Added files

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "/data/models/xlmr-base-cont-is-bsz160k-steps225k/xlmr-base-cont-is-bsz160k-steps225k-hf",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "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 sha256:1816e88264f5173cca414488fcd74ebcb8076c6d9196743aa3646a33a49fb20b
+size 1109918449

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": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "/data/models/xlmr-base-cont-is-bsz160k-steps225k/xlmr-base-cont-is-bsz160k-steps225k-hf", "tokenizer_class": "RobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,280 @@
+{
+  "best_metric": 0.3449392712550607,
+  "best_model_checkpoint": "xlmr-base-cont-is-bsz160k-steps225k-hf-finetuned-iec-token-errors-uniq-42/checkpoint-17080",
+  "epoch": 5.0,
+  "global_step": 17080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9414519906323187e-05,
+      "loss": 0.2543,
+      "step": 500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.8829039812646373e-05,
+      "loss": 0.1982,
+      "step": 1000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8243559718969555e-05,
+      "loss": 0.1951,
+      "step": 1500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.765807962529274e-05,
+      "loss": 0.1787,
+      "step": 2000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7072599531615927e-05,
+      "loss": 0.1804,
+      "step": 2500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6487119437939112e-05,
+      "loss": 0.1833,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9657446996355014,
+      "eval_f1": 0.2873458792991564,
+      "eval_loss": 0.15018649399280548,
+      "eval_precision": 0.6944792973651192,
+      "eval_recall": 0.18114874815905743,
+      "eval_runtime": 5.7645,
+      "eval_samples_per_second": 857.316,
+      "eval_steps_per_second": 53.604,
+      "step": 3416
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5901639344262295e-05,
+      "loss": 0.1703,
+      "step": 3500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.531615925058548e-05,
+      "loss": 0.1605,
+      "step": 4000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4730679156908668e-05,
+      "loss": 0.1577,
+      "step": 4500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.4145199063231852e-05,
+      "loss": 0.1578,
+      "step": 5000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.3559718969555036e-05,
+      "loss": 0.1526,
+      "step": 5500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.2974238875878221e-05,
+      "loss": 0.1513,
+      "step": 6000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.2388758782201407e-05,
+      "loss": 0.1557,
+      "step": 6500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9658519051042416,
+      "eval_f1": 0.2957278076234331,
+      "eval_loss": 0.15432876348495483,
+      "eval_precision": 0.677211482132396,
+      "eval_recall": 0.1891670757650139,
+      "eval_runtime": 5.6853,
+      "eval_samples_per_second": 869.262,
+      "eval_steps_per_second": 54.351,
+      "step": 6832
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.1803278688524591e-05,
+      "loss": 0.1516,
+      "step": 7000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.1217798594847775e-05,
+      "loss": 0.1301,
+      "step": 7500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.0632318501170963e-05,
+      "loss": 0.1321,
+      "step": 8000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.0046838407494147e-05,
+      "loss": 0.1262,
+      "step": 8500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 9.461358313817332e-06,
+      "loss": 0.1365,
+      "step": 9000
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 8.875878220140516e-06,
+      "loss": 0.1339,
+      "step": 9500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 8.290398126463702e-06,
+      "loss": 0.1267,
+      "step": 10000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9658077616759367,
+      "eval_f1": 0.32741425443930916,
+      "eval_loss": 0.15831299126148224,
+      "eval_precision": 0.6376125059213643,
+      "eval_recall": 0.22025855015545737,
+      "eval_runtime": 5.7385,
+      "eval_samples_per_second": 861.2,
+      "eval_steps_per_second": 53.847,
+      "step": 10248
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 7.704918032786886e-06,
+      "loss": 0.1247,
+      "step": 10500
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 7.119437939110071e-06,
+      "loss": 0.1106,
+      "step": 11000
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 6.5339578454332556e-06,
+      "loss": 0.1079,
+      "step": 11500
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 5.94847775175644e-06,
+      "loss": 0.1124,
+      "step": 12000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 5.362997658079626e-06,
+      "loss": 0.1091,
+      "step": 12500
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 4.77751756440281e-06,
+      "loss": 0.1141,
+      "step": 13000
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 4.192037470725996e-06,
+      "loss": 0.1085,
+      "step": 13500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9649879551502768,
+      "eval_f1": 0.3396051103368177,
+      "eval_loss": 0.16941741108894348,
+      "eval_precision": 0.5850340136054422,
+      "eval_recall": 0.2392407134675176,
+      "eval_runtime": 5.6434,
+      "eval_samples_per_second": 875.708,
+      "eval_steps_per_second": 54.754,
+      "step": 13664
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 3.6065573770491806e-06,
+      "loss": 0.1036,
+      "step": 14000
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 3.0210772833723655e-06,
+      "loss": 0.0961,
+      "step": 14500
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 2.4355971896955503e-06,
+      "loss": 0.0959,
+      "step": 15000
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 1.8501170960187356e-06,
+      "loss": 0.0958,
+      "step": 15500
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 1.2646370023419204e-06,
+      "loss": 0.0949,
+      "step": 16000
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 6.791569086651055e-07,
+      "loss": 0.0946,
+      "step": 16500
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 9.367681498829041e-08,
+      "loss": 0.0919,
+      "step": 17000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9652086722918006,
+      "eval_f1": 0.3449392712550607,
+      "eval_loss": 0.1819370836019516,
+      "eval_precision": 0.5883977900552486,
+      "eval_recall": 0.24398625429553264,
+      "eval_runtime": 5.7966,
+      "eval_samples_per_second": 852.569,
+      "eval_steps_per_second": 53.307,
+      "step": 17080
+    }
+  ],
+  "max_steps": 17080,
+  "num_train_epochs": 5,
+  "total_flos": 9598023469073754.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77a7361c36c93212a75dc525380c431e0dca5a710a2757688c68ab61f658cf7
+size 3055