Upload folder using huggingface_hub

.gitattributes

@@ -38,3 +38,4 @@ 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_202/checkpoint-8877/tokenizer.json filter=lfs diff=lfs merge=lfs -text

xlmr_checkpoints_seed_202/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_202/checkpoint-8877/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a807e7eb805dbd9eebfb2effc3d2ab36b0899db7a1a4c4803f077cd2b2f950
+size 1112229616

xlmr_checkpoints_seed_202/checkpoint-8877/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b12bccdfc01b47628f76db27c8e74c5227cf65a1bf62ba7a43cc396c4b7f07
+size 2224582027

xlmr_checkpoints_seed_202/checkpoint-8877/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704700473f5ec19ca8d6479adff6b10483f5576ae2733081db967fdcd6111206
+size 14645

xlmr_checkpoints_seed_202/checkpoint-8877/scheduler.pt

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

xlmr_checkpoints_seed_202/checkpoint-8877/tokenizer.json

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

xlmr_checkpoints_seed_202/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_202/checkpoint-8877/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_global_step": 8877,
+  "best_metric": 0.940629867698253,
+  "best_model_checkpoint": "./xlmr_checkpoints_seed_202/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": 4.905686378479004,
+      "learning_rate": 4.681050656660413e-05,
+      "loss": 0.7301978149414062,
+      "step": 500
+    },
+    {
+      "epoch": 0.33795201081446435,
+      "grad_norm": 4.162442207336426,
+      "learning_rate": 4.720757430488975e-05,
+      "loss": 0.27902072143554685,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5069280162216965,
+      "grad_norm": 2.380737066268921,
+      "learning_rate": 4.421140939597316e-05,
+      "loss": 0.24155935668945314,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6759040216289287,
+      "grad_norm": 2.1990551948547363,
+      "learning_rate": 4.121524448705657e-05,
+      "loss": 0.22269638061523436,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8448800270361608,
+      "grad_norm": 2.2804040908813477,
+      "learning_rate": 3.8219079578139984e-05,
+      "loss": 0.21019873046875,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9311291855920566,
+      "eval_loss": 0.19129826128482819,
+      "eval_macro_auc": 0.9965905633908084,
+      "eval_macro_f1": 0.9232039599017469,
+      "eval_macro_precision": 0.9229213887448425,
+      "eval_macro_recall": 0.9260382349221203,
+      "eval_runtime": 36.5716,
+      "eval_samples_per_second": 2588.619,
+      "eval_steps_per_second": 10.117,
+      "step": 2959
+    },
+    {
+      "epoch": 1.013856032443393,
+      "grad_norm": 2.3989100456237793,
+      "learning_rate": 3.5222914669223394e-05,
+      "loss": 0.19795292663574218,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1828320378506252,
+      "grad_norm": 2.795443296432495,
+      "learning_rate": 3.2226749760306804e-05,
+      "loss": 0.1686121063232422,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3518080432578574,
+      "grad_norm": 2.0825798511505127,
+      "learning_rate": 2.923058485139022e-05,
+      "loss": 0.1651682586669922,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5207840486650896,
+      "grad_norm": 2.1733877658843994,
+      "learning_rate": 2.6234419942473638e-05,
+      "loss": 0.16280000305175782,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6897600540723219,
+      "grad_norm": 1.7175102233886719,
+      "learning_rate": 2.3238255033557048e-05,
+      "loss": 0.15737954711914062,
+      "step": 5000
+    },
+    {
+      "epoch": 1.858736059479554,
+      "grad_norm": 1.6600334644317627,
+      "learning_rate": 2.024209012464046e-05,
+      "loss": 0.15802685546875,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.941512622794972,
+      "eval_loss": 0.16234929859638214,
+      "eval_macro_auc": 0.9975151205070638,
+      "eval_macro_f1": 0.9358308065263617,
+      "eval_macro_precision": 0.9340274143653156,
+      "eval_macro_recall": 0.9380237662721548,
+      "eval_runtime": 36.6026,
+      "eval_samples_per_second": 2586.426,
+      "eval_steps_per_second": 10.109,
+      "step": 5918
+    },
+    {
+      "epoch": 2.027712064886786,
+      "grad_norm": 1.5459070205688477,
+      "learning_rate": 1.7245925215723874e-05,
+      "loss": 0.14857688903808594,
+      "step": 6000
+    },
+    {
+      "epoch": 2.196688070294018,
+      "grad_norm": 3.2165985107421875,
+      "learning_rate": 1.4249760306807286e-05,
+      "loss": 0.1216359634399414,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3656640757012504,
+      "grad_norm": 2.588282346725464,
+      "learning_rate": 1.1253595397890701e-05,
+      "loss": 0.12032920837402344,
+      "step": 7000
+    },
+    {
+      "epoch": 2.5346400811084826,
+      "grad_norm": 2.8378584384918213,
+      "learning_rate": 8.257430488974113e-06,
+      "loss": 0.11635771179199218,
+      "step": 7500
+    },
+    {
+      "epoch": 2.703616086515715,
+      "grad_norm": 2.1362733840942383,
+      "learning_rate": 5.261265580057527e-06,
+      "loss": 0.11488867950439453,
+      "step": 8000
+    },
+    {
+      "epoch": 2.872592091922947,
+      "grad_norm": 1.4959301948547363,
+      "learning_rate": 2.2651006711409396e-06,
+      "loss": 0.11301873779296875,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9456533220661244,
+      "eval_loss": 0.1558140218257904,
+      "eval_macro_auc": 0.9977583795852312,
+      "eval_macro_f1": 0.940629867698253,
+      "eval_macro_precision": 0.9401240209929883,
+      "eval_macro_recall": 0.9412960171744027,
+      "eval_runtime": 36.6358,
+      "eval_samples_per_second": 2584.082,
+      "eval_steps_per_second": 10.099,
+      "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_202/checkpoint-8877/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24387c158afe692fddb22c4f16291440545b0f73bbe542e6da7b8c976feadbc
+size 5201