Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-650/config.json

@@ -0,0 +1,56 @@
+{
+  "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": 1024,
+  "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",
+    "10": "LABEL_10",
+    "11": "LABEL_11"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "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": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-650/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a61d3d7d4c6e39dc60f95ebcc8ac78cb8907334c82a62302305b29cc691b20d1
+size 2239659672

checkpoint-650/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e43e921848b4160b479d0e3d1069ce07dd246d00a1f0f6b915c6dc641476471
+size 4479554705

checkpoint-650/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7ff2d3adf149de93fb9af2596af86a4e073e792b944f7a34a8d9e43b7f2e09
+size 14244

checkpoint-650/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc49ce2ed3a78b592179072211a7232b0ec4bf21d989c819aa813a0eee974496
+size 1064

checkpoint-650/trainer_state.json

@@ -0,0 +1,233 @@
+{
+  "best_global_step": 650,
+  "best_metric": 1.446366786956787,
+  "best_model_checkpoint": "model/checkpoint-650",
+  "epoch": 10.0,
+  "eval_steps": 100,
+  "global_step": 650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 18.839448928833008,
+      "learning_rate": 9e-06,
+      "loss": 2.2193,
+      "step": 65
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.296875,
+      "eval_f1": 0.13591867469879518,
+      "eval_loss": 1.9436771869659424,
+      "eval_precision": 0.088134765625,
+      "eval_recall": 0.296875,
+      "eval_runtime": 0.5308,
+      "eval_samples_per_second": 120.581,
+      "eval_steps_per_second": 15.073,
+      "step": 65
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.428215026855469,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.0787,
+      "step": 130
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.34375,
+      "eval_f1": 0.2071691176470588,
+      "eval_loss": 1.872170329093933,
+      "eval_precision": 0.15072278911564627,
+      "eval_recall": 0.34375,
+      "eval_runtime": 0.5302,
+      "eval_samples_per_second": 120.719,
+      "eval_steps_per_second": 15.09,
+      "step": 130
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 53.54623031616211,
+      "learning_rate": 7e-06,
+      "loss": 1.9946,
+      "step": 195
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4375,
+      "eval_f1": 0.29532839962997226,
+      "eval_loss": 1.8184549808502197,
+      "eval_precision": 0.2342509920634921,
+      "eval_recall": 0.4375,
+      "eval_runtime": 0.5335,
+      "eval_samples_per_second": 119.973,
+      "eval_steps_per_second": 14.997,
+      "step": 195
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 15.883207321166992,
+      "learning_rate": 6e-06,
+      "loss": 1.8783,
+      "step": 260
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.421875,
+      "eval_f1": 0.3224431818181818,
+      "eval_loss": 1.8057754039764404,
+      "eval_precision": 0.3003472222222222,
+      "eval_recall": 0.421875,
+      "eval_runtime": 0.5292,
+      "eval_samples_per_second": 120.949,
+      "eval_steps_per_second": 15.119,
+      "step": 260
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 52.486629486083984,
+      "learning_rate": 5e-06,
+      "loss": 1.7463,
+      "step": 325
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.359375,
+      "eval_f1": 0.2792616648992577,
+      "eval_loss": 1.7504793405532837,
+      "eval_precision": 0.24629103535353536,
+      "eval_recall": 0.359375,
+      "eval_runtime": 0.5495,
+      "eval_samples_per_second": 116.477,
+      "eval_steps_per_second": 14.56,
+      "step": 325
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 81.41285705566406,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.5803,
+      "step": 390
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.46875,
+      "eval_f1": 0.41320569674228214,
+      "eval_loss": 1.6302127838134766,
+      "eval_precision": 0.3737571022727273,
+      "eval_recall": 0.46875,
+      "eval_runtime": 0.5313,
+      "eval_samples_per_second": 120.469,
+      "eval_steps_per_second": 15.059,
+      "step": 390
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 45.92146682739258,
+      "learning_rate": 3e-06,
+      "loss": 1.3897,
+      "step": 455
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.453125,
+      "eval_f1": 0.41390128968253964,
+      "eval_loss": 1.587652325630188,
+      "eval_precision": 0.3891989087301588,
+      "eval_recall": 0.453125,
+      "eval_runtime": 0.5534,
+      "eval_samples_per_second": 115.652,
+      "eval_steps_per_second": 14.456,
+      "step": 455
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 164.84347534179688,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.2265,
+      "step": 520
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.46875,
+      "eval_f1": 0.44462377899877903,
+      "eval_loss": 1.482975959777832,
+      "eval_precision": 0.4474907904595405,
+      "eval_recall": 0.46875,
+      "eval_runtime": 0.5315,
+      "eval_samples_per_second": 120.403,
+      "eval_steps_per_second": 15.05,
+      "step": 520
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 163.72511291503906,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.0659,
+      "step": 585
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.453125,
+      "eval_f1": 0.4214488636363637,
+      "eval_loss": 1.4710180759429932,
+      "eval_precision": 0.41629464285714285,
+      "eval_recall": 0.453125,
+      "eval_runtime": 0.5304,
+      "eval_samples_per_second": 120.672,
+      "eval_steps_per_second": 15.084,
+      "step": 585
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 280.70709228515625,
+      "learning_rate": 0.0,
+      "loss": 0.9751,
+      "step": 650
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.47144955738705735,
+      "eval_loss": 1.446366786956787,
+      "eval_precision": 0.4710898042929293,
+      "eval_recall": 0.5,
+      "eval_runtime": 0.5301,
+      "eval_samples_per_second": 120.735,
+      "eval_steps_per_second": 15.092,
+      "step": 650
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 650,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1199902171084800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-650/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0597ad01e6d745620abded78b27c0d3132d1fd4cfaee8c266a31971c0273581a
+size 5240

config.json

@@ -0,0 +1,56 @@
+{
+  "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": 1024,
+  "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",
+    "10": "LABEL_10",
+    "11": "LABEL_11"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "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": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

events.out.tfevents.1743875863.ebf3ff675ae4.574.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd3e5822df4a4c9faf60f0a71e28c44567b793104db065e222cc1a169b09520
+size 9275

events.out.tfevents.1743876063.ebf3ff675ae4.574.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d39a80fc3beb36a5f482aafd8bf5dccb007090ae478e67e0922850511b4eb2
+size 12691

logs/events.out.tfevents.1740652331.686e763fa1a3.6372.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b679ab2ba83443dd64c4ce1ad8fc68431d53c7b4e8729e949e77a6e9887185a
+size 5048

logs/events.out.tfevents.1740652422.686e763fa1a3.6372.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f61ba655f9b9482c492b3b9d0281386398db0edc9c5bdd8042bffbc72875f99
+size 8912

logs/events.out.tfevents.1740653808.686e763fa1a3.6372.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db458f0b236db8c609f2ced5700e0d9f1d569bb73ce0e0146707cf3c1d3623d
+size 5925

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a61d3d7d4c6e39dc60f95ebcc8ac78cb8907334c82a62302305b29cc691b20d1
+size 2239659672

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0597ad01e6d745620abded78b27c0d3132d1fd4cfaee8c266a31971c0273581a
+size 5240