Training in progress, step 500

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "knurm/xlm-roberta-base-finetuned-est",
+  "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": "4.19.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97e8d824a5bcbea91b6f5f63b588cd3e9100d1357108a341a260f8a8ed2fc8d
+size 1109889457

runs/May30_10-48-28_falcon3/1653896918.5142047/events.out.tfevents.1653896918.falcon3.28351.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a729052597363cd8053fc53bfba6a48e50218ae92d56e85ea730fb86fb9aaa7
+size 5186

runs/May30_10-48-28_falcon3/events.out.tfevents.1653896918.falcon3.28351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dded15de39fc104b7f308d8526a9587d27c3cf0442fb2a1b655b1c417588f350
+size 3631

runs/May30_10-59-30_falcon4/1653897579.087929/events.out.tfevents.1653897579.falcon4.16892.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6092b7c37aec3020ccb23c8cf351036f894f68ec8831a5562f66380da4fd6b
+size 5186

runs/May30_10-59-30_falcon4/events.out.tfevents.1653897579.falcon4.16892.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac65fb0d450a16e286403debeec161852c427ab3a9c5bb0c76fffa2e241e6b5
+size 3788

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87df8b5822e8de40a826123aac6fcd969f604772ff7754eb334529840f8501bc
+size 17082925

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": "knurm/xlm-roberta-base-finetuned-est", "tokenizer_class": "XLMRobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa4a02273c12544554fa50cc3631535a2dfe078a0159a4340ec9aff715771644
+size 3247