000
+    },
+    {
+      "epoch": 1.858736059479554,
+      "grad_norm": 1.9312297105789185,
+      "learning_rate": 2.024209012464046e-05,
+      "loss": 0.1588658447265625,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.94184007605366,
+      "eval_loss": 0.16147716343402863,
+      "eval_macro_auc": 0.9975790133104768,
+      "eval_macro_f1": 0.9363972305566394,
+      "eval_macro_precision": 0.9332707441404324,
+      "eval_macro_recall": 0.9398515320045094,
+      "eval_runtime": 36.6652,
+      "eval_samples_per_second": 2582.015,
+      "eval_steps_per_second": 10.091,
+      "step": 5918
+    },
+    {
+      "epoch": 2.027712064886786,
+      "grad_norm": 2.168081760406494,
+      "learning_rate": 1.7245925215723874e-05,
+      "loss": 0.14772994995117186,
+      "step": 6000
+    },
+    {
+      "epoch": 2.196688070294018,
+      "grad_norm": 2.4388930797576904,
+      "learning_rate": 1.4249760306807286e-05,
+      "loss": 0.11921089935302734,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3656640757012504,
+      "grad_norm": 2.313595771789551,
+      "learning_rate": 1.1253595397890701e-05,
+      "loss": 0.11971865844726562,
+      "step": 7000
+    },
+    {
+      "epoch": 2.5346400811084826,
+      "grad_norm": 2.8708314895629883,
+      "learning_rate": 8.257430488974113e-06,
+      "loss": 0.12086968231201171,
+      "step": 7500
+    },
+    {
+      "epoch": 2.703616086515715,
+      "grad_norm": 2.4916293621063232,
+      "learning_rate": 5.261265580057527e-06,
+      "loss": 0.11663914489746094,
+      "step": 8000
+    },
+    {
+      "epoch": 2.872592091922947,
+      "grad_norm": 1.8451826572418213,
+      "learning_rate": 2.2651006711409396e-06,
+      "loss": 0.11132289123535156,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9465089257420514,
+      "eval_loss": 0.15379028022289276,
+      "eval_macro_auc": 0.9978227510764514,
+      "eval_macro_f1": 0.9416269933164496,
+      "eval_macro_precision": 0.9410781473052303,
+      "eval_macro_recall": 0.9422793394730571,
+      "eval_runtime": 36.6423,
+      "eval_samples_per_second": 2583.628,
+      "eval_steps_per_second": 10.098,
+      "step": 8877
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8877,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9892457450779034e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

xlmr_checkpoints_seed_22/checkpoint-8877/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1826a13fa3556960ca97d64568b8725d5513b1b9019f417c59b8cf7dff352c
+size 5201