copy paste

.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

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: single_label_unbiased_relevant_profession
+  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. -->
+
+# single_label_unbiased_relevant_profession
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5581
+- Acc At K: 0.8934
+- Acc: 0.5742
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Acc At K | Acc    |
+|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|
+| 4.1013        | 0.5   | 22700  | 2.6410          | 0.7356   | 0.4504 |
+| 2.3359        | 1.0   | 45400  | 2.1112          | 0.8115   | 0.4979 |
+| 1.9045        | 1.5   | 68100  | 1.9027          | 0.8428   | 0.5240 |
+| 1.7084        | 2.0   | 90800  | 1.7826          | 0.8607   | 0.5340 |
+| 1.5155        | 2.5   | 113500 | 1.7117          | 0.8711   | 0.5444 |
+| 1.4211        | 3.0   | 136200 | 1.6643          | 0.8782   | 0.5493 |
+| 1.2865        | 3.5   | 158900 | 1.6342          | 0.8812   | 0.5568 |
+| 1.2357        | 4.0   | 181600 | 1.6077          | 0.8852   | 0.5588 |
+| 1.1303        | 4.5   | 204300 | 1.6023          | 0.8873   | 0.5632 |
+| 1.0987        | 5.0   | 227000 | 1.5784          | 0.8896   | 0.5652 |
+| 1.0186        | 5.5   | 249700 | 1.5782          | 0.8904   | 0.5673 |
+| 0.9982        | 6.0   | 272400 | 1.5712          | 0.8914   | 0.5707 |
+| 0.9404        | 6.5   | 295100 | 1.5685          | 0.8920   | 0.5710 |
+| 0.9263        | 7.0   | 317800 | 1.5615          | 0.8925   | 0.5725 |
+| 0.8839        | 7.5   | 340500 | 1.5603          | 0.8929   | 0.5741 |
+| 0.878         | 8.0   | 363200 | 1.5581          | 0.8934   | 0.5742 |
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 2.0.0+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3

label_to_ids.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90daaab57f699b8a87b5a5c0d483b1f0bdf07b3b4ae53c8be5efaac8df1b0f12
+size 215823

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d480c9464f4daba28debbda04a3eb18547e0ed0ab908b4c2cbba19b5a82b712c
+size 2265359813

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d447ef6303c43f9940675e81d43f3e20e35f97097b908270af7b4adbe1ddd163
+size 1132694197

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90bd02baf6214ae01f1b407108ebdacb7280385a5871c8a223bb4689636d7cb
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc266f42cee6a5338936cd9429837a516919132ca70cf301a4ba6a3766b45a84
+size 627

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f620ed598f02c6e9ad8bd7c093e0bf1f883f0a113b315e3299ae7d1b85581a
+size 17082912

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "xlm-roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.929340763419308,
+  "global_step": 360000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.8750027532433207e-05,
+      "loss": 4.1013,
+      "step": 22700
+    },
+    {
+      "epoch": 0.5,
+      "eval_acc": 0.45036102325248506,
+      "eval_acc_at_k": 0.7356285768554228,
+      "eval_loss": 2.6409595012664795,
+      "eval_runtime": 780.8248,
+      "eval_samples_per_second": 465.243,
+      "eval_steps_per_second": 7.271,
+      "step": 22700
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.7500055064866416e-05,
+      "loss": 2.3359,
+      "step": 45400
+    },
+    {
+      "epoch": 1.0,
+      "eval_acc": 0.4979065331032034,
+      "eval_acc_at_k": 0.8115219132718369,
+      "eval_loss": 2.111237049102783,
+      "eval_runtime": 763.2781,
+      "eval_samples_per_second": 475.938,
+      "eval_steps_per_second": 7.438,
+      "step": 45400
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.625008259729962e-05,
+      "loss": 1.9045,
+      "step": 68100
+    },
+    {
+      "epoch": 1.5,
+      "eval_acc": 0.5239503073446141,
+      "eval_acc_at_k": 0.8428344523264872,
+      "eval_loss": 1.902678370475769,
+      "eval_runtime": 753.8194,
+      "eval_samples_per_second": 481.91,
+      "eval_steps_per_second": 7.531,
+      "step": 68100
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.5000110129732826e-05,
+      "loss": 1.7084,
+      "step": 90800
+    },
+    {
+      "epoch": 2.0,
+      "eval_acc": 0.5340171166037663,
+      "eval_acc_at_k": 0.8607108152821707,
+      "eval_loss": 1.7825987339019775,
+      "eval_runtime": 756.3653,
+      "eval_samples_per_second": 480.288,
+      "eval_steps_per_second": 7.506,
+      "step": 90800
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.3750137662166031e-05,
+      "loss": 1.5155,
+      "step": 113500
+    },
+    {
+      "epoch": 2.5,
+      "eval_acc": 0.5443592009315308,
+      "eval_acc_at_k": 0.8710528996099353,
+      "eval_loss": 1.7116812467575073,
+      "eval_runtime": 757.8065,
+      "eval_samples_per_second": 479.374,
+      "eval_steps_per_second": 7.491,
+      "step": 113500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.2500165194599238e-05,
+      "loss": 1.4211,
+      "step": 136200
+    },
+    {
+      "epoch": 3.0,
+      "eval_acc": 0.5492563444021439,
+      "eval_acc_at_k": 0.878157749130819,
+      "eval_loss": 1.6643491983413696,
+      "eval_runtime": 759.0909,
+      "eval_samples_per_second": 478.563,
+      "eval_steps_per_second": 7.479,
+      "step": 136200
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 1.1250192727032445e-05,
+      "loss": 1.2865,
+      "step": 158900
+    },
+    {
+      "epoch": 3.5,
+      "eval_acc": 0.556774106525946,
+      "eval_acc_at_k": 0.8812353243979046,
+      "eval_loss": 1.6341607570648193,
+      "eval_runtime": 756.5457,
+      "eval_samples_per_second": 480.173,
+      "eval_steps_per_second": 7.504,
+      "step": 158900
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.0000220259465652e-05,
+      "loss": 1.2357,
+      "step": 181600
+    },
+    {
+      "epoch": 4.0,
+      "eval_acc": 0.5588056365323049,
+      "eval_acc_at_k": 0.8852185546407247,
+      "eval_loss": 1.6077438592910767,
+      "eval_runtime": 755.3821,
+      "eval_samples_per_second": 480.913,
+      "eval_steps_per_second": 7.515,
+      "step": 181600
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 8.750247791898858e-06,
+      "loss": 1.1303,
+      "step": 204300
+    },
+    {
+      "epoch": 4.5,
+      "eval_acc": 0.5632485761397076,
+      "eval_acc_at_k": 0.8873409254197256,
+      "eval_loss": 1.6022595167160034,
+      "eval_runtime": 756.1367,
+      "eval_samples_per_second": 480.433,
+      "eval_steps_per_second": 7.508,
+      "step": 204300
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 7.500275324332064e-06,
+      "loss": 1.0987,
+      "step": 227000
+    },
+    {
+      "epoch": 5.0,
+      "eval_acc": 0.5652388148857747,
+      "eval_acc_at_k": 0.8896284612398939,
+      "eval_loss": 1.5783677101135254,
+      "eval_runtime": 753.7746,
+      "eval_samples_per_second": 481.938,
+      "eval_steps_per_second": 7.531,
+      "step": 227000
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 6.25030285676527e-06,
+      "loss": 1.0186,
+      "step": 249700
+    },
+    {
+      "epoch": 5.5,
+      "eval_acc": 0.5673474219113449,
+      "eval_acc_at_k": 0.8903992314320084,
+      "eval_loss": 1.5781617164611816,
+      "eval_runtime": 755.2261,
+      "eval_samples_per_second": 481.012,
+      "eval_steps_per_second": 7.517,
+      "step": 249700
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 5.000330389198477e-06,
+      "loss": 0.9982,
+      "step": 272400
+    },
+    {
+      "epoch": 6.0,
+      "eval_acc": 0.5707277997539041,
+      "eval_acc_at_k": 0.8913929744296989,
+      "eval_loss": 1.5712472200393677,
+      "eval_runtime": 755.7584,
+      "eval_samples_per_second": 480.673,
+      "eval_steps_per_second": 7.512,
+      "step": 272400
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 3.7503579216316827e-06,
+      "loss": 0.9404,
+      "step": 295100
+    },
+    {
+      "epoch": 6.5,
+      "eval_acc": 0.5709975693211442,
+      "eval_acc_at_k": 0.8920068378327043,
+      "eval_loss": 1.5684970617294312,
+      "eval_runtime": 753.639,
+      "eval_samples_per_second": 482.025,
+      "eval_steps_per_second": 7.533,
+      "step": 295100
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.500385454064889e-06,
+      "loss": 0.9263,
+      "step": 317800
+    },
+    {
+      "epoch": 7.0,
+      "eval_acc": 0.57247029093822,
+      "eval_acc_at_k": 0.8925023329562065,
+      "eval_loss": 1.5614935159683228,
+      "eval_runtime": 759.0312,
+      "eval_samples_per_second": 478.601,
+      "eval_steps_per_second": 7.479,
+      "step": 317800
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 1.250412986498095e-06,
+      "loss": 0.8839,
+      "step": 340500
+    },
+    {
+      "epoch": 7.5,
+      "eval_acc": 0.5740751445882298,
+      "eval_acc_at_k": 0.8929262565618694,
+      "eval_loss": 1.5602914094924927,
+      "eval_runtime": 762.0808,
+      "eval_samples_per_second": 476.686,
+      "eval_steps_per_second": 7.449,
+      "step": 340500
+    }
+  ],
+  "max_steps": 363208,
+  "num_train_epochs": 8,
+  "total_flos": 8.029681855685318e+17,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8887aadbdbf0e95ece37ccd6d4b294d27d54e53293287a89603855f7b5894389
+size 3899

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cefa0240b97317d3734b730ab9263c41bb62633a28ec6d94ea3015d5d6215b50
+size 1132694197

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f620ed598f02c6e9ad8bd7c093e0bf1f883f0a113b315e3299ae7d1b85581a
+size 17082912

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "xlm-roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8887aadbdbf0e95ece37ccd6d4b294d27d54e53293287a89603855f7b5894389
+size 3899