Initial model release

README.md

@@ -1,3 +1,61 @@
 ---
 license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [ukr-models/xlm-roberta-base-uk](https://huggingface.co/ukr-models/xlm-roberta-base-uk) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4778
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.4526        | 1.0   | 650  | 1.3631          |
+| 1.3317        | 2.0   | 1300 | 1.2229          |
+| 1.0693        | 3.0   | 1950 | 1.2184          |
+| 0.6851        | 4.0   | 2600 | 1.3171          |
+| 0.5594        | 5.0   | 3250 | 1.3893          |
+| 0.4954        | 6.0   | 3900 | 1.4778          |
+
+
+### Framework versions
+
+- Transformers 4.19.2
+- Pytorch 1.11.0
+- Datasets 2.2.2
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "ukr-models/xlm-roberta-base-uk",
+  "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": "4.19.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 31274
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c0d00b7b006c61360316f26496f32e3da70fffa6ca29d6ff74b703eae75f15
+size 437957041

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8aa19cb4bb4c090199aa04e6075b0e5f8b6b423132c971304fbd5a579cc022e
+size 14503

runs/Jun01_22-23-16_robinhad-pc/1654111398.2056837/events.out.tfevents.1654111398.robinhad-pc.1294.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334d23dec731faef2dc603ef4642f4741e2f33451219f87d684fcf7174998cd8
+size 5138

runs/Jun01_22-23-16_robinhad-pc/events.out.tfevents.1654111398.robinhad-pc.1294.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:607bba7dbf9bb9d59789e8c1c9834c31fd3a4524cdf8411a968c355f5ad163ef
+size 6642

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfa595f7e4790ae011bb385a1f9920f912c53e812fdd8eb4dc63347457849ad
+size 623

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e60d59d103a3650d675c36c75b3a9c4b47e2c494eeea699f21ccd6e055f78feb
+size 854151

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": true}}

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"}, "sp_model_kwargs": {}, "extra_ids": 0, "special_tokens_map_file": "./xlm-roberta-base-uk/special_tokens_map.json", "name_or_path": "ukr-models/xlm-roberta-base-uk", "tokenizer_class": "XLMRobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "global_step": 3900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7435897435897438e-05,
+      "loss": 2.4526,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.363105058670044,
+      "eval_runtime": 2.6865,
+      "eval_samples_per_second": 203.236,
+      "eval_steps_per_second": 13.028,
+      "step": 650
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.4871794871794874e-05,
+      "loss": 1.3317,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.222852349281311,
+      "eval_runtime": 2.6807,
+      "eval_samples_per_second": 203.678,
+      "eval_steps_per_second": 13.056,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 1.0693,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2184115648269653,
+      "eval_runtime": 2.7363,
+      "eval_samples_per_second": 199.542,
+      "eval_steps_per_second": 12.791,
+      "step": 1950
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 9.743589743589744e-06,
+      "loss": 0.8692,
+      "step": 2000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 0.6851,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.317087173461914,
+      "eval_runtime": 2.4998,
+      "eval_samples_per_second": 218.418,
+      "eval_steps_per_second": 14.001,
+      "step": 2600
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.5594,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.3892898559570312,
+      "eval_runtime": 2.5134,
+      "eval_samples_per_second": 217.235,
+      "eval_steps_per_second": 13.925,
+      "step": 3250
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 2.0512820512820513e-06,
+      "loss": 0.4954,
+      "step": 3500
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.4778178930282593,
+      "eval_runtime": 2.7344,
+      "eval_samples_per_second": 199.677,
+      "eval_steps_per_second": 12.8,
+      "step": 3900
+    }
+  ],
+  "max_steps": 3900,
+  "num_train_epochs": 6,
+  "total_flos": 1.2212226519570432e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d85c00a0cfae9edcf9e4d58debf8c3d736a3a24527f3b51cd2c677c002605a0
+size 3183