Upload folder using huggingface_hub

visobert_checkpoints_seed_22/checkpoint-8877/config.json

@@ -0,0 +1,54 @@
+{
+  "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-12,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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": 2,
+  "use_cache": false,
+  "vocab_size": 15004
+}

visobert_checkpoints_seed_22/checkpoint-8877/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab21459743d48d86e05ed0970fb88360514fdf260837193376b78d4a0a305b5d
+size 390318648

visobert_checkpoints_seed_22/checkpoint-8877/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48515230256c046ec7e1d975f5be57aa2f68cd6862e990528d1c1e68f28575dc
+size 780760459

visobert_checkpoints_seed_22/checkpoint-8877/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64bcf5ec5bd3eae92d0a8ddfc63967c885aa3b20cba5f1334cf1036330666980
+size 14645

visobert_checkpoints_seed_22/checkpoint-8877/scheduler.pt

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

visobert_checkpoints_seed_22/checkpoint-8877/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_id": 0,
+  "unk_token": "<unk>"
+}

visobert_checkpoints_seed_22/checkpoint-8877/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_global_step": 8877,
+  "best_metric": 0.9192446513023889,
+  "best_model_checkpoint": "./visobert_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": 6.283323764801025,
+      "learning_rate": 4.681050656660413e-05,
+      "loss": 0.858648193359375,
+      "step": 500
+    },
+    {
+      "epoch": 0.33795201081446435,
+      "grad_norm": 4.389909267425537,
+      "learning_rate": 4.720757430488975e-05,
+      "loss": 0.38937628173828126,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5069280162216965,
+      "grad_norm": 3.18888521194458,
+      "learning_rate": 4.421140939597316e-05,
+      "loss": 0.3332505798339844,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6759040216289287,
+      "grad_norm": 2.0255439281463623,
+      "learning_rate": 4.121524448705657e-05,
+      "loss": 0.29934005737304686,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8448800270361608,
+      "grad_norm": 2.3967268466949463,
+      "learning_rate": 3.8219079578139984e-05,
+      "loss": 0.28441644287109374,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9083342135840288,
+      "eval_loss": 0.2619016468524933,
+      "eval_macro_auc": 0.9943587562280356,
+      "eval_macro_f1": 0.9007025624863008,
+      "eval_macro_precision": 0.9018134431253848,
+      "eval_macro_recall": 0.9002699487813762,
+      "eval_runtime": 39.5773,
+      "eval_samples_per_second": 2392.025,
+      "eval_steps_per_second": 18.698,
+      "step": 2959
+    },
+    {
+      "epoch": 1.013856032443393,
+      "grad_norm": 2.434843063354492,
+      "learning_rate": 3.5222914669223394e-05,
+      "loss": 0.26524542236328125,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1828320378506252,
+      "grad_norm": 2.3567428588867188,
+      "learning_rate": 3.2226749760306804e-05,
+      "loss": 0.2254783172607422,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3518080432578574,
+      "grad_norm": 2.3784019947052,
+      "learning_rate": 2.923058485139022e-05,
+      "loss": 0.22080050659179687,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5207840486650896,
+      "grad_norm": 2.162022829055786,
+      "learning_rate": 2.6234419942473638e-05,
+      "loss": 0.21156744384765624,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6897600540723219,
+      "grad_norm": 2.594876766204834,
+      "learning_rate": 2.3238255033557048e-05,
+      "loss": 0.20629013061523438,
+      "step": 5000
+    },
+    {
+      "epoch": 1.858736059479554,
+      "grad_norm": 2.3263511657714844,
+      "learning_rate": 2.024209012464046e-05,
+      "loss": 0.20743641662597656,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9224463927326503,
+      "eval_loss": 0.21836993098258972,
+      "eval_macro_auc": 0.9958366681076674,
+      "eval_macro_f1": 0.9152791082780608,
+      "eval_macro_precision": 0.9122267006321545,
+      "eval_macro_recall": 0.9191421422858446,
+      "eval_runtime": 39.5308,
+      "eval_samples_per_second": 2394.844,
+      "eval_steps_per_second": 18.72,
+      "step": 5918
+    },
+    {
+      "epoch": 2.027712064886786,
+      "grad_norm": 2.3093361854553223,
+      "learning_rate": 1.7245925215723874e-05,
+      "loss": 0.1920579071044922,
+      "step": 6000
+    },
+    {
+      "epoch": 2.196688070294018,
+      "grad_norm": 1.9817551374435425,
+      "learning_rate": 1.4249760306807286e-05,
+      "loss": 0.1485968780517578,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3656640757012504,
+      "grad_norm": 2.270033597946167,
+      "learning_rate": 1.1253595397890701e-05,
+      "loss": 0.14900279235839844,
+      "step": 7000
+    },
+    {
+      "epoch": 2.5346400811084826,
+      "grad_norm": 2.36781644821167,
+      "learning_rate": 8.257430488974113e-06,
+      "loss": 0.14796644592285157,
+      "step": 7500
+    },
+    {
+      "epoch": 2.703616086515715,
+      "grad_norm": 2.2283663749694824,
+      "learning_rate": 5.261265580057527e-06,
+      "loss": 0.14279981994628907,
+      "step": 8000
+    },
+    {
+      "epoch": 2.872592091922947,
+      "grad_norm": 2.292788505554199,
+      "learning_rate": 2.2651006711409396e-06,
+      "loss": 0.1387650604248047,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9258371184113235,
+      "eval_loss": 0.21822181344032288,
+      "eval_macro_auc": 0.9960757558422927,
+      "eval_macro_f1": 0.9192446513023889,
+      "eval_macro_precision": 0.9178944858991189,
+      "eval_macro_recall": 0.9207754284150103,
+      "eval_runtime": 39.5727,
+      "eval_samples_per_second": 2392.308,
+      "eval_steps_per_second": 18.7,
+      "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
+}

visobert_checkpoints_seed_22/checkpoint-8877/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853cb63dc86c4cf2f5d9bf6c85de801bf7d8f8ed159f8755ff9b0422e41674d8
+size 5201