Upload folder using huggingface_hub

README.md

@@ -0,0 +1,108 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: pos_final_mono_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_mono_fr
+
+This model is a fine-tuned version of [almanach/camembert-base](https://huggingface.co/almanach/camembert-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5416
+- Precision: 0.9742
+- Recall: 0.9745
+- F1: 0.9743
+- Accuracy: 0.9768
+
+## 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   | 3.6697          | 0.0210    | 0.0194 | 0.0201 | 0.0215   |
+| No log        | 1.95  | 28   | 3.6329          | 0.0513    | 0.0484 | 0.0498 | 0.0511   |
+| No log        | 2.95  | 42   | 3.5739          | 0.1142    | 0.1086 | 0.1113 | 0.1267   |
+| No log        | 3.95  | 56   | 3.4791          | 0.2535    | 0.1976 | 0.2221 | 0.3061   |
+| No log        | 4.95  | 70   | 3.3377          | 0.3393    | 0.2029 | 0.2539 | 0.3788   |
+| No log        | 5.95  | 84   | 3.1886          | 0.3737    | 0.1401 | 0.2038 | 0.3427   |
+| No log        | 6.95  | 98   | 3.0505          | 0.4342    | 0.3211 | 0.3692 | 0.4600   |
+| No log        | 7.95  | 112  | 2.8996          | 0.5160    | 0.4319 | 0.4702 | 0.5282   |
+| No log        | 8.95  | 126  | 2.7485          | 0.5617    | 0.4878 | 0.5222 | 0.5732   |
+| No log        | 9.95  | 140  | 2.5862          | 0.6077    | 0.5374 | 0.5704 | 0.6246   |
+| No log        | 10.95 | 154  | 2.4205          | 0.6805    | 0.6311 | 0.6549 | 0.6887   |
+| No log        | 11.95 | 168  | 2.2603          | 0.7816    | 0.7569 | 0.7691 | 0.7839   |
+| No log        | 12.95 | 182  | 2.1124          | 0.8366    | 0.8305 | 0.8335 | 0.8370   |
+| No log        | 13.95 | 196  | 1.9826          | 0.8691    | 0.8681 | 0.8686 | 0.8736   |
+| No log        | 14.95 | 210  | 1.8721          | 0.9210    | 0.92   | 0.9205 | 0.9240   |
+| No log        | 15.95 | 224  | 1.7779          | 0.9390    | 0.9392 | 0.9391 | 0.9417   |
+| No log        | 16.95 | 238  | 1.6986          | 0.9442    | 0.9452 | 0.9447 | 0.9466   |
+| No log        | 17.95 | 252  | 1.6294          | 0.9467    | 0.9476 | 0.9472 | 0.9486   |
+| No log        | 18.95 | 266  | 1.5667          | 0.9481    | 0.9493 | 0.9487 | 0.9499   |
+| No log        | 19.95 | 280  | 1.5073          | 0.9507    | 0.9522 | 0.9514 | 0.9523   |
+| No log        | 20.95 | 294  | 1.4499          | 0.9538    | 0.9550 | 0.9544 | 0.9552   |
+| No log        | 21.95 | 308  | 1.3926          | 0.9555    | 0.9563 | 0.9559 | 0.9563   |
+| No log        | 22.95 | 322  | 1.3373          | 0.9609    | 0.9614 | 0.9612 | 0.9612   |
+| No log        | 23.95 | 336  | 1.2815          | 0.9622    | 0.9624 | 0.9623 | 0.9623   |
+| No log        | 24.95 | 350  | 1.2246          | 0.9649    | 0.9648 | 0.9648 | 0.9646   |
+| No log        | 25.95 | 364  | 1.1682          | 0.9653    | 0.9652 | 0.9652 | 0.9648   |
+| No log        | 26.95 | 378  | 1.1114          | 0.9650    | 0.9659 | 0.9654 | 0.9661   |
+| No log        | 27.95 | 392  | 1.0521          | 0.9669    | 0.9675 | 0.9672 | 0.9699   |
+| No log        | 28.95 | 406  | 0.9950          | 0.9677    | 0.9679 | 0.9678 | 0.9707   |
+| No log        | 29.95 | 420  | 0.9364          | 0.9687    | 0.9690 | 0.9688 | 0.9716   |
+| No log        | 30.95 | 434  | 0.8800          | 0.9691    | 0.9693 | 0.9692 | 0.9721   |
+| No log        | 31.95 | 448  | 0.8233          | 0.9693    | 0.9698 | 0.9696 | 0.9726   |
+| No log        | 32.95 | 462  | 0.7679          | 0.9703    | 0.9703 | 0.9703 | 0.9733   |
+| No log        | 33.95 | 476  | 0.7146          | 0.9711    | 0.9711 | 0.9711 | 0.9737   |
+| No log        | 34.95 | 490  | 0.6641          | 0.9722    | 0.9724 | 0.9723 | 0.9750   |
+| 2.0937        | 35.95 | 504  | 0.6187          | 0.9729    | 0.9729 | 0.9729 | 0.9755   |
+| 2.0937        | 36.95 | 518  | 0.5834          | 0.9727    | 0.9732 | 0.9729 | 0.9756   |
+| 2.0937        | 37.95 | 532  | 0.5605          | 0.9735    | 0.9739 | 0.9737 | 0.9762   |
+| 2.0937        | 38.95 | 546  | 0.5466          | 0.9737    | 0.9742 | 0.9739 | 0.9765   |
+| 2.0937        | 39.95 | 560  | 0.5416          | 0.9742    | 0.9745 | 0.9743 | 0.9768   |
+
+
+### 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": 0.9768268831861554,
+    "eval_f1": 0.9743472495313,
+    "eval_loss": 0.5415592193603516,
+    "eval_precision": 0.974243301734386,
+    "eval_recall": 0.9744512195121952,
+    "eval_runtime": 1.948,
+    "eval_samples": 1431,
+    "eval_samples_per_second": 851.633,
+    "eval_steps_per_second": 3.593,
+    "train_loss": 1.9360494545527867,
+    "train_runtime": 526.0611,
+    "train_samples": 14928,
+    "train_samples_per_second": 1135.077,
+    "train_steps_per_second": 1.065
+}

config.json

@@ -0,0 +1,111 @@
+{
+  "_name_or_path": "almanach/camembert-base",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "finetuning_task": "pos",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "VER:infi",
+    "1": "KON",
+    "2": "VER:",
+    "3": "VER:impf",
+    "4": "VER:cond",
+    "5": "PRO:IND",
+    "6": "ABR",
+    "7": "DET:POS",
+    "8": "PRP:det",
+    "9": "FW",
+    "10": "PRP",
+    "11": "VER:pper",
+    "12": "PRO:DEM",
+    "13": "PRO:REL",
+    "14": "VER:subi",
+    "15": "SYM",
+    "16": "VER:impe",
+    "17": "PRO:POS",
+    "18": "#",
+    "19": "PRO",
+    "20": "futu",
+    "21": "DET:art",
+    "22": "PRO:PER",
+    "23": "NOM",
+    "24": "VER:subp",
+    "25": "INT",
+    "26": "VER:futu",
+    "27": "NUM",
+    "28": "NAM",
+    "29": "@",
+    "30": "ADV",
+    "31": "VER:ppre",
+    "32": "VER:pres",
+    "33": "PUN:cit",
+    "34": "PUN",
+    "35": "DET:ART",
+    "36": "VER:simp",
+    "37": "SENT",
+    "38": "ADJ"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "#": 18,
+    "@": 29,
+    "ABR": 6,
+    "ADJ": 38,
+    "ADV": 30,
+    "DET:ART": 35,
+    "DET:POS": 7,
+    "DET:art": 21,
+    "FW": 9,
+    "INT": 25,
+    "KON": 1,
+    "NAM": 28,
+    "NOM": 23,
+    "NUM": 27,
+    "PRO": 19,
+    "PRO:DEM": 12,
+    "PRO:IND": 5,
+    "PRO:PER": 22,
+    "PRO:POS": 17,
+    "PRO:REL": 13,
+    "PRP": 10,
+    "PRP:det": 8,
+    "PUN": 34,
+    "PUN:cit": 33,
+    "SENT": 37,
+    "SYM": 15,
+    "VER:": 2,
+    "VER:cond": 4,
+    "VER:futu": 26,
+    "VER:impe": 16,
+    "VER:impf": 3,
+    "VER:infi": 0,
+    "VER:pper": 11,
+    "VER:ppre": 31,
+    "VER:pres": 32,
+    "VER:simp": 36,
+    "VER:subi": 14,
+    "VER:subp": 24,
+    "futu": 20
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "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": 32005
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 39.95,
+    "eval_accuracy": 0.9768268831861554,
+    "eval_f1": 0.9743472495313,
+    "eval_loss": 0.5415592193603516,
+    "eval_precision": 0.974243301734386,
+    "eval_recall": 0.9744512195121952,
+    "eval_runtime": 1.948,
+    "eval_samples": 1431,
+    "eval_samples_per_second": 851.633,
+    "eval_steps_per_second": 3.593
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3351f608977c0896611d38dfcf41b569194b05050afad76bedb879625d120b1b
+size 440316465

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "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_config.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "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": "almanach/camembert-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "token": null,
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 39.95,
+    "train_loss": 1.9360494545527867,
+    "train_runtime": 526.0611,
+    "train_samples": 14928,
+    "train_samples_per_second": 1135.077,
+    "train_steps_per_second": 1.065
+}

trainer_state.json

@@ -0,0 +1,511 @@
+{
+  "best_metric": 0.9743472495313,
+  "best_model_checkpoint": "models/pos_final_mono_fr/checkpoint-560",
+  "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": 0.021484027736620635,
+      "eval_f1": 0.02014146604497732,
+      "eval_loss": 3.6696622371673584,
+      "eval_precision": 0.02098896013750248,
+      "eval_recall": 0.019359756097560975,
+      "eval_runtime": 1.991,
+      "eval_samples_per_second": 833.259,
+      "eval_steps_per_second": 3.516,
+      "step": 14
+    },
+    {
+      "epoch": 1.95,
+      "eval_accuracy": 0.051117169442304274,
+      "eval_f1": 0.049818939975858664,
+      "eval_loss": 3.6328794956207275,
+      "eval_precision": 0.051272950211351684,
+      "eval_recall": 0.048445121951219514,
+      "eval_runtime": 1.9795,
+      "eval_samples_per_second": 838.108,
+      "eval_steps_per_second": 3.536,
+      "step": 28
+    },
+    {
+      "epoch": 2.95,
+      "eval_accuracy": 0.12674094707520892,
+      "eval_f1": 0.11132299612354632,
+      "eval_loss": 3.5738770961761475,
+      "eval_precision": 0.11422247882986913,
+      "eval_recall": 0.1085670731707317,
+      "eval_runtime": 2.9806,
+      "eval_samples_per_second": 556.603,
+      "eval_steps_per_second": 2.349,
+      "step": 42
+    },
+    {
+      "epoch": 3.95,
+      "eval_accuracy": 0.30611035381971197,
+      "eval_f1": 0.22206610578982539,
+      "eval_loss": 3.4791259765625,
+      "eval_precision": 0.2535112084816713,
+      "eval_recall": 0.1975609756097561,
+      "eval_runtime": 1.9318,
+      "eval_samples_per_second": 858.799,
+      "eval_steps_per_second": 3.624,
+      "step": 56
+    },
+    {
+      "epoch": 4.95,
+      "eval_accuracy": 0.3788300835654596,
+      "eval_f1": 0.25393978707978787,
+      "eval_loss": 3.3377487659454346,
+      "eval_precision": 0.339298460283471,
+      "eval_recall": 0.20289634146341465,
+      "eval_runtime": 1.9526,
+      "eval_samples_per_second": 849.649,
+      "eval_steps_per_second": 3.585,
+      "step": 70
+    },
+    {
+      "epoch": 5.95,
+      "eval_accuracy": 0.34273691696793696,
+      "eval_f1": 0.20375216215017516,
+      "eval_loss": 3.188615560531616,
+      "eval_precision": 0.3736782170164308,
+      "eval_recall": 0.1400609756097561,
+      "eval_runtime": 1.9288,
+      "eval_samples_per_second": 860.111,
+      "eval_steps_per_second": 3.629,
+      "step": 84
+    },
+    {
+      "epoch": 6.95,
+      "eval_accuracy": 0.4599656255556214,
+      "eval_f1": 0.36921620863712845,
+      "eval_loss": 3.0504870414733887,
+      "eval_precision": 0.434243073878628,
+      "eval_recall": 0.3211280487804878,
+      "eval_runtime": 1.9835,
+      "eval_samples_per_second": 836.412,
+      "eval_steps_per_second": 3.529,
+      "step": 98
+    },
+    {
+      "epoch": 7.95,
+      "eval_accuracy": 0.5282403840455165,
+      "eval_f1": 0.4701918608510921,
+      "eval_loss": 2.8996212482452393,
+      "eval_precision": 0.5159915488853272,
+      "eval_recall": 0.431859756097561,
+      "eval_runtime": 2.2513,
+      "eval_samples_per_second": 736.924,
+      "eval_steps_per_second": 3.109,
+      "step": 112
+    },
+    {
+      "epoch": 8.95,
+      "eval_accuracy": 0.573164226871333,
+      "eval_f1": 0.5221832422289304,
+      "eval_loss": 2.748504161834717,
+      "eval_precision": 0.5617342460944357,
+      "eval_recall": 0.48783536585365855,
+      "eval_runtime": 1.9301,
+      "eval_samples_per_second": 859.535,
+      "eval_steps_per_second": 3.627,
+      "step": 126
+    },
+    {
+      "epoch": 9.95,
+      "eval_accuracy": 0.6246369940141053,
+      "eval_f1": 0.5703931402685649,
+      "eval_loss": 2.586193084716797,
+      "eval_precision": 0.6076525336091003,
+      "eval_recall": 0.5374390243902439,
+      "eval_runtime": 2.1049,
+      "eval_samples_per_second": 788.176,
+      "eval_steps_per_second": 3.326,
+      "step": 140
+    },
+    {
+      "epoch": 10.95,
+      "eval_accuracy": 0.6886742132400877,
+      "eval_f1": 0.6548560582094275,
+      "eval_loss": 2.420483112335205,
+      "eval_precision": 0.6804733727810651,
+      "eval_recall": 0.6310975609756098,
+      "eval_runtime": 2.1866,
+      "eval_samples_per_second": 758.715,
+      "eval_steps_per_second": 3.201,
+      "step": 154
+    },
+    {
+      "epoch": 11.95,
+      "eval_accuracy": 0.7838854975404492,
+      "eval_f1": 0.7690782646407386,
+      "eval_loss": 2.260331869125366,
+      "eval_precision": 0.7816327173125964,
+      "eval_recall": 0.7569207317073171,
+      "eval_runtime": 2.2785,
+      "eval_samples_per_second": 728.116,
+      "eval_steps_per_second": 3.072,
+      "step": 168
+    },
+    {
+      "epoch": 12.95,
+      "eval_accuracy": 0.83701772061874,
+      "eval_f1": 0.8335373317013463,
+      "eval_loss": 2.1123812198638916,
+      "eval_precision": 0.8366093366093366,
+      "eval_recall": 0.8304878048780487,
+      "eval_runtime": 2.9322,
+      "eval_samples_per_second": 565.792,
+      "eval_steps_per_second": 2.387,
+      "step": 182
+    },
+    {
+      "epoch": 13.95,
+      "eval_accuracy": 0.8735553843418479,
+      "eval_f1": 0.8685824105426924,
+      "eval_loss": 1.9825972318649292,
+      "eval_precision": 0.8690861363775105,
+      "eval_recall": 0.8680792682926829,
+      "eval_runtime": 1.9874,
+      "eval_samples_per_second": 834.748,
+      "eval_steps_per_second": 3.522,
+      "step": 196
+    },
+    {
+      "epoch": 14.95,
+      "eval_accuracy": 0.9239613583832158,
+      "eval_f1": 0.9204770765335692,
+      "eval_loss": 1.8721418380737305,
+      "eval_precision": 0.9209546481108466,
+      "eval_recall": 0.92,
+      "eval_runtime": 1.9558,
+      "eval_samples_per_second": 848.258,
+      "eval_steps_per_second": 3.579,
+      "step": 210
+    },
+    {
+      "epoch": 15.95,
+      "eval_accuracy": 0.9416819771232146,
+      "eval_f1": 0.9391052511241521,
+      "eval_loss": 1.7779291868209839,
+      "eval_precision": 0.9390336838896509,
+      "eval_recall": 0.9391768292682927,
+      "eval_runtime": 1.9975,
+      "eval_samples_per_second": 830.55,
+      "eval_steps_per_second": 3.504,
+      "step": 224
+    },
+    {
+      "epoch": 16.95,
+      "eval_accuracy": 0.9466010786463581,
+      "eval_f1": 0.944723771216138,
+      "eval_loss": 1.698561429977417,
+      "eval_precision": 0.9442346348297497,
+      "eval_recall": 0.9452134146341463,
+      "eval_runtime": 1.9516,
+      "eval_samples_per_second": 850.075,
+      "eval_steps_per_second": 3.587,
+      "step": 238
+    },
+    {
+      "epoch": 17.95,
+      "eval_accuracy": 0.9486161322823445,
+      "eval_f1": 0.9471599219892736,
+      "eval_loss": 1.6294448375701904,
+      "eval_precision": 0.9466983430799221,
+      "eval_recall": 0.9476219512195122,
+      "eval_runtime": 1.9621,
+      "eval_samples_per_second": 845.505,
+      "eval_steps_per_second": 3.568,
+      "step": 252
+    },
+    {
+      "epoch": 18.95,
+      "eval_accuracy": 0.9498607242339833,
+      "eval_f1": 0.9487042764210301,
+      "eval_loss": 1.5666829347610474,
+      "eval_precision": 0.948140929991778,
+      "eval_recall": 0.9492682926829268,
+      "eval_runtime": 2.1244,
+      "eval_samples_per_second": 780.914,
+      "eval_steps_per_second": 3.295,
+      "step": 266
+    },
+    {
+      "epoch": 19.95,
+      "eval_accuracy": 0.9523499081372607,
+      "eval_f1": 0.9514249592542383,
+      "eval_loss": 1.5073306560516357,
+      "eval_precision": 0.9506864326808925,
+      "eval_recall": 0.9521646341463414,
+      "eval_runtime": 1.9609,
+      "eval_samples_per_second": 846.058,
+      "eval_steps_per_second": 3.57,
+      "step": 280
+    },
+    {
+      "epoch": 20.95,
+      "eval_accuracy": 0.9551650565993006,
+      "eval_f1": 0.9544048870405071,
+      "eval_loss": 1.4499109983444214,
+      "eval_precision": 0.953780105349694,
+      "eval_recall": 0.9550304878048781,
+      "eval_runtime": 2.9847,
+      "eval_samples_per_second": 555.827,
+      "eval_steps_per_second": 2.345,
+      "step": 294
+    },
+    {
+      "epoch": 21.95,
+      "eval_accuracy": 0.9562911159841166,
+      "eval_f1": 0.9558884029925795,
+      "eval_loss": 1.3926490545272827,
+      "eval_precision": 0.9554662036613969,
+      "eval_recall": 0.9563109756097561,
+      "eval_runtime": 2.0934,
+      "eval_samples_per_second": 792.487,
+      "eval_steps_per_second": 3.344,
+      "step": 308
+    },
+    {
+      "epoch": 22.95,
+      "eval_accuracy": 0.9612102175072601,
+      "eval_f1": 0.961168007802975,
+      "eval_loss": 1.3373351097106934,
+      "eval_precision": 0.9609336908824964,
+      "eval_recall": 0.9614024390243903,
+      "eval_runtime": 2.5845,
+      "eval_samples_per_second": 641.892,
+      "eval_steps_per_second": 2.708,
+      "step": 322
+    },
+    {
+      "epoch": 23.95,
+      "eval_accuracy": 0.9622770106086648,
+      "eval_f1": 0.9623058515097475,
+      "eval_loss": 1.2815097570419312,
+      "eval_precision": 0.962203188343951,
+      "eval_recall": 0.9624085365853658,
+      "eval_runtime": 1.9491,
+      "eval_samples_per_second": 851.178,
+      "eval_steps_per_second": 3.591,
+      "step": 336
+    },
+    {
+      "epoch": 24.95,
+      "eval_accuracy": 0.9646180288034137,
+      "eval_f1": 0.9648307087214354,
+      "eval_loss": 1.2245593070983887,
+      "eval_precision": 0.9648748361130591,
+      "eval_recall": 0.9647865853658537,
+      "eval_runtime": 2.9881,
+      "eval_samples_per_second": 555.195,
+      "eval_steps_per_second": 2.343,
+      "step": 350
+    },
+    {
+      "epoch": 25.95,
+      "eval_accuracy": 0.9647661945119421,
+      "eval_f1": 0.9652270683110508,
+      "eval_loss": 1.16820228099823,
+      "eval_precision": 0.9652712138305333,
+      "eval_recall": 0.9651829268292683,
+      "eval_runtime": 2.9793,
+      "eval_samples_per_second": 556.84,
+      "eval_steps_per_second": 2.35,
+      "step": 364
+    },
+    {
+      "epoch": 26.95,
+      "eval_accuracy": 0.9660996858886979,
+      "eval_f1": 0.9654436860068261,
+      "eval_loss": 1.1113808155059814,
+      "eval_precision": 0.9649731968810916,
+      "eval_recall": 0.9659146341463415,
+      "eval_runtime": 2.0371,
+      "eval_samples_per_second": 814.377,
+      "eval_steps_per_second": 3.436,
+      "step": 378
+    },
+    {
+      "epoch": 27.95,
+      "eval_accuracy": 0.9699223611687311,
+      "eval_f1": 0.9672198601014949,
+      "eval_loss": 1.0521485805511475,
+      "eval_precision": 0.9669398823852037,
+      "eval_recall": 0.9675,
+      "eval_runtime": 2.1723,
+      "eval_samples_per_second": 763.722,
+      "eval_steps_per_second": 3.222,
+      "step": 392
+    },
+    {
+      "epoch": 28.95,
+      "eval_accuracy": 0.9706928228530789,
+      "eval_f1": 0.9678383074718775,
+      "eval_loss": 0.9949794411659241,
+      "eval_precision": 0.9677498018655124,
+      "eval_recall": 0.9679268292682927,
+      "eval_runtime": 2.9777,
+      "eval_samples_per_second": 557.141,
+      "eval_steps_per_second": 2.351,
+      "step": 406
+    },
+    {
+      "epoch": 29.95,
+      "eval_accuracy": 0.9716410833876608,
+      "eval_f1": 0.9688157293095565,
+      "eval_loss": 0.9363731741905212,
+      "eval_precision": 0.968668088997257,
+      "eval_recall": 0.9689634146341464,
+      "eval_runtime": 2.0063,
+      "eval_samples_per_second": 826.911,
+      "eval_steps_per_second": 3.489,
+      "step": 420
+    },
+    {
+      "epoch": 30.95,
+      "eval_accuracy": 0.9720559473715403,
+      "eval_f1": 0.9692110718205097,
+      "eval_loss": 0.8799633383750916,
+      "eval_precision": 0.9690929041697147,
+      "eval_recall": 0.969329268292683,
+      "eval_runtime": 1.9828,
+      "eval_samples_per_second": 836.683,
+      "eval_steps_per_second": 3.53,
+      "step": 434
+    },
+    {
+      "epoch": 31.95,
+      "eval_accuracy": 0.9726189770639483,
+      "eval_f1": 0.9695962936434156,
+      "eval_loss": 0.8233166337013245,
+      "eval_precision": 0.9693451564737788,
+      "eval_recall": 0.9698475609756098,
+      "eval_runtime": 1.9361,
+      "eval_samples_per_second": 856.891,
+      "eval_steps_per_second": 3.616,
+      "step": 448
+    },
+    {
+      "epoch": 32.95,
+      "eval_accuracy": 0.9733301724648847,
+      "eval_f1": 0.9703057833602635,
+      "eval_loss": 0.7679479122161865,
+      "eval_precision": 0.9702762026705689,
+      "eval_recall": 0.9703353658536585,
+      "eval_runtime": 1.9498,
+      "eval_samples_per_second": 850.85,
+      "eval_steps_per_second": 3.59,
+      "step": 462
+    },
+    {
+      "epoch": 33.95,
+      "eval_accuracy": 0.9737450364487643,
+      "eval_f1": 0.9711132452249204,
+      "eval_loss": 0.7146441340446472,
+      "eval_precision": 0.9710984421206671,
+      "eval_recall": 0.9711280487804878,
+      "eval_runtime": 1.9736,
+      "eval_samples_per_second": 840.614,
+      "eval_steps_per_second": 3.547,
+      "step": 476
+    },
+    {
+      "epoch": 34.95,
+      "eval_accuracy": 0.9749599952586974,
+      "eval_f1": 0.9722899646384587,
+      "eval_loss": 0.6641064286231995,
+      "eval_precision": 0.9721714216044867,
+      "eval_recall": 0.9724085365853659,
+      "eval_runtime": 1.9368,
+      "eval_samples_per_second": 856.569,
+      "eval_steps_per_second": 3.614,
+      "step": 490
+    },
+    {
+      "epoch": 35.68,
+      "learning_rate": 5e-05,
+      "loss": 2.0937,
+      "step": 500
+    },
+    {
+      "epoch": 35.95,
+      "eval_accuracy": 0.9755230249511053,
+      "eval_f1": 0.9729268292682927,
+      "eval_loss": 0.6186906099319458,
+      "eval_precision": 0.9729268292682927,
+      "eval_recall": 0.9729268292682927,
+      "eval_runtime": 1.993,
+      "eval_samples_per_second": 832.399,
+      "eval_steps_per_second": 3.512,
+      "step": 504
+    },
+    {
+      "epoch": 36.95,
+      "eval_accuracy": 0.9756119243762224,
+      "eval_f1": 0.9729490833168234,
+      "eval_loss": 0.5833659172058105,
+      "eval_precision": 0.9726970777341012,
+      "eval_recall": 0.9732012195121951,
+      "eval_runtime": 2.9665,
+      "eval_samples_per_second": 559.252,
+      "eval_steps_per_second": 2.36,
+      "step": 518
+    },
+    {
+      "epoch": 37.95,
+      "eval_accuracy": 0.9761749540686303,
+      "eval_f1": 0.9736946383393786,
+      "eval_loss": 0.5605461597442627,
+      "eval_precision": 0.97348692631194,
+      "eval_recall": 0.9739024390243902,
+      "eval_runtime": 2.0134,
+      "eval_samples_per_second": 823.972,
+      "eval_steps_per_second": 3.477,
+      "step": 532
+    },
+    {
+      "epoch": 38.95,
+      "eval_accuracy": 0.9764712854856872,
+      "eval_f1": 0.9739244403127238,
+      "eval_loss": 0.5465701222419739,
+      "eval_precision": 0.9736721821007405,
+      "eval_recall": 0.9741768292682926,
+      "eval_runtime": 2.9641,
+      "eval_samples_per_second": 559.689,
+      "eval_steps_per_second": 2.362,
+      "step": 546
+    },
+    {
+      "epoch": 39.95,
+      "eval_accuracy": 0.9768268831861554,
+      "eval_f1": 0.9743472495313,
+      "eval_loss": 0.5415592193603516,
+      "eval_precision": 0.974243301734386,
+      "eval_recall": 0.9744512195121952,
+      "eval_runtime": 1.9918,
+      "eval_samples_per_second": 832.894,
+      "eval_steps_per_second": 3.514,
+      "step": 560
+    },
+    {
+      "epoch": 39.95,
+      "step": 560,
+      "total_flos": 3.723450094214784e+16,
+      "train_loss": 1.9360494545527867,
+      "train_runtime": 526.0611,
+      "train_samples_per_second": 1135.077,
+      "train_steps_per_second": 1.065
+    }
+  ],
+  "max_steps": 560,
+  "num_train_epochs": 40,
+  "total_flos": 3.723450094214784e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c3bc0bf649b8aee94ec3886118cfcb6f816ebb22141d51777c8d76e625b62c
+size 3439