add files

README.md

@@ -0,0 +1,48 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: eval
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# eval
+
+This model is a fine-tuned version of [xlm-roberta-large_squad](https://huggingface.co/xlm-roberta-large_squad) on the squad dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 12
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 0.67
+
+### Framework versions
+
+- Transformers 4.14.1
+- Pytorch 1.9.0
+- Datasets 1.16.1
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,5 @@
+{
+    "eval_exact_match": 85.96026490066225,
+    "eval_f1": 92.25000664341768,
+    "eval_samples": 10918
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.14.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.json

@@ -0,0 +1,5 @@
+{
+    "eval_exact_match": 85.96026490066225,
+    "eval_f1": 92.25000664341768,
+    "eval_samples": 10918
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68836353857e2c3c0ded8c18afe5a43d18535aa2b9dfca793cab232b4dc9b84a
+size 2235534897

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3392259274139549,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.8995580554439533e-05,
+      "loss": 1.7911,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.799116110887907e-05,
+      "loss": 1.1202,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.69867416633186e-05,
+      "loss": 1.071,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5982322217758134e-05,
+      "loss": 1.0396,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.497790277219767e-05,
+      "loss": 0.9828,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.3973483326637206e-05,
+      "loss": 0.9747,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.296906388107674e-05,
+      "loss": 0.9792,
+      "step": 3500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.1964644435516274e-05,
+      "loss": 0.9584,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.0960224989955807e-05,
+      "loss": 0.9178,
+      "step": 4500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.995580554439534e-05,
+      "loss": 0.9288,
+      "step": 5000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.8951386098834875e-05,
+      "loss": 0.9089,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7946966653274408e-05,
+      "loss": 0.883,
+      "step": 6000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.694254720771394e-05,
+      "loss": 0.8601,
+      "step": 6500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5938127762153476e-05,
+      "loss": 0.847,
+      "step": 7000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.493370831659301e-05,
+      "loss": 0.831,
+      "step": 7500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.3929288871032543e-05,
+      "loss": 0.6511,
+      "step": 8000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.2924869425472077e-05,
+      "loss": 0.6223,
+      "step": 8500
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.1920449979911611e-05,
+      "loss": 0.6363,
+      "step": 9000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.0916030534351145e-05,
+      "loss": 0.6226,
+      "step": 9500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 9.91161108879068e-06,
+      "loss": 0.6203,
+      "step": 10000
+    }
+  ],
+  "max_steps": 14934,
+  "num_train_epochs": 2,
+  "total_flos": 8.357875357981133e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccdcefa60f2e955b04838abfd9a8dcd0a0a549398bc3f694aa2f80f4094c16f2
+size 2927