Upload folder using huggingface_hub

.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

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "O",
+    "1": "B-GF",
+    "2": "I-GF",
+    "3": "B-VF",
+    "4": "I-VF",
+    "5": "B-DF",
+    "6": "I-DF"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DF": 5,
+    "B-GF": 1,
+    "B-VF": 3,
+    "I-DF": 6,
+    "I-GF": 2,
+    "I-VF": 4,
+    "O": 0
+  },
+  "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": "4.47.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8208f7656e1a9a715256ed619392336dd51729a4383995835d2af4909508fc61
+size 1109857804

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf50448e1692c9eb0e74f0735940c66aa5821669202840535e4fe7cb1dab2a8
+size 2219828410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013d13e4b269a8648da58d2f40bf48e004388ea0631771b8c8e588ab75375092
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a0c5c299cf4cf4d2698b8536c2cc16b11a9f613f6883c3a39162f7c6bac6b5
+size 1064

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 sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,172 @@
+{
+  "best_metric": 0.2894308269023895,
+  "best_model_checkpoint": "xlm-roberta-base-ner/checkpoint-1257",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 6285,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.39777247414478917,
+      "grad_norm": 10.322513580322266,
+      "learning_rate": 1.9204455051710422e-05,
+      "loss": 0.5382,
+      "step": 500
+    },
+    {
+      "epoch": 0.7955449482895783,
+      "grad_norm": 6.790235996246338,
+      "learning_rate": 1.8408910103420846e-05,
+      "loss": 0.395,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8085669291338583,
+      "eval_loss": 0.2894308269023895,
+      "eval_precision": 0.8323174685514201,
+      "eval_recall": 0.7861342479176874,
+      "eval_runtime": 14.4214,
+      "eval_samples_per_second": 150.817,
+      "eval_steps_per_second": 18.861,
+      "step": 1257
+    },
+    {
+      "epoch": 1.1933174224343674,
+      "grad_norm": 2.2459216117858887,
+      "learning_rate": 1.7613365155131266e-05,
+      "loss": 0.3372,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5910898965791567,
+      "grad_norm": 3.4064340591430664,
+      "learning_rate": 1.681782020684169e-05,
+      "loss": 0.3252,
+      "step": 2000
+    },
+    {
+      "epoch": 1.988862370723946,
+      "grad_norm": 2.284067392349243,
+      "learning_rate": 1.602227525855211e-05,
+      "loss": 0.3229,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8084385006592578,
+      "eval_loss": 0.30411699414253235,
+      "eval_precision": 0.8293185624114389,
+      "eval_recall": 0.7885840274375306,
+      "eval_runtime": 9.1696,
+      "eval_samples_per_second": 237.197,
+      "eval_steps_per_second": 29.663,
+      "step": 2514
+    },
+    {
+      "epoch": 2.386634844868735,
+      "grad_norm": 3.480130672454834,
+      "learning_rate": 1.5226730310262532e-05,
+      "loss": 0.2692,
+      "step": 3000
+    },
+    {
+      "epoch": 2.7844073190135243,
+      "grad_norm": 9.41341781616211,
+      "learning_rate": 1.4431185361972953e-05,
+      "loss": 0.2692,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.7990613807583056,
+      "eval_loss": 0.3256344497203827,
+      "eval_precision": 0.8057285180572852,
+      "eval_recall": 0.7925036746692797,
+      "eval_runtime": 9.1536,
+      "eval_samples_per_second": 237.61,
+      "eval_steps_per_second": 29.715,
+      "step": 3771
+    },
+    {
+      "epoch": 3.1821797931583133,
+      "grad_norm": 10.631413459777832,
+      "learning_rate": 1.3635640413683375e-05,
+      "loss": 0.2578,
+      "step": 4000
+    },
+    {
+      "epoch": 3.579952267303103,
+      "grad_norm": 1.1227880716323853,
+      "learning_rate": 1.2840095465393797e-05,
+      "loss": 0.2237,
+      "step": 4500
+    },
+    {
+      "epoch": 3.977724741447892,
+      "grad_norm": 3.822526693344116,
+      "learning_rate": 1.2044550517104217e-05,
+      "loss": 0.2554,
+      "step": 5000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.8008445631248836,
+      "eval_loss": 0.34640657901763916,
+      "eval_precision": 0.8121929714069782,
+      "eval_recall": 0.7898089171974523,
+      "eval_runtime": 9.0831,
+      "eval_samples_per_second": 239.454,
+      "eval_steps_per_second": 29.946,
+      "step": 5028
+    },
+    {
+      "epoch": 4.375497215592681,
+      "grad_norm": 15.420336723327637,
+      "learning_rate": 1.1249005568814639e-05,
+      "loss": 0.2123,
+      "step": 5500
+    },
+    {
+      "epoch": 4.77326968973747,
+      "grad_norm": 2.319063663482666,
+      "learning_rate": 1.045346062052506e-05,
+      "loss": 0.2157,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.8262004492199356,
+      "eval_loss": 0.312337189912796,
+      "eval_precision": 0.8189914550487424,
+      "eval_recall": 0.8335374816266536,
+      "eval_runtime": 9.0172,
+      "eval_samples_per_second": 241.205,
+      "eval_steps_per_second": 30.164,
+      "step": 6285
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12570,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1621809589393752.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb1cb45857760114cfd11fc9057275a6e984acd43b4fbc1518715e526f36790
+size 5304