upload model

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,31 @@
+{
+  "_name_or_path": "deepset/xlm-roberta-large-squad2",
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "name": "XLMRoberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "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:e2bd6015423b40ad673b67c061a027f1f29811ede0d7890418e557671602e6a9
+size 4470971045

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012d7c377a346d731e0aad0cb4bf25f3cadbd015af12376af7f6fd56a849b684
+size 2235508081

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa2675dda0f1f1bb4b827f55a2b5d3fb89065a1d782687e6982b1557793cb67
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab0e52973fe8087f3ac01ea4ace31502a560486b70b20e5ef5a49e1c71693d40
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8665294e3886774bbb7aecbbfad2b6c582db1f989fa593de5318a2ac37110e83
+size 623

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 +1,9 @@
+{
+  "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 sha256:82c8b78c0e538c5607cdc49a421e63b57a05d79abee8ce1da011742a9e28621c
+size 17098345

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "full_tokenizer_file": null,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "deepset/xlm-roberta-large-squad2",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "germanQA/saved_models/xlm-roberta-large-squad2/special_tokens_map.json",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,152 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 5690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.8263620386643236e-05,
+      "loss": 0.693,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_runtime": 7.7102,
+      "eval_samples_per_second": 65.368,
+      "eval_steps_per_second": 8.171,
+      "step": 569
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.650615114235501e-05,
+      "loss": 0.4198,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_runtime": 7.6907,
+      "eval_samples_per_second": 65.533,
+      "eval_steps_per_second": 8.192,
+      "step": 1138
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.4748681898066785e-05,
+      "loss": 0.3079,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_runtime": 7.8146,
+      "eval_samples_per_second": 64.494,
+      "eval_steps_per_second": 8.062,
+      "step": 1707
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 1.299121265377856e-05,
+      "loss": 0.2031,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_runtime": 7.6687,
+      "eval_samples_per_second": 65.721,
+      "eval_steps_per_second": 8.215,
+      "step": 2276
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 1.1237258347978912e-05,
+      "loss": 0.1858,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_runtime": 7.7223,
+      "eval_samples_per_second": 65.266,
+      "eval_steps_per_second": 8.158,
+      "step": 2845
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 9.479789103690687e-06,
+      "loss": 0.1088,
+      "step": 3000
+    },
+    {
+      "epoch": 6.0,
+      "eval_runtime": 7.6837,
+      "eval_samples_per_second": 65.594,
+      "eval_steps_per_second": 8.199,
+      "step": 3414
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 7.72231985940246e-06,
+      "loss": 0.086,
+      "step": 3500
+    },
+    {
+      "epoch": 7.0,
+      "eval_runtime": 7.6991,
+      "eval_samples_per_second": 65.462,
+      "eval_steps_per_second": 8.183,
+      "step": 3983
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 5.968365553602813e-06,
+      "loss": 0.0536,
+      "step": 4000
+    },
+    {
+      "epoch": 7.91,
+      "learning_rate": 4.214411247803164e-06,
+      "loss": 0.0433,
+      "step": 4500
+    },
+    {
+      "epoch": 8.0,
+      "eval_runtime": 7.691,
+      "eval_samples_per_second": 65.531,
+      "eval_steps_per_second": 8.191,
+      "step": 4552
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 2.4569420035149386e-06,
+      "loss": 0.0224,
+      "step": 5000
+    },
+    {
+      "epoch": 9.0,
+      "eval_runtime": 7.6949,
+      "eval_samples_per_second": 65.498,
+      "eval_steps_per_second": 8.187,
+      "step": 5121
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 6.994727592267137e-07,
+      "loss": 0.0135,
+      "step": 5500
+    },
+    {
+      "epoch": 10.0,
+      "eval_runtime": 7.6822,
+      "eval_samples_per_second": 65.607,
+      "eval_steps_per_second": 8.201,
+      "step": 5690
+    }
+  ],
+  "max_steps": 5690,
+  "num_train_epochs": 10,
+  "total_flos": 2.111879700099072e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:639b463c827f3c2272d5a17c29a985a98a62b2383b6869bc7e21e7273c5b93b3
+size 3439