Upload 9 files

.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

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0de0a8a597dcf25f892cb6e00f52f7b2f737c36247e4b26465913cfa26c2a52
+size 1109842416

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7dd53f0df8b1d80033430fdedb0514af4adfe1f4a44b465e893e90f436b8150
+size 14645

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9092d8b5989337626af7001a7a97b88471e2da7c59dce83aba82a0ef90cad1f
+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>"
+}

trainer_state.json

@@ -0,0 +1,270 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 14425,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17335529167027824,
+      "grad_norm": 11.912790298461914,
+      "learning_rate": 1.0812567713976167e-06,
+      "loss": 5.3489,
+      "step": 500
+    },
+    {
+      "epoch": 0.3467105833405565,
+      "grad_norm": 26.164979934692383,
+      "learning_rate": 2.164680390032503e-06,
+      "loss": 2.4606,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5200658750108347,
+      "grad_norm": 22.109607696533203,
+      "learning_rate": 3.248104008667389e-06,
+      "loss": 1.6107,
+      "step": 1500
+    },
+    {
+      "epoch": 0.693421166681113,
+      "grad_norm": 11.122232437133789,
+      "learning_rate": 4.331527627302276e-06,
+      "loss": 1.3092,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8667764583513912,
+      "grad_norm": 9.637592315673828,
+      "learning_rate": 5.414951245937162e-06,
+      "loss": 1.1522,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9044516682624817,
+      "eval_runtime": 73.1068,
+      "eval_samples_per_second": 1322.489,
+      "eval_steps_per_second": 82.66,
+      "step": 2885
+    },
+    {
+      "epoch": 1.039871717084164,
+      "grad_norm": 8.937479972839355,
+      "learning_rate": 6.498374864572048e-06,
+      "loss": 1.0359,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2132270087544423,
+      "grad_norm": 9.546417236328125,
+      "learning_rate": 7.581798483206935e-06,
+      "loss": 0.9387,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3865823004247204,
+      "grad_norm": 12.781045913696289,
+      "learning_rate": 8.66522210184182e-06,
+      "loss": 0.8925,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5599375920949987,
+      "grad_norm": 16.61449432373047,
+      "learning_rate": 9.748645720476708e-06,
+      "loss": 0.8351,
+      "step": 4500
+    },
+    {
+      "epoch": 1.733292883765277,
+      "grad_norm": 8.786149024963379,
+      "learning_rate": 9.791948854093299e-06,
+      "loss": 0.804,
+      "step": 5000
+    },
+    {
+      "epoch": 1.906648175435555,
+      "grad_norm": 8.35647201538086,
+      "learning_rate": 9.52104892452728e-06,
+      "loss": 0.7741,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.681246817111969,
+      "eval_runtime": 73.1325,
+      "eval_samples_per_second": 1322.025,
+      "eval_steps_per_second": 82.631,
+      "step": 5770
+    },
+    {
+      "epoch": 2.079743434168328,
+      "grad_norm": 8.843521118164062,
+      "learning_rate": 9.250148994961262e-06,
+      "loss": 0.7289,
+      "step": 6000
+    },
+    {
+      "epoch": 2.253098725838606,
+      "grad_norm": 7.018795490264893,
+      "learning_rate": 8.979249065395244e-06,
+      "loss": 0.6891,
+      "step": 6500
+    },
+    {
+      "epoch": 2.4264540175088847,
+      "grad_norm": 7.121385097503662,
+      "learning_rate": 8.708349135829224e-06,
+      "loss": 0.6894,
+      "step": 7000
+    },
+    {
+      "epoch": 2.5998093091791628,
+      "grad_norm": 7.603145599365234,
+      "learning_rate": 8.437449206263208e-06,
+      "loss": 0.6573,
+      "step": 7500
+    },
+    {
+      "epoch": 2.773164600849441,
+      "grad_norm": 7.313769817352295,
+      "learning_rate": 8.16654927669719e-06,
+      "loss": 0.6599,
+      "step": 8000
+    },
+    {
+      "epoch": 2.946519892519719,
+      "grad_norm": 12.033502578735352,
+      "learning_rate": 7.89564934713117e-06,
+      "loss": 0.6459,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6194610595703125,
+      "eval_runtime": 73.1152,
+      "eval_samples_per_second": 1322.339,
+      "eval_steps_per_second": 82.65,
+      "step": 8655
+    },
+    {
+      "epoch": 3.119615151252492,
+      "grad_norm": 8.768052101135254,
+      "learning_rate": 7.6247494175651514e-06,
+      "loss": 0.6049,
+      "step": 9000
+    },
+    {
+      "epoch": 3.29297044292277,
+      "grad_norm": 8.126376152038574,
+      "learning_rate": 7.353849487999134e-06,
+      "loss": 0.5915,
+      "step": 9500
+    },
+    {
+      "epoch": 3.4663257345930485,
+      "grad_norm": 8.753697395324707,
+      "learning_rate": 7.082949558433115e-06,
+      "loss": 0.5856,
+      "step": 10000
+    },
+    {
+      "epoch": 3.6396810262633266,
+      "grad_norm": 8.999127388000488,
+      "learning_rate": 6.812049628867097e-06,
+      "loss": 0.5807,
+      "step": 10500
+    },
+    {
+      "epoch": 3.813036317933605,
+      "grad_norm": 8.415000915527344,
+      "learning_rate": 6.5411496993010795e-06,
+      "loss": 0.575,
+      "step": 11000
+    },
+    {
+      "epoch": 3.986391609603883,
+      "grad_norm": 9.230948448181152,
+      "learning_rate": 6.27024976973506e-06,
+      "loss": 0.5722,
+      "step": 11500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6000474691390991,
+      "eval_runtime": 73.0477,
+      "eval_samples_per_second": 1323.56,
+      "eval_steps_per_second": 82.727,
+      "step": 11540
+    },
+    {
+      "epoch": 4.159486868336656,
+      "grad_norm": 10.552839279174805,
+      "learning_rate": 5.999349840169042e-06,
+      "loss": 0.5376,
+      "step": 12000
+    },
+    {
+      "epoch": 4.332842160006934,
+      "grad_norm": 9.041687965393066,
+      "learning_rate": 5.728449910603023e-06,
+      "loss": 0.5222,
+      "step": 12500
+    },
+    {
+      "epoch": 4.506197451677212,
+      "grad_norm": 11.044148445129395,
+      "learning_rate": 5.457549981037006e-06,
+      "loss": 0.5183,
+      "step": 13000
+    },
+    {
+      "epoch": 4.67955274334749,
+      "grad_norm": 8.885095596313477,
+      "learning_rate": 5.186650051470988e-06,
+      "loss": 0.522,
+      "step": 13500
+    },
+    {
+      "epoch": 4.852908035017769,
+      "grad_norm": 9.691495895385742,
+      "learning_rate": 4.9157501219049685e-06,
+      "loss": 0.5134,
+      "step": 14000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5658867359161377,
+      "eval_runtime": 73.1854,
+      "eval_samples_per_second": 1321.07,
+      "eval_steps_per_second": 82.571,
+      "step": 14425
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 23072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.617438027185613e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017afcf1fd9814bcd9376ebaf89bdb7d98c1c3bc6e014b869bb77889a39234b7
+size 5841