Upload 12 files

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "EMBEDDIA/est-roberta",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "I-UNK",
+    "2": "I-PROD",
+    "3": "I-PER",
+    "4": "I-ORG",
+    "5": "I-MUU",
+    "6": "I-LOC",
+    "7": "I-GEP",
+    "8": "I-EVE",
+    "9": "B-UNK",
+    "10": "B-PROD",
+    "11": "B-PER",
+    "12": "B-ORG",
+    "13": "B-MUU",
+    "14": "B-LOC",
+    "15": "B-GEP",
+    "16": "B-EVE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EVE": 16,
+    "B-GEP": 15,
+    "B-LOC": 14,
+    "B-MUU": 13,
+    "B-ORG": 12,
+    "B-PER": 11,
+    "B-PROD": 10,
+    "B-UNK": 9,
+    "I-EVE": 8,
+    "I-GEP": 7,
+    "I-LOC": 6,
+    "I-MUU": 5,
+    "I-ORG": 4,
+    "I-PER": 3,
+    "I-PROD": 2,
+    "I-UNK": 1,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 40005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ccac48063ae55585e451f362f01a996d613aa879d25cdd2da4ebcd074b3e9e
+size 464777660

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86bc28e16647ae0f011194122976d10ad414abc558a77ad8fb5c52758d6ed38
+size 929673914

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d00a39203097e4d8f49e7e5687171694b5b679a1c06aa0eb44acdd3931ecfa
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b883480ebc3636fcf97045d201b18945b8223a8bbbdcf103c8fabf4ae39cdeed
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8e58de78a9d04ab5f4b227a1f313edab80352cfbeb999dc9de88beb1a87279
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4efafd8f3bf5547faaa9561ce37181ee61b2aada8bdcee7ad5f2aac10a1a76
+size 935725

special_tokens_map.json

@@ -0,0 +1,55 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,80 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "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>NOTUSED",
+      "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
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "padding": "max_length",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "truncation": "longest_first",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,251 @@
+{
+  "best_metric": 0.7874266388142842,
+  "best_model_checkpoint": "./results/models/est-roberta/Combined/trained_for_3/checkpoint-5634",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5634,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26624068157614483,
+      "grad_norm": 2.042728900909424,
+      "learning_rate": 4.559815406460774e-05,
+      "loss": 0.2505,
+      "step": 500
+    },
+    {
+      "epoch": 0.5324813631522897,
+      "grad_norm": 1.1207706928253174,
+      "learning_rate": 4.116080937167199e-05,
+      "loss": 0.1009,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 2.805177927017212,
+      "learning_rate": 3.6723464678736245e-05,
+      "loss": 0.0905,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_EVE F1": 0.389937106918239,
+      "eval_EVE Number": 71,
+      "eval_EVE Precision": 0.3522727272727273,
+      "eval_EVE Recall": 0.43661971830985913,
+      "eval_GEP F1": 0.6512141280353201,
+      "eval_GEP Number": 431,
+      "eval_GEP Precision": 0.6210526315789474,
+      "eval_GEP Recall": 0.6844547563805105,
+      "eval_LOC F1": 0.7064760302775441,
+      "eval_LOC Number": 663,
+      "eval_LOC Precision": 0.7984790874524715,
+      "eval_LOC Recall": 0.6334841628959276,
+      "eval_MUU F1": 0.0,
+      "eval_MUU Number": 9,
+      "eval_MUU Precision": 0.0,
+      "eval_MUU Recall": 0.0,
+      "eval_ORG F1": 0.5944919278252612,
+      "eval_ORG Number": 446,
+      "eval_ORG Precision": 0.515650741350906,
+      "eval_ORG Recall": 0.7017937219730942,
+      "eval_PER F1": 0.9311899627524014,
+      "eval_PER Number": 2527,
+      "eval_PER Precision": 0.9226884226884227,
+      "eval_PER Recall": 0.9398496240601504,
+      "eval_PROD F1": 0.5536967080410146,
+      "eval_PROD Number": 876,
+      "eval_PROD Precision": 0.5250767656090072,
+      "eval_PROD Recall": 0.5856164383561644,
+      "eval_UNK F1": 0.0,
+      "eval_UNK Number": 49,
+      "eval_UNK Precision": 0.0,
+      "eval_UNK Recall": 0.0,
+      "eval_accuracy": 0.9708692828648298,
+      "eval_f1": 0.7649966081984688,
+      "eval_loss": 0.12275230139493942,
+      "eval_precision": 0.7522393748808843,
+      "eval_recall": 0.7781940063091483,
+      "eval_runtime": 9.3902,
+      "eval_samples_per_second": 421.185,
+      "eval_steps_per_second": 26.411,
+      "step": 1878
+    },
+    {
+      "epoch": 1.0649627263045793,
+      "grad_norm": 1.198572039604187,
+      "learning_rate": 3.22861199858005e-05,
+      "loss": 0.0718,
+      "step": 2000
+    },
+    {
+      "epoch": 1.3312034078807242,
+      "grad_norm": 1.9659144878387451,
+      "learning_rate": 2.7848775292864754e-05,
+      "loss": 0.0472,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 1.3795360326766968,
+      "learning_rate": 2.3411430599929004e-05,
+      "loss": 0.0464,
+      "step": 3000
+    },
+    {
+      "epoch": 1.863684771033014,
+      "grad_norm": 2.0997838973999023,
+      "learning_rate": 1.8974085906993255e-05,
+      "loss": 0.0382,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_EVE F1": 0.637037037037037,
+      "eval_EVE Number": 71,
+      "eval_EVE Precision": 0.671875,
+      "eval_EVE Recall": 0.6056338028169014,
+      "eval_GEP F1": 0.6681564245810055,
+      "eval_GEP Number": 431,
+      "eval_GEP Precision": 0.6443965517241379,
+      "eval_GEP Recall": 0.6937354988399071,
+      "eval_LOC F1": 0.6912650602409638,
+      "eval_LOC Number": 663,
+      "eval_LOC Precision": 0.6902255639097744,
+      "eval_LOC Recall": 0.6923076923076923,
+      "eval_MUU F1": 0.0,
+      "eval_MUU Number": 9,
+      "eval_MUU Precision": 0.0,
+      "eval_MUU Recall": 0.0,
+      "eval_ORG F1": 0.6564551422319476,
+      "eval_ORG Number": 446,
+      "eval_ORG Precision": 0.6410256410256411,
+      "eval_ORG Recall": 0.672645739910314,
+      "eval_PER F1": 0.9397979797979797,
+      "eval_PER Number": 2527,
+      "eval_PER Precision": 0.9599669830788279,
+      "eval_PER Recall": 0.9204590423426988,
+      "eval_PROD F1": 0.5508625817965498,
+      "eval_PROD Number": 876,
+      "eval_PROD Precision": 0.5751552795031056,
+      "eval_PROD Recall": 0.5285388127853882,
+      "eval_UNK F1": 0.0,
+      "eval_UNK Number": 49,
+      "eval_UNK Precision": 0.0,
+      "eval_UNK Recall": 0.0,
+      "eval_accuracy": 0.9725259433024532,
+      "eval_f1": 0.7810460797108723,
+      "eval_loss": 0.1317518949508667,
+      "eval_precision": 0.7956637349151156,
+      "eval_recall": 0.7669558359621451,
+      "eval_runtime": 9.0481,
+      "eval_samples_per_second": 437.11,
+      "eval_steps_per_second": 27.409,
+      "step": 3756
+    },
+    {
+      "epoch": 2.1299254526091587,
+      "grad_norm": 0.37376314401626587,
+      "learning_rate": 1.453674121405751e-05,
+      "loss": 0.0351,
+      "step": 4000
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 0.17092548310756683,
+      "learning_rate": 1.0099396521121762e-05,
+      "loss": 0.0224,
+      "step": 4500
+    },
+    {
+      "epoch": 2.6624068157614484,
+      "grad_norm": 1.0416895151138306,
+      "learning_rate": 5.662051828186014e-06,
+      "loss": 0.0228,
+      "step": 5000
+    },
+    {
+      "epoch": 2.928647497337593,
+      "grad_norm": 2.613699436187744,
+      "learning_rate": 1.2247071352502663e-06,
+      "loss": 0.0207,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_EVE F1": 0.6153846153846154,
+      "eval_EVE Number": 71,
+      "eval_EVE Precision": 0.6111111111111112,
+      "eval_EVE Recall": 0.6197183098591549,
+      "eval_GEP F1": 0.6620825147347741,
+      "eval_GEP Number": 431,
+      "eval_GEP Precision": 0.5741056218057922,
+      "eval_GEP Recall": 0.7819025522041764,
+      "eval_LOC F1": 0.6327782646801051,
+      "eval_LOC Number": 663,
+      "eval_LOC Precision": 0.7552301255230126,
+      "eval_LOC Recall": 0.5444947209653092,
+      "eval_MUU F1": 0.0,
+      "eval_MUU Number": 9,
+      "eval_MUU Precision": 0.0,
+      "eval_MUU Recall": 0.0,
+      "eval_ORG F1": 0.6534446764091859,
+      "eval_ORG Number": 446,
+      "eval_ORG Precision": 0.611328125,
+      "eval_ORG Recall": 0.7017937219730942,
+      "eval_PER F1": 0.9506391347099312,
+      "eval_PER Number": 2527,
+      "eval_PER Precision": 0.9448788115715403,
+      "eval_PER Recall": 0.9564701226751088,
+      "eval_PROD F1": 0.5890909090909091,
+      "eval_PROD Number": 876,
+      "eval_PROD Precision": 0.627906976744186,
+      "eval_PROD Recall": 0.5547945205479452,
+      "eval_UNK F1": 0.0,
+      "eval_UNK Number": 49,
+      "eval_UNK Precision": 0.0,
+      "eval_UNK Recall": 0.0,
+      "eval_accuracy": 0.9744211628430943,
+      "eval_f1": 0.7874266388142842,
+      "eval_loss": 0.13450972735881805,
+      "eval_precision": 0.7946195543063642,
+      "eval_recall": 0.7803627760252366,
+      "eval_runtime": 13.8279,
+      "eval_samples_per_second": 286.015,
+      "eval_steps_per_second": 17.935,
+      "step": 5634
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5634,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5888794287248640.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d46d869b19d5d2c4a64435a2a7cae898dbe3aa17a08988fd66872903e558cd0
+size 5368