Upload folder using huggingface_hub

checkpoint-1965/config.json

@@ -0,0 +1,47 @@
+{
+  "_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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-1965/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6092b238a261e286f40368487b5b6bebbee42857fe038bce09e7a3d57be91527
+size 1112220388

checkpoint-1965/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:437649ad9d605ab3d6c0e5292c0ee9e37c2f3d0d1c32e2f9fff685c490fb5479
+size 2224560378

checkpoint-1965/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bbf8977cff56e770ac1fc89fc118744b3604183b78e4eba2cfac0f5c30e33a8
+size 14244

checkpoint-1965/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd3538a0504a81cfe71e3069423853a9f9b7f28aa7ad84cd7cd85d2af41fb52
+size 1064

checkpoint-1965/trainer_state.json

@@ -0,0 +1,80 @@
+{
+  "best_metric": 0.24109159409999847,
+  "best_model_checkpoint": "/project_antwerp/v4slant/model_hu/checkpoint-1965",
+  "epoch": 1.9992369324685235,
+  "eval_steps": 500,
+  "global_step": 1965,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9991097545466107,
+      "grad_norm": 249.48770141601562,
+      "learning_rate": 4.008146639511201e-06,
+      "loss": 0.8591,
+      "step": 982
+    },
+    {
+      "epoch": 0.9991097545466107,
+      "eval_accuracy": 0.9257375381485249,
+      "eval_f1": 0.9252737729208254,
+      "eval_loss": 0.24675492942333221,
+      "eval_precision": 0.9261535074038819,
+      "eval_recall": 0.9257375381485249,
+      "eval_runtime": 9.5851,
+      "eval_samples_per_second": 102.555,
+      "eval_steps_per_second": 102.555,
+      "step": 982
+    },
+    {
+      "epoch": 1.9992369324685235,
+      "grad_norm": 1.3834336996078491,
+      "learning_rate": 3.008146639511202e-06,
+      "loss": 0.227,
+      "step": 1965
+    },
+    {
+      "epoch": 1.9992369324685235,
+      "eval_accuracy": 0.9511698880976602,
+      "eval_f1": 0.9512503361009931,
+      "eval_loss": 0.24109159409999847,
+      "eval_precision": 0.9515974956975125,
+      "eval_recall": 0.9511698880976602,
+      "eval_runtime": 9.7481,
+      "eval_samples_per_second": 100.84,
+      "eval_steps_per_second": 100.84,
+      "step": 1965
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4910,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "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": 258616888099200.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1965/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2fce8eb376fba76f3d443a55c3918c9b558b6b97ace4610281be9635a376cb
+size 5240

config.json

@@ -0,0 +1,47 @@
+{
+  "_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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

events.out.tfevents.1730916187.c4bf49004bf1.1537.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ca00e7730d3bb67f8fa92acfcb57e1eeb5449831393ac50f29c9fea1025195
+size 8535

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6092b238a261e286f40368487b5b6bebbee42857fe038bce09e7a3d57be91527
+size 1112220388

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2fce8eb376fba76f3d443a55c3918c9b558b6b97ace4610281be9635a376cb
+size 5240