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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "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": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a7dc44630bdc5b9b3bca6473f8537bfdd1a8e8a463ff94ab4dd49c23d352cf
+size 2219803194

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a5738e8136709ddd5ea3586e0400cc6950d9b01695c051a5f06cc87b3f4d43
+size 1109887142

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6cf6f95989b774f37b885b5e53e76fcc6c7fe7a8b6aafb0e00aec59e24887b6
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a8ea2268948301b867b05dd85905cf1e41748e55932b3508c99d5271631459
+size 1064

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878651887ee9b23df6f7c6ca7e87b6409eae7a37ec9fbd481e52b08ded3eb322
+size 17082951

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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": 0.9376567006111145,
+  "best_model_checkpoint": "finetune_xlm-roberta-base/checkpoint-5476",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5476,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8789870952033116e-05,
+      "loss": 2.1799,
+      "step": 500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7572437302167033e-05,
+      "loss": 1.2786,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.635500365230095e-05,
+      "loss": 1.1682,
+      "step": 1500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.513757000243487e-05,
+      "loss": 1.1019,
+      "step": 2000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3920136352568787e-05,
+      "loss": 1.0745,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9917843341827393,
+      "eval_runtime": 32.4148,
+      "eval_samples_per_second": 326.086,
+      "eval_steps_per_second": 2.561,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.2702702702702702e-05,
+      "loss": 0.9744,
+      "step": 3000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.1487703920136353e-05,
+      "loss": 0.9039,
+      "step": 3500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.027027027027027e-05,
+      "loss": 0.8688,
+      "step": 4000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.052836620404189e-06,
+      "loss": 0.8802,
+      "step": 4500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.835402970538106e-06,
+      "loss": 0.8816,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9376567006111145,
+      "eval_runtime": 32.177,
+      "eval_samples_per_second": 328.495,
+      "eval_steps_per_second": 2.579,
+      "step": 5476
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8214,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.4334001889975296e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10189f5b89439c9bf25c82faa8284cd997c974e3e32657c149cffd6836abe1d
+size 4536