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

README.md

@@ -0,0 +1,108 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: pos_final_xlm_fr
+  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. -->
+
+# pos_final_xlm_fr
+
+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: 0.1022
+- Precision: 0.9744
+- Recall: 0.9746
+- F1: 0.9745
+- Accuracy: 0.9769
+
+## 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: 5e-05
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 40.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.95  | 14   | 3.5537          | 0.0       | 0.0    | 0.0    | 0.0026   |
+| No log        | 1.95  | 28   | 3.4536          | 0.0153    | 0.0024 | 0.0042 | 0.0049   |
+| No log        | 2.95  | 42   | 3.1247          | 0.2395    | 0.1816 | 0.2066 | 0.2843   |
+| No log        | 3.95  | 56   | 2.5988          | 0.4342    | 0.3539 | 0.3900 | 0.4543   |
+| No log        | 4.95  | 70   | 2.0168          | 0.5125    | 0.4086 | 0.4547 | 0.5148   |
+| No log        | 5.95  | 84   | 1.4838          | 0.5959    | 0.5180 | 0.5543 | 0.6086   |
+| No log        | 6.95  | 98   | 0.9300          | 0.7905    | 0.7619 | 0.7759 | 0.7981   |
+| No log        | 7.95  | 112  | 0.4874          | 0.9111    | 0.9078 | 0.9094 | 0.9147   |
+| No log        | 8.95  | 126  | 0.2940          | 0.9372    | 0.9368 | 0.9370 | 0.9396   |
+| No log        | 9.95  | 140  | 0.2086          | 0.9471    | 0.9482 | 0.9476 | 0.9490   |
+| No log        | 10.95 | 154  | 0.1688          | 0.9594    | 0.9610 | 0.9602 | 0.9627   |
+| No log        | 11.95 | 168  | 0.1450          | 0.9624    | 0.9641 | 0.9632 | 0.9659   |
+| No log        | 12.95 | 182  | 0.1334          | 0.9651    | 0.9669 | 0.9660 | 0.9686   |
+| No log        | 13.95 | 196  | 0.1213          | 0.9674    | 0.9685 | 0.9679 | 0.9702   |
+| No log        | 14.95 | 210  | 0.1155          | 0.9684    | 0.9696 | 0.9690 | 0.9718   |
+| No log        | 15.95 | 224  | 0.1093          | 0.9707    | 0.9712 | 0.9709 | 0.9734   |
+| No log        | 16.95 | 238  | 0.1059          | 0.9710    | 0.9716 | 0.9713 | 0.9739   |
+| No log        | 17.95 | 252  | 0.1046          | 0.9711    | 0.9716 | 0.9714 | 0.9740   |
+| No log        | 18.95 | 266  | 0.1014          | 0.9719    | 0.9724 | 0.9722 | 0.9745   |
+| No log        | 19.95 | 280  | 0.1003          | 0.9715    | 0.9722 | 0.9718 | 0.9742   |
+| No log        | 20.95 | 294  | 0.0987          | 0.9724    | 0.9730 | 0.9727 | 0.9751   |
+| No log        | 21.95 | 308  | 0.0971          | 0.9722    | 0.9728 | 0.9725 | 0.9750   |
+| No log        | 22.95 | 322  | 0.0968          | 0.9724    | 0.9735 | 0.9730 | 0.9754   |
+| No log        | 23.95 | 336  | 0.0954          | 0.9728    | 0.9736 | 0.9732 | 0.9756   |
+| No log        | 24.95 | 350  | 0.0967          | 0.9722    | 0.9731 | 0.9727 | 0.9752   |
+| No log        | 25.95 | 364  | 0.0965          | 0.9735    | 0.9744 | 0.9739 | 0.9763   |
+| No log        | 26.95 | 378  | 0.0963          | 0.9725    | 0.9735 | 0.9730 | 0.9757   |
+| No log        | 27.95 | 392  | 0.0972          | 0.9728    | 0.9738 | 0.9733 | 0.9759   |
+| No log        | 28.95 | 406  | 0.0987          | 0.9736    | 0.9745 | 0.9740 | 0.9766   |
+| No log        | 29.95 | 420  | 0.0994          | 0.9737    | 0.9742 | 0.9740 | 0.9764   |
+| No log        | 30.95 | 434  | 0.0985          | 0.9737    | 0.9741 | 0.9739 | 0.9764   |
+| No log        | 31.95 | 448  | 0.1022          | 0.9744    | 0.9746 | 0.9745 | 0.9769   |
+| No log        | 32.95 | 462  | 0.1020          | 0.9740    | 0.9744 | 0.9742 | 0.9767   |
+| No log        | 33.95 | 476  | 0.1055          | 0.9730    | 0.9738 | 0.9734 | 0.9758   |
+| No log        | 34.95 | 490  | 0.1068          | 0.9732    | 0.9742 | 0.9737 | 0.9760   |
+| 0.6768        | 35.95 | 504  | 0.1085          | 0.9737    | 0.9740 | 0.9739 | 0.9764   |
+| 0.6768        | 36.95 | 518  | 0.1088          | 0.9735    | 0.9743 | 0.9739 | 0.9764   |
+| 0.6768        | 37.95 | 532  | 0.1100          | 0.9739    | 0.9744 | 0.9742 | 0.9768   |
+| 0.6768        | 38.95 | 546  | 0.1107          | 0.9739    | 0.9745 | 0.9742 | 0.9767   |
+| 0.6768        | 39.95 | 560  | 0.1115          | 0.9740    | 0.9747 | 0.9744 | 0.9769   |
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- Pytorch 1.12.0
+- Datasets 2.18.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 39.95,
+    "eval_accuracy": 0.9768565163278611,
+    "eval_f1": 0.9745301568430197,
+    "eval_loss": 0.10217323899269104,
+    "eval_precision": 0.9744261895327216,
+    "eval_recall": 0.9746341463414634,
+    "eval_runtime": 2.1359,
+    "eval_samples": 1431,
+    "eval_samples_per_second": 776.71,
+    "eval_steps_per_second": 3.277,
+    "train_loss": 0.6079375518219812,
+    "train_runtime": 701.2451,
+    "train_samples": 14928,
+    "train_samples_per_second": 851.514,
+    "train_steps_per_second": 0.799
+}

config.json

@@ -0,0 +1,111 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "pos",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "VER:pper",
+    "1": "#",
+    "2": "PRO:PER",
+    "3": "VER:cond",
+    "4": "VER:pres",
+    "5": "VER:subp",
+    "6": "SENT",
+    "7": "VER:",
+    "8": "VER:simp",
+    "9": "PUN:cit",
+    "10": "DET:ART",
+    "11": "SYM",
+    "12": "NOM",
+    "13": "VER:impf",
+    "14": "PRP:det",
+    "15": "PUN",
+    "16": "PRO:IND",
+    "17": "INT",
+    "18": "PRO",
+    "19": "FW",
+    "20": "PRO:DEM",
+    "21": "VER:subi",
+    "22": "DET:art",
+    "23": "PRO:POS",
+    "24": "PRP",
+    "25": "VER:futu",
+    "26": "DET:POS",
+    "27": "PRO:REL",
+    "28": "ADV",
+    "29": "NUM",
+    "30": "VER:impe",
+    "31": "@",
+    "32": "futu",
+    "33": "VER:infi",
+    "34": "NAM",
+    "35": "ABR",
+    "36": "ADJ",
+    "37": "KON",
+    "38": "VER:ppre"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "#": 1,
+    "@": 31,
+    "ABR": 35,
+    "ADJ": 36,
+    "ADV": 28,
+    "DET:ART": 10,
+    "DET:POS": 26,
+    "DET:art": 22,
+    "FW": 19,
+    "INT": 17,
+    "KON": 37,
+    "NAM": 34,
+    "NOM": 12,
+    "NUM": 29,
+    "PRO": 18,
+    "PRO:DEM": 20,
+    "PRO:IND": 16,
+    "PRO:PER": 2,
+    "PRO:POS": 23,
+    "PRO:REL": 27,
+    "PRP": 24,
+    "PRP:det": 14,
+    "PUN": 15,
+    "PUN:cit": 9,
+    "SENT": 6,
+    "SYM": 11,
+    "VER:": 7,
+    "VER:cond": 3,
+    "VER:futu": 25,
+    "VER:impe": 30,
+    "VER:impf": 13,
+    "VER:infi": 33,
+    "VER:pper": 0,
+    "VER:ppre": 38,
+    "VER:pres": 4,
+    "VER:simp": 8,
+    "VER:subi": 21,
+    "VER:subp": 5,
+    "futu": 32
+  },
+  "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": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 39.95,
+    "eval_accuracy": 0.9768565163278611,
+    "eval_f1": 0.9745301568430197,
+    "eval_loss": 0.10217323899269104,
+    "eval_precision": 0.9744261895327216,
+    "eval_recall": 0.9746341463414634,
+    "eval_runtime": 2.1359,
+    "eval_samples": 1431,
+    "eval_samples_per_second": 776.71,
+    "eval_steps_per_second": 3.277
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1442d2f613e0213897cfa0c36f5bde79edc0e93e3cc2722b5d0d7e067246222
+size 1110003249

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:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "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,
+  "token": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 39.95,
+    "train_loss": 0.6079375518219812,
+    "train_runtime": 701.2451,
+    "train_samples": 14928,
+    "train_samples_per_second": 851.514,
+    "train_steps_per_second": 0.799
+}

trainer_state.json

@@ -0,0 +1,511 @@
+{
+  "best_metric": 0.9745301568430197,
+  "best_model_checkpoint": "models/pos_final_xlm_fr/checkpoint-448",
+  "epoch": 39.94915254237288,
+  "global_step": 560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.95,
+      "eval_accuracy": 0.0025780833283944762,
+      "eval_f1": 0.0,
+      "eval_loss": 3.5537023544311523,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 2.1805,
+      "eval_samples_per_second": 760.825,
+      "eval_steps_per_second": 3.21,
+      "step": 14
+    },
+    {
+      "epoch": 1.95,
+      "eval_accuracy": 0.004948734664849168,
+      "eval_f1": 0.004161179878851726,
+      "eval_loss": 3.453566551208496,
+      "eval_precision": 0.01528046421663443,
+      "eval_recall": 0.0024085365853658536,
+      "eval_runtime": 2.2293,
+      "eval_samples_per_second": 744.195,
+      "eval_steps_per_second": 3.14,
+      "step": 28
+    },
+    {
+      "epoch": 2.95,
+      "eval_accuracy": 0.2843003615243288,
+      "eval_f1": 0.2065520889335946,
+      "eval_loss": 3.1247434616088867,
+      "eval_precision": 0.23953179679015324,
+      "eval_recall": 0.18155487804878048,
+      "eval_runtime": 2.0115,
+      "eval_samples_per_second": 824.764,
+      "eval_steps_per_second": 3.48,
+      "step": 42
+    },
+    {
+      "epoch": 3.95,
+      "eval_accuracy": 0.45430569548983585,
+      "eval_f1": 0.3899751394208157,
+      "eval_loss": 2.598811149597168,
+      "eval_precision": 0.4342361215023193,
+      "eval_recall": 0.3539024390243902,
+      "eval_runtime": 2.3441,
+      "eval_samples_per_second": 707.74,
+      "eval_steps_per_second": 2.986,
+      "step": 56
+    },
+    {
+      "epoch": 4.95,
+      "eval_accuracy": 0.5148462039945475,
+      "eval_f1": 0.454724342663274,
+      "eval_loss": 2.0168328285217285,
+      "eval_precision": 0.5125430210325048,
+      "eval_recall": 0.4086280487804878,
+      "eval_runtime": 2.0095,
+      "eval_samples_per_second": 825.594,
+      "eval_steps_per_second": 3.484,
+      "step": 70
+    },
+    {
+      "epoch": 5.95,
+      "eval_accuracy": 0.6085758312096249,
+      "eval_f1": 0.5542561693660192,
+      "eval_loss": 1.4837758541107178,
+      "eval_precision": 0.5959454245729718,
+      "eval_recall": 0.5180182926829269,
+      "eval_runtime": 2.0097,
+      "eval_samples_per_second": 825.481,
+      "eval_steps_per_second": 3.483,
+      "step": 84
+    },
+    {
+      "epoch": 6.95,
+      "eval_accuracy": 0.7980501392757661,
+      "eval_f1": 0.7759372816890475,
+      "eval_loss": 0.9300474524497986,
+      "eval_precision": 0.7904792029100111,
+      "eval_recall": 0.7619207317073171,
+      "eval_runtime": 2.0866,
+      "eval_samples_per_second": 795.072,
+      "eval_steps_per_second": 3.355,
+      "step": 98
+    },
+    {
+      "epoch": 7.95,
+      "eval_accuracy": 0.9146565518876312,
+      "eval_f1": 0.909426874150543,
+      "eval_loss": 0.4873865842819214,
+      "eval_precision": 0.911054676743261,
+      "eval_recall": 0.9078048780487805,
+      "eval_runtime": 2.0506,
+      "eval_samples_per_second": 809.029,
+      "eval_steps_per_second": 3.414,
+      "step": 112
+    },
+    {
+      "epoch": 8.95,
+      "eval_accuracy": 0.9395780240621111,
+      "eval_f1": 0.9370149572323785,
+      "eval_loss": 0.2940390408039093,
+      "eval_precision": 0.9372007197974808,
+      "eval_recall": 0.936829268292683,
+      "eval_runtime": 2.4026,
+      "eval_samples_per_second": 690.513,
+      "eval_steps_per_second": 2.914,
+      "step": 126
+    },
+    {
+      "epoch": 9.95,
+      "eval_accuracy": 0.9490309962662241,
+      "eval_f1": 0.9476378372613843,
+      "eval_loss": 0.20862668752670288,
+      "eval_precision": 0.9470751240902585,
+      "eval_recall": 0.9482012195121952,
+      "eval_runtime": 2.1173,
+      "eval_samples_per_second": 783.547,
+      "eval_steps_per_second": 3.306,
+      "step": 140
+    },
+    {
+      "epoch": 10.95,
+      "eval_accuracy": 0.96272150773425,
+      "eval_f1": 0.9601852133914156,
+      "eval_loss": 0.16879160702228546,
+      "eval_precision": 0.9593961161502405,
+      "eval_recall": 0.9609756097560975,
+      "eval_runtime": 2.6297,
+      "eval_samples_per_second": 630.882,
+      "eval_steps_per_second": 2.662,
+      "step": 154
+    },
+    {
+      "epoch": 11.95,
+      "eval_accuracy": 0.9659218870384638,
+      "eval_f1": 0.9632472774350773,
+      "eval_loss": 0.1449553668498993,
+      "eval_precision": 0.9624410287627454,
+      "eval_recall": 0.9640548780487805,
+      "eval_runtime": 2.1659,
+      "eval_samples_per_second": 765.976,
+      "eval_steps_per_second": 3.232,
+      "step": 168
+    },
+    {
+      "epoch": 12.95,
+      "eval_accuracy": 0.9685592366502697,
+      "eval_f1": 0.9659930249912432,
+      "eval_loss": 0.13338540494441986,
+      "eval_precision": 0.9650670967349299,
+      "eval_recall": 0.9669207317073171,
+      "eval_runtime": 2.0965,
+      "eval_samples_per_second": 791.329,
+      "eval_steps_per_second": 3.339,
+      "step": 182
+    },
+    {
+      "epoch": 13.95,
+      "eval_accuracy": 0.9702483257274936,
+      "eval_f1": 0.9679444207447133,
+      "eval_loss": 0.12125352025032043,
+      "eval_precision": 0.9674138141064685,
+      "eval_recall": 0.9684756097560976,
+      "eval_runtime": 2.0848,
+      "eval_samples_per_second": 795.757,
+      "eval_steps_per_second": 3.358,
+      "step": 196
+    },
+    {
+      "epoch": 14.95,
+      "eval_accuracy": 0.9718188822378948,
+      "eval_f1": 0.9689970901445788,
+      "eval_loss": 0.11550796031951904,
+      "eval_precision": 0.9684216937178355,
+      "eval_recall": 0.9695731707317073,
+      "eval_runtime": 2.1294,
+      "eval_samples_per_second": 779.097,
+      "eval_steps_per_second": 3.287,
+      "step": 210
+    },
+    {
+      "epoch": 15.95,
+      "eval_accuracy": 0.9733598056065904,
+      "eval_f1": 0.9709382953108094,
+      "eval_loss": 0.10925151407718658,
+      "eval_precision": 0.9706572412322131,
+      "eval_recall": 0.9712195121951219,
+      "eval_runtime": 2.0792,
+      "eval_samples_per_second": 797.884,
+      "eval_steps_per_second": 3.367,
+      "step": 224
+    },
+    {
+      "epoch": 16.95,
+      "eval_accuracy": 0.9739228352989984,
+      "eval_f1": 0.9713353956812605,
+      "eval_loss": 0.10589804500341415,
+      "eval_precision": 0.9710246488528685,
+      "eval_recall": 0.9716463414634147,
+      "eval_runtime": 3.3331,
+      "eval_samples_per_second": 497.732,
+      "eval_steps_per_second": 2.1,
+      "step": 238
+    },
+    {
+      "epoch": 17.95,
+      "eval_accuracy": 0.973952468440704,
+      "eval_f1": 0.9713650009905667,
+      "eval_loss": 0.10459830611944199,
+      "eval_precision": 0.9710838233949846,
+      "eval_recall": 0.9716463414634147,
+      "eval_runtime": 2.0698,
+      "eval_samples_per_second": 801.518,
+      "eval_steps_per_second": 3.382,
+      "step": 252
+    },
+    {
+      "epoch": 18.95,
+      "eval_accuracy": 0.9745154981331121,
+      "eval_f1": 0.9721574543958305,
+      "eval_loss": 0.10144730657339096,
+      "eval_precision": 0.9718760474115604,
+      "eval_recall": 0.9724390243902439,
+      "eval_runtime": 2.3781,
+      "eval_samples_per_second": 697.618,
+      "eval_steps_per_second": 2.944,
+      "step": 266
+    },
+    {
+      "epoch": 19.95,
+      "eval_accuracy": 0.9741599004326439,
+      "eval_f1": 0.971824761904762,
+      "eval_loss": 0.1002810001373291,
+      "eval_precision": 0.9714546839299315,
+      "eval_recall": 0.9721951219512195,
+      "eval_runtime": 2.3329,
+      "eval_samples_per_second": 711.141,
+      "eval_steps_per_second": 3.001,
+      "step": 280
+    },
+    {
+      "epoch": 20.95,
+      "eval_accuracy": 0.9750785278255201,
+      "eval_f1": 0.9727077396644468,
+      "eval_loss": 0.09868494421243668,
+      "eval_precision": 0.9723669378179934,
+      "eval_recall": 0.9730487804878049,
+      "eval_runtime": 2.094,
+      "eval_samples_per_second": 792.279,
+      "eval_steps_per_second": 3.343,
+      "step": 294
+    },
+    {
+      "epoch": 21.95,
+      "eval_accuracy": 0.9750192615421087,
+      "eval_f1": 0.9725075436618001,
+      "eval_loss": 0.09709486365318298,
+      "eval_precision": 0.9722408434395758,
+      "eval_recall": 0.9727743902439024,
+      "eval_runtime": 2.3309,
+      "eval_samples_per_second": 711.747,
+      "eval_steps_per_second": 3.003,
+      "step": 308
+    },
+    {
+      "epoch": 22.95,
+      "eval_accuracy": 0.9753748592425769,
+      "eval_f1": 0.9729877965172083,
+      "eval_loss": 0.09679476916790009,
+      "eval_precision": 0.9724396260316107,
+      "eval_recall": 0.9735365853658536,
+      "eval_runtime": 2.3344,
+      "eval_samples_per_second": 710.679,
+      "eval_steps_per_second": 2.999,
+      "step": 322
+    },
+    {
+      "epoch": 23.95,
+      "eval_accuracy": 0.975641557517928,
+      "eval_f1": 0.9732274825910068,
+      "eval_loss": 0.09535854309797287,
+      "eval_precision": 0.9728272458646846,
+      "eval_recall": 0.9736280487804878,
+      "eval_runtime": 3.076,
+      "eval_samples_per_second": 539.342,
+      "eval_steps_per_second": 2.276,
+      "step": 336
+    },
+    {
+      "epoch": 24.95,
+      "eval_accuracy": 0.9751970603923428,
+      "eval_f1": 0.9726641067836899,
+      "eval_loss": 0.09671631455421448,
+      "eval_precision": 0.9722492993785793,
+      "eval_recall": 0.9730792682926829,
+      "eval_runtime": 2.2902,
+      "eval_samples_per_second": 724.376,
+      "eval_steps_per_second": 3.056,
+      "step": 350
+    },
+    {
+      "epoch": 25.95,
+      "eval_accuracy": 0.9762638534937474,
+      "eval_f1": 0.9739440482720789,
+      "eval_loss": 0.09651771187782288,
+      "eval_precision": 0.9735286950164493,
+      "eval_recall": 0.974359756097561,
+      "eval_runtime": 2.3507,
+      "eval_samples_per_second": 705.738,
+      "eval_steps_per_second": 2.978,
+      "step": 364
+    },
+    {
+      "epoch": 26.95,
+      "eval_accuracy": 0.9756711906596337,
+      "eval_f1": 0.973000975134081,
+      "eval_loss": 0.09634628146886826,
+      "eval_precision": 0.9725268031189084,
+      "eval_recall": 0.9734756097560976,
+      "eval_runtime": 2.1161,
+      "eval_samples_per_second": 783.981,
+      "eval_steps_per_second": 3.308,
+      "step": 378
+    },
+    {
+      "epoch": 27.95,
+      "eval_accuracy": 0.9759082557932792,
+      "eval_f1": 0.9732752315943443,
+      "eval_loss": 0.09717196971178055,
+      "eval_precision": 0.9728009259259259,
+      "eval_recall": 0.97375,
+      "eval_runtime": 2.4757,
+      "eval_samples_per_second": 670.113,
+      "eval_steps_per_second": 2.827,
+      "step": 392
+    },
+    {
+      "epoch": 28.95,
+      "eval_accuracy": 0.9765601849108042,
+      "eval_f1": 0.9740214228032484,
+      "eval_loss": 0.09867348521947861,
+      "eval_precision": 0.9735615729036581,
+      "eval_recall": 0.9744817073170732,
+      "eval_runtime": 2.2832,
+      "eval_samples_per_second": 726.617,
+      "eval_steps_per_second": 3.066,
+      "step": 406
+    },
+    {
+      "epoch": 29.95,
+      "eval_accuracy": 0.9764416523439815,
+      "eval_f1": 0.9739541263430618,
+      "eval_loss": 0.09944748878479004,
+      "eval_precision": 0.9737315252171264,
+      "eval_recall": 0.9741768292682926,
+      "eval_runtime": 2.2486,
+      "eval_samples_per_second": 737.785,
+      "eval_steps_per_second": 3.113,
+      "step": 420
+    },
+    {
+      "epoch": 30.95,
+      "eval_accuracy": 0.9763527529188645,
+      "eval_f1": 0.9738618871260268,
+      "eval_loss": 0.09847575426101685,
+      "eval_precision": 0.9736689726632737,
+      "eval_recall": 0.9740548780487804,
+      "eval_runtime": 2.8613,
+      "eval_samples_per_second": 579.816,
+      "eval_steps_per_second": 2.446,
+      "step": 434
+    },
+    {
+      "epoch": 31.95,
+      "eval_accuracy": 0.9768565163278611,
+      "eval_f1": 0.9745301568430197,
+      "eval_loss": 0.10217323899269104,
+      "eval_precision": 0.9744261895327216,
+      "eval_recall": 0.9746341463414634,
+      "eval_runtime": 2.2672,
+      "eval_samples_per_second": 731.743,
+      "eval_steps_per_second": 3.088,
+      "step": 448
+    },
+    {
+      "epoch": 32.95,
+      "eval_accuracy": 0.9767379837610384,
+      "eval_f1": 0.9742120343839542,
+      "eval_loss": 0.10195796191692352,
+      "eval_precision": 0.9740338900402292,
+      "eval_recall": 0.974390243902439,
+      "eval_runtime": 2.0866,
+      "eval_samples_per_second": 795.073,
+      "eval_steps_per_second": 3.355,
+      "step": 462
+    },
+    {
+      "epoch": 33.95,
+      "eval_accuracy": 0.9757897232264565,
+      "eval_f1": 0.9734095238095238,
+      "eval_loss": 0.10545694828033447,
+      "eval_precision": 0.9730388423457731,
+      "eval_recall": 0.973780487804878,
+      "eval_runtime": 2.3249,
+      "eval_samples_per_second": 713.591,
+      "eval_steps_per_second": 3.011,
+      "step": 476
+    },
+    {
+      "epoch": 34.95,
+      "eval_accuracy": 0.9760267883601019,
+      "eval_f1": 0.9736721821007404,
+      "eval_loss": 0.10677994042634964,
+      "eval_precision": 0.9731680575013705,
+      "eval_recall": 0.9741768292682926,
+      "eval_runtime": 2.2489,
+      "eval_samples_per_second": 737.696,
+      "eval_steps_per_second": 3.113,
+      "step": 490
+    },
+    {
+      "epoch": 35.68,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 0.6768,
+      "step": 500
+    },
+    {
+      "epoch": 35.95,
+      "eval_accuracy": 0.9764416523439815,
+      "eval_f1": 0.9738759335467154,
+      "eval_loss": 0.10853772610425949,
+      "eval_precision": 0.9737275220969217,
+      "eval_recall": 0.9740243902439024,
+      "eval_runtime": 2.1342,
+      "eval_samples_per_second": 777.355,
+      "eval_steps_per_second": 3.28,
+      "step": 504
+    },
+    {
+      "epoch": 36.95,
+      "eval_accuracy": 0.9763527529188645,
+      "eval_f1": 0.9738987337914641,
+      "eval_loss": 0.1088031679391861,
+      "eval_precision": 0.9734685796094916,
+      "eval_recall": 0.974329268292683,
+      "eval_runtime": 2.3204,
+      "eval_samples_per_second": 714.977,
+      "eval_steps_per_second": 3.017,
+      "step": 518
+    },
+    {
+      "epoch": 37.95,
+      "eval_accuracy": 0.976767616902744,
+      "eval_f1": 0.9741534335090981,
+      "eval_loss": 0.10998602956533432,
+      "eval_precision": 0.9738862819184594,
+      "eval_recall": 0.974420731707317,
+      "eval_runtime": 2.2182,
+      "eval_samples_per_second": 747.919,
+      "eval_steps_per_second": 3.156,
+      "step": 532
+    },
+    {
+      "epoch": 38.95,
+      "eval_accuracy": 0.9767379837610384,
+      "eval_f1": 0.9741690668861153,
+      "eval_loss": 0.11069974303245544,
+      "eval_precision": 0.9738870776074835,
+      "eval_recall": 0.9744512195121952,
+      "eval_runtime": 2.083,
+      "eval_samples_per_second": 796.451,
+      "eval_steps_per_second": 3.361,
+      "step": 546
+    },
+    {
+      "epoch": 39.95,
+      "eval_accuracy": 0.9768861494695668,
+      "eval_f1": 0.9743683520770474,
+      "eval_loss": 0.11153056472539902,
+      "eval_precision": 0.9740418012308817,
+      "eval_recall": 0.9746951219512195,
+      "eval_runtime": 2.295,
+      "eval_samples_per_second": 722.863,
+      "eval_steps_per_second": 3.05,
+      "step": 560
+    },
+    {
+      "epoch": 39.95,
+      "step": 560,
+      "total_flos": 4.190909533741901e+16,
+      "train_loss": 0.6079375518219812,
+      "train_runtime": 701.2451,
+      "train_samples_per_second": 851.514,
+      "train_steps_per_second": 0.799
+    }
+  ],
+  "max_steps": 560,
+  "num_train_epochs": 40,
+  "total_flos": 4.190909533741901e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c931e07ae9288e99b67ff30078445ee1dca8352a82af3bafe38f3167d2d09dd
+size 3439