Model update

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "pdelobelle/robbert-v2-dutch-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 40000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910daa14f01d5ccf57987683c512c11dfd9ebed44e78c4bfcd01b03c71999102
+size 934225693

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de26a3cbd85a8df2791d86cc86f6effd4e23f3996c1edc0cf3012c6a309d6aa
+size 467140013

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c71aa49f7fbc9ee34a4ce29c3f8b22493dd0074f4e95650db7ac5ff4b84de20
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57471df008f47fc442d96a15e0831d3c5089476f7e646f62a2d9599992ca66f3
+size 623

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 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "special_tokens_map_file": "./robbert-v2-dutch-base/special_tokens_map.json", "name_or_path": "pdelobelle/robbert-v2-dutch-base", "tokenizer_class": "RobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": 0.5771182141045155,
+  "best_model_checkpoint": "./results_c/checkpoint-2250",
+  "epoch": 0.7100031555695803,
+  "global_step": 2250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.2758,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 0.2004,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.9320512236248462,
+      "eval_f1": 0.5911708253358925,
+      "eval_loss": 0.17533589899539948,
+      "eval_precision": 0.6431980906921241,
+      "eval_recall": 0.5469304921359716,
+      "eval_runtime": 153.0891,
+      "eval_samples_per_second": 286.67,
+      "eval_steps_per_second": 35.835,
+      "step": 250
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.8e-06,
+      "loss": 0.1794,
+      "step": 300
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.1954,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1774,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.9371097844415075,
+      "eval_f1": 0.5845875978326308,
+      "eval_loss": 0.17303350567817688,
+      "eval_precision": 0.7187268689859363,
+      "eval_recall": 0.4926433282597666,
+      "eval_runtime": 153.4653,
+      "eval_samples_per_second": 285.967,
+      "eval_steps_per_second": 35.747,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.1597,
+      "step": 600
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.1741,
+      "step": 700
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.9397757827097479,
+      "eval_f1": 0.5786704925872788,
+      "eval_loss": 0.16740337014198303,
+      "eval_precision": 0.7786357786357786,
+      "eval_recall": 0.4604261796042618,
+      "eval_runtime": 152.7876,
+      "eval_samples_per_second": 287.235,
+      "eval_steps_per_second": 35.906,
+      "step": 750
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.1676,
+      "step": 800
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.1694,
+      "step": 900
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6e-06,
+      "loss": 0.1605,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.9402770815294171,
+      "eval_f1": 0.5811091577433275,
+      "eval_loss": 0.16347511112689972,
+      "eval_precision": 0.7853131749460043,
+      "eval_recall": 0.4611872146118721,
+      "eval_runtime": 153.4862,
+      "eval_samples_per_second": 285.928,
+      "eval_steps_per_second": 35.743,
+      "step": 1000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.1659,
+      "step": 1100
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 5.2e-06,
+      "loss": 0.1524,
+      "step": 1200
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.9379300916009662,
+      "eval_f1": 0.5199154035953473,
+      "eval_loss": 0.1782103329896927,
+      "eval_precision": 0.8516166281755196,
+      "eval_recall": 0.3741755454084221,
+      "eval_runtime": 153.3211,
+      "eval_samples_per_second": 286.236,
+      "eval_steps_per_second": 35.781,
+      "step": 1250
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.1564,
+      "step": 1300
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.4e-06,
+      "loss": 0.1685,
+      "step": 1400
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1536,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "eval_accuracy": 0.9428291482477328,
+      "eval_f1": 0.642643498077197,
+      "eval_loss": 0.14973676204681396,
+      "eval_precision": 0.7327054238389087,
+      "eval_recall": 0.5722983257229832,
+      "eval_runtime": 153.7107,
+      "eval_samples_per_second": 285.51,
+      "eval_steps_per_second": 35.69,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.1698,
+      "step": 1600
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.1534,
+      "step": 1700
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.9436038827872214,
+      "eval_f1": 0.6217331499312242,
+      "eval_loss": 0.15507051348686218,
+      "eval_precision": 0.7820069204152249,
+      "eval_recall": 0.5159817351598174,
+      "eval_runtime": 153.2946,
+      "eval_samples_per_second": 286.285,
+      "eval_steps_per_second": 35.787,
+      "step": 1750
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.1637,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.1575,
+      "step": 1900
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1669,
+      "step": 2000
+    },
+    {
+      "epoch": 0.63,
+      "eval_accuracy": 0.9451989244861687,
+      "eval_f1": 0.641419412554048,
+      "eval_loss": 0.14974650740623474,
+      "eval_precision": 0.7779385171790235,
+      "eval_recall": 0.545662100456621,
+      "eval_runtime": 153.6101,
+      "eval_samples_per_second": 285.697,
+      "eval_steps_per_second": 35.714,
+      "step": 2000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1482,
+      "step": 2100
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.1449,
+      "step": 2200
+    },
+    {
+      "epoch": 0.71,
+      "eval_accuracy": 0.9451989244861687,
+      "eval_f1": 0.6542056074766355,
+      "eval_loss": 0.1456586718559265,
+      "eval_precision": 0.7550614005974112,
+      "eval_recall": 0.5771182141045155,
+      "eval_runtime": 152.2253,
+      "eval_samples_per_second": 288.296,
+      "eval_steps_per_second": 36.039,
+      "step": 2250
+    }
+  ],
+  "max_steps": 2500,
+  "num_train_epochs": 1,
+  "total_flos": 4567250254458720.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35cc5616b86e51cb54a61c16200f9e508724750d248536b72cc00aab9cf690c
+size 2927