model data

README

@@ -0,0 +1,34 @@
+***** Running training *****
+  Num examples = 6004
+  Num Epochs = 14
+  Instantaneous batch size per device = 16
+  Total train batch size (w. parallel, distributed & accumulation) = 16
+  Gradient Accumulation steps = 1
+  Total optimization steps = 5000
+ [2500/5000 12:15 < 12:15, 3.40 it/s, Epoch 6/14]
+Step	Training Loss	Validation Loss	Precision	Recall	F1	Accuracy
+100	No log	0.247325	0.912333	0.925744	0.918990	0.960895
+200	No log	0.171694	0.930514	0.928760	0.929636	0.963143
+300	No log	0.132045	0.935375	0.943837	0.939587	0.970515
+400	No log	0.142074	0.936490	0.939314	0.937900	0.968141
+500	0.245500	0.105783	0.949794	0.955522	0.952649	0.975887
+600	0.245500	0.107380	0.948120	0.950622	0.949369	0.973138
+700	0.245500	0.111011	0.951504	0.954014	0.952757	0.972889
+800	0.245500	0.093002	0.947999	0.955145	0.951558	0.975387
+900	0.245500	0.100926	0.956193	0.954391	0.955291	0.976262
+1000	0.086800	0.090775	0.955263	0.957784	0.956522	0.976637
+1100	0.086800	0.099250	0.953829	0.957784	0.955802	0.976137
+1200	0.086800	0.088502	0.952327	0.956276	0.954298	0.976762
+1300	0.086800	0.094135	0.957078	0.958161	0.957619	0.977011
+1400	0.086800	0.099687	0.957768	0.957407	0.957587	0.975887
+1500	0.056000	0.108563	0.958930	0.959291	0.959111	0.974888
+1600	0.056000	0.101031	0.957784	0.957784	0.957784	0.976262
+1700	0.056000	0.099654	0.960135	0.962307	0.961220	0.978386
+1800	0.056000	0.106387	0.954118	0.956276	0.955196	0.975512
+1900	0.056000	0.096317	0.953846	0.958161	0.955998	0.975762
+2000	0.040000	0.094224	0.959444	0.963061	0.961249	0.977761
+2100	0.040000	0.110398	0.956669	0.957030	0.956849	0.975262
+2200	0.040000	0.096151	0.955706	0.959668	0.957683	0.977386
+2300	0.040000	0.108148	0.945149	0.954768	0.949934	0.974513
+2400	0.040000	0.109966	0.950991	0.958161	0.954563	0.976637
+2500	0.030900	0.117515	0.947921	0.953637	0.950770	0.973888

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "Jean-Baptiste/camembert-ner",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-LOC",
+    "2": "I-PER",
+    "3": "I-MISC",
+    "4": "I-ORG",
+    "5": "I-CARDINAL",
+    "6": "I-ACT",
+    "7": "I-TITRE",
+    "8": "I-FT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "I-ACT": 6,
+    "I-CARDINAL": 5,
+    "I-FT": 8,
+    "I-LOC": 1,
+    "I-MISC": 3,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "I-TITRE": 7,
+    "O": 0
+  },
+  "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": "4.15.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79e5d7804ef407c5b2fbffe41db1698f53c051a01ef68ea9f8224e2a2d623fd
+size 880421605

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392027a1e97297c1e36b64a814594211ff3e68f9b65f51c417cf8305841dbacb
+size 440237809

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74c47781022724c1a2706ba33421f7e3935186d7b6f4f51050f89cce7c7ae1e
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51041b89734cb38f61e5930792b2813f44d4562e4b27ac1f3179a1197589a078
+size 623

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 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "model_max_length": 512, "name_or_path": "Jean-Baptiste/camembert-ner", "special_tokens_map_file": "/root/.cache/huggingface/transformers/fe0e213c44079a9ee091098f81fff2941484006e9ba3001a9bf1ee9f87537599.cb3ec3a6c1200d181228d8825ae9767572abca54efa1bbb37fd83d721b2ef323", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}

trainer_state.json

@@ -0,0 +1,280 @@
+{
+  "best_metric": 0.9612490594431903,
+  "best_model_checkpoint": "/content/drive/MyDrive/SODUCO/article_das_2022/44-camembert_finetuned_pero/checkpoint-2000",
+  "epoch": 5.319148936170213,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "eval_accuracy": 0.9608945527236382,
+      "eval_f1": 0.9189897100093545,
+      "eval_loss": 0.24732524156570435,
+      "eval_precision": 0.912332838038633,
+      "eval_recall": 0.9257444402563136,
+      "eval_runtime": 2.7834,
+      "eval_samples_per_second": 239.997,
+      "eval_steps_per_second": 15.09,
+      "step": 100
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.9631434282858571,
+      "eval_f1": 0.9296359177513677,
+      "eval_loss": 0.17169421911239624,
+      "eval_precision": 0.9305135951661632,
+      "eval_recall": 0.9287598944591029,
+      "eval_runtime": 2.6347,
+      "eval_samples_per_second": 253.541,
+      "eval_steps_per_second": 15.941,
+      "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.9705147426286856,
+      "eval_f1": 0.9395872420262664,
+      "eval_loss": 0.13204523921012878,
+      "eval_precision": 0.9353754202465446,
+      "eval_recall": 0.9438371654730494,
+      "eval_runtime": 2.6,
+      "eval_samples_per_second": 256.926,
+      "eval_steps_per_second": 16.154,
+      "step": 300
+    },
+    {
+      "epoch": 1.06,
+      "eval_accuracy": 0.9681409295352323,
+      "eval_f1": 0.9378998870907039,
+      "eval_loss": 0.1420740932226181,
+      "eval_precision": 0.936490041337843,
+      "eval_recall": 0.9393139841688655,
+      "eval_runtime": 2.565,
+      "eval_samples_per_second": 260.431,
+      "eval_steps_per_second": 16.374,
+      "step": 400
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 9e-05,
+      "loss": 0.2455,
+      "step": 500
+    },
+    {
+      "epoch": 1.33,
+      "eval_accuracy": 0.9758870564717641,
+      "eval_f1": 0.9526493799323562,
+      "eval_loss": 0.1057828888297081,
+      "eval_precision": 0.9497939303109779,
+      "eval_recall": 0.9555220505088579,
+      "eval_runtime": 2.6085,
+      "eval_samples_per_second": 256.084,
+      "eval_steps_per_second": 16.101,
+      "step": 500
+    },
+    {
+      "epoch": 1.6,
+      "eval_accuracy": 0.9731384307846077,
+      "eval_f1": 0.9493694711086017,
+      "eval_loss": 0.10737968236207962,
+      "eval_precision": 0.9481203007518797,
+      "eval_recall": 0.9506219374293253,
+      "eval_runtime": 2.5863,
+      "eval_samples_per_second": 258.283,
+      "eval_steps_per_second": 16.239,
+      "step": 600
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.972888555722139,
+      "eval_f1": 0.9527573875399962,
+      "eval_loss": 0.11101129651069641,
+      "eval_precision": 0.9515037593984963,
+      "eval_recall": 0.9540143234074633,
+      "eval_runtime": 2.5978,
+      "eval_samples_per_second": 257.138,
+      "eval_steps_per_second": 16.167,
+      "step": 700
+    },
+    {
+      "epoch": 2.13,
+      "eval_accuracy": 0.9753873063468266,
+      "eval_f1": 0.9515583927900865,
+      "eval_loss": 0.09300221502780914,
+      "eval_precision": 0.9479985035540591,
+      "eval_recall": 0.9551451187335093,
+      "eval_runtime": 2.6079,
+      "eval_samples_per_second": 256.141,
+      "eval_steps_per_second": 16.105,
+      "step": 800
+    },
+    {
+      "epoch": 2.39,
+      "eval_accuracy": 0.9762618690654673,
+      "eval_f1": 0.9552914544425579,
+      "eval_loss": 0.10092608630657196,
+      "eval_precision": 0.9561933534743202,
+      "eval_recall": 0.9543912551828119,
+      "eval_runtime": 2.604,
+      "eval_samples_per_second": 256.532,
+      "eval_steps_per_second": 16.129,
+      "step": 900
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 8e-05,
+      "loss": 0.0868,
+      "step": 1000
+    },
+    {
+      "epoch": 2.66,
+      "eval_accuracy": 0.9766366816591704,
+      "eval_f1": 0.9565217391304348,
+      "eval_loss": 0.09077496081590652,
+      "eval_precision": 0.9552631578947368,
+      "eval_recall": 0.9577836411609498,
+      "eval_runtime": 2.6166,
+      "eval_samples_per_second": 255.294,
+      "eval_steps_per_second": 16.051,
+      "step": 1000
+    },
+    {
+      "epoch": 2.93,
+      "eval_accuracy": 0.9761369315342329,
+      "eval_f1": 0.9558021440662028,
+      "eval_loss": 0.09924957156181335,
+      "eval_precision": 0.9538288288288288,
+      "eval_recall": 0.9577836411609498,
+      "eval_runtime": 2.6844,
+      "eval_samples_per_second": 248.843,
+      "eval_steps_per_second": 15.646,
+      "step": 1100
+    },
+    {
+      "epoch": 3.19,
+      "eval_accuracy": 0.9767616191904048,
+      "eval_f1": 0.9542975362046267,
+      "eval_loss": 0.08850151300430298,
+      "eval_precision": 0.9523273273273273,
+      "eval_recall": 0.9562759140595553,
+      "eval_runtime": 2.8038,
+      "eval_samples_per_second": 238.25,
+      "eval_steps_per_second": 14.98,
+      "step": 1200
+    },
+    {
+      "epoch": 3.46,
+      "eval_accuracy": 0.9770114942528736,
+      "eval_f1": 0.9576191373139952,
+      "eval_loss": 0.09413458406925201,
+      "eval_precision": 0.9570783132530121,
+      "eval_recall": 0.9581605729362985,
+      "eval_runtime": 2.631,
+      "eval_samples_per_second": 253.897,
+      "eval_steps_per_second": 15.964,
+      "step": 1300
+    },
+    {
+      "epoch": 3.72,
+      "eval_accuracy": 0.9758870564717641,
+      "eval_f1": 0.9575871819038644,
+      "eval_loss": 0.09968729317188263,
+      "eval_precision": 0.9577677224736049,
+      "eval_recall": 0.9574067093856012,
+      "eval_runtime": 2.6616,
+      "eval_samples_per_second": 250.976,
+      "eval_steps_per_second": 15.78,
+      "step": 1400
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 7e-05,
+      "loss": 0.056,
+      "step": 1500
+    },
+    {
+      "epoch": 3.99,
+      "eval_accuracy": 0.974887556221889,
+      "eval_f1": 0.9591106086301111,
+      "eval_loss": 0.10856281220912933,
+      "eval_precision": 0.9589299171062547,
+      "eval_recall": 0.9592913682623445,
+      "eval_runtime": 2.616,
+      "eval_samples_per_second": 255.356,
+      "eval_steps_per_second": 16.055,
+      "step": 1500
+    },
+    {
+      "epoch": 4.26,
+      "eval_accuracy": 0.9762618690654673,
+      "eval_f1": 0.9577836411609498,
+      "eval_loss": 0.10103093087673187,
+      "eval_precision": 0.9577836411609498,
+      "eval_recall": 0.9577836411609498,
+      "eval_runtime": 2.6677,
+      "eval_samples_per_second": 250.406,
+      "eval_steps_per_second": 15.744,
+      "step": 1600
+    },
+    {
+      "epoch": 4.52,
+      "eval_accuracy": 0.9783858070964517,
+      "eval_f1": 0.9612198795180723,
+      "eval_loss": 0.09965386986732483,
+      "eval_precision": 0.9601353892440767,
+      "eval_recall": 0.9623068224651338,
+      "eval_runtime": 2.9477,
+      "eval_samples_per_second": 226.62,
+      "eval_steps_per_second": 14.249,
+      "step": 1700
+    },
+    {
+      "epoch": 4.79,
+      "eval_accuracy": 0.975512243878061,
+      "eval_f1": 0.9551957831325302,
+      "eval_loss": 0.10638727992773056,
+      "eval_precision": 0.9541180895073336,
+      "eval_recall": 0.9562759140595553,
+      "eval_runtime": 2.6219,
+      "eval_samples_per_second": 254.779,
+      "eval_steps_per_second": 16.019,
+      "step": 1800
+    },
+    {
+      "epoch": 5.05,
+      "eval_accuracy": 0.9757621189405298,
+      "eval_f1": 0.9559984956750659,
+      "eval_loss": 0.09631699323654175,
+      "eval_precision": 0.9538461538461539,
+      "eval_recall": 0.9581605729362985,
+      "eval_runtime": 2.6401,
+      "eval_samples_per_second": 253.021,
+      "eval_steps_per_second": 15.908,
+      "step": 1900
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 6e-05,
+      "loss": 0.04,
+      "step": 2000
+    },
+    {
+      "epoch": 5.32,
+      "eval_accuracy": 0.9777611194402799,
+      "eval_f1": 0.9612490594431903,
+      "eval_loss": 0.09422445297241211,
+      "eval_precision": 0.9594442358242583,
+      "eval_recall": 0.9630606860158312,
+      "eval_runtime": 2.6383,
+      "eval_samples_per_second": 253.191,
+      "eval_steps_per_second": 15.919,
+      "step": 2000
+    }
+  ],
+  "max_steps": 5000,
+  "num_train_epochs": 14,
+  "total_flos": 790348180152456.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414647f811ebf9ca8f02bde659b5ecabd916d671a6e16632fd0c18225c2e2901
+size 3055