adding model finetuned on NER

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9777703135973618,
+    "eval_f1": 0.8632724446171783,
+    "eval_loss": 0.09008093178272247,
+    "eval_precision": 0.8535198278512143,
+    "eval_recall": 0.8732505110866489,
+    "eval_runtime": 2.5664,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 746.578,
+    "eval_steps_per_second": 46.759,
+    "train_loss": 0.08574806804925451,
+    "train_runtime": 168.5849,
+    "train_samples": 8324,
+    "train_samples_per_second": 148.127,
+    "train_steps_per_second": 9.271
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "bertin-project/bertin-roberta-base-spanish",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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": 50262
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9777703135973618,
+    "eval_f1": 0.8632724446171783,
+    "eval_loss": 0.09008093178272247,
+    "eval_precision": 0.8535198278512143,
+    "eval_recall": 0.8732505110866489,
+    "eval_runtime": 2.5664,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 746.578,
+    "eval_steps_per_second": 46.759
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157b08174a2976a55b86f7a0c9898fdd9488f7c6e2afd43f07f129bc2203f2a2
+size 496323313

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "bertin-project/bertin-roberta-base-spanish", "do_lower_case": false, "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.08574806804925451,
+    "train_runtime": 168.5849,
+    "train_samples": 8324,
+    "train_samples_per_second": 148.127,
+    "train_steps_per_second": 9.271
+}

trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_metric": 0.09008093178272247,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/ner/bertin_roberta_base/epochs_3_bs_16_lr_3e-5/checkpoint-900",
+  "epoch": 3.0,
+  "global_step": 1563,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.8860423219029588,
+      "eval_f1": 0.348936885452559,
+      "eval_loss": 0.3453126847743988,
+      "eval_precision": 0.3747292418772563,
+      "eval_recall": 0.3264664255386067,
+      "eval_runtime": 2.6554,
+      "eval_samples_per_second": 721.552,
+      "eval_steps_per_second": 45.191,
+      "step": 100
+    },
+    {
+      "epoch": 0.38,
+      "eval_accuracy": 0.9502274878622248,
+      "eval_f1": 0.6605220354736272,
+      "eval_loss": 0.1896633505821228,
+      "eval_precision": 0.6507936507936508,
+      "eval_recall": 0.6705456832835351,
+      "eval_runtime": 2.5793,
+      "eval_samples_per_second": 742.845,
+      "eval_steps_per_second": 46.525,
+      "step": 200
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.9694952517634127,
+      "eval_f1": 0.8140789988267502,
+      "eval_loss": 0.11993961036205292,
+      "eval_precision": 0.8098350451291628,
+      "eval_recall": 0.818367667872307,
+      "eval_runtime": 2.5794,
+      "eval_samples_per_second": 742.807,
+      "eval_steps_per_second": 46.522,
+      "step": 300
+    },
+    {
+      "epoch": 0.77,
+      "eval_accuracy": 0.9709762130141378,
+      "eval_f1": 0.8182973316391361,
+      "eval_loss": 0.11212530732154846,
+      "eval_precision": 0.8265682656826568,
+      "eval_recall": 0.8101902814908004,
+      "eval_runtime": 2.5886,
+      "eval_samples_per_second": 740.159,
+      "eval_steps_per_second": 46.357,
+      "step": 400
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.0460652591170824e-05,
+      "loss": 0.2024,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.9743350942013497,
+      "eval_f1": 0.8378357811429876,
+      "eval_loss": 0.09800967574119568,
+      "eval_precision": 0.8117074609259806,
+      "eval_recall": 0.8657021544267967,
+      "eval_runtime": 2.5773,
+      "eval_samples_per_second": 743.42,
+      "eval_steps_per_second": 46.561,
+      "step": 500
+    },
+    {
+      "epoch": 1.15,
+      "eval_accuracy": 0.9757091819597545,
+      "eval_f1": 0.8524022961390265,
+      "eval_loss": 0.09717094898223877,
+      "eval_precision": 0.8524693299779805,
+      "eval_recall": 0.8523352728416418,
+      "eval_runtime": 2.6535,
+      "eval_samples_per_second": 722.067,
+      "eval_steps_per_second": 45.223,
+      "step": 600
+    },
+    {
+      "epoch": 1.34,
+      "eval_accuracy": 0.9756633790344743,
+      "eval_f1": 0.8469219278245145,
+      "eval_loss": 0.10494286566972733,
+      "eval_precision": 0.8468553459119497,
+      "eval_recall": 0.8469885202075798,
+      "eval_runtime": 2.5616,
+      "eval_samples_per_second": 747.968,
+      "eval_steps_per_second": 46.846,
+      "step": 700
+    },
+    {
+      "epoch": 1.54,
+      "eval_accuracy": 0.9754343644080735,
+      "eval_f1": 0.8522736197282652,
+      "eval_loss": 0.1033582091331482,
+      "eval_precision": 0.8512707875745215,
+      "eval_recall": 0.8532788174241233,
+      "eval_runtime": 2.5767,
+      "eval_samples_per_second": 743.6,
+      "eval_steps_per_second": 46.572,
+      "step": 800
+    },
+    {
+      "epoch": 1.73,
+      "eval_accuracy": 0.9777703135973618,
+      "eval_f1": 0.8632724446171783,
+      "eval_loss": 0.09008093178272247,
+      "eval_precision": 0.8535198278512143,
+      "eval_recall": 0.8732505110866489,
+      "eval_runtime": 2.5668,
+      "eval_samples_per_second": 746.461,
+      "eval_steps_per_second": 46.751,
+      "step": 900
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.0863723608445298e-05,
+      "loss": 0.0435,
+      "step": 1000
+    },
+    {
+      "epoch": 1.92,
+      "eval_accuracy": 0.9767779168829582,
+      "eval_f1": 0.8591637849732788,
+      "eval_loss": 0.09683168679475784,
+      "eval_precision": 0.8587588373919874,
+      "eval_recall": 0.8595691146406668,
+      "eval_runtime": 2.5807,
+      "eval_samples_per_second": 742.428,
+      "eval_steps_per_second": 46.499,
+      "step": 1000
+    },
+    {
+      "epoch": 2.11,
+      "eval_accuracy": 0.9784726251183242,
+      "eval_f1": 0.8643483709273184,
+      "eval_loss": 0.09452169388532639,
+      "eval_precision": 0.8609767514432829,
+      "eval_recall": 0.8677465010221733,
+      "eval_runtime": 2.5589,
+      "eval_samples_per_second": 748.766,
+      "eval_steps_per_second": 46.896,
+      "step": 1100
+    },
+    {
+      "epoch": 2.3,
+      "eval_accuracy": 0.9770527344346392,
+      "eval_f1": 0.8597122302158274,
+      "eval_loss": 0.10257242619991302,
+      "eval_precision": 0.8550318867631047,
+      "eval_recall": 0.864444094983488,
+      "eval_runtime": 2.7283,
+      "eval_samples_per_second": 702.266,
+      "eval_steps_per_second": 43.983,
+      "step": 1200
+    },
+    {
+      "epoch": 2.5,
+      "eval_accuracy": 0.9772054108522398,
+      "eval_f1": 0.8668813319720412,
+      "eval_loss": 0.10338085889816284,
+      "eval_precision": 0.8658613115782868,
+      "eval_recall": 0.8679037584525869,
+      "eval_runtime": 2.5673,
+      "eval_samples_per_second": 746.324,
+      "eval_steps_per_second": 46.743,
+      "step": 1300
+    },
+    {
+      "epoch": 2.69,
+      "eval_accuracy": 0.9771290726434395,
+      "eval_f1": 0.8576551294044278,
+      "eval_loss": 0.09793581068515778,
+      "eval_precision": 0.8503632709846962,
+      "eval_recall": 0.8650731247051423,
+      "eval_runtime": 2.5716,
+      "eval_samples_per_second": 745.057,
+      "eval_steps_per_second": 46.663,
+      "step": 1400
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.2667946257197696e-06,
+      "loss": 0.02,
+      "step": 1500
+    },
+    {
+      "epoch": 2.88,
+      "eval_accuracy": 0.9782130752084033,
+      "eval_f1": 0.868623450007848,
+      "eval_loss": 0.09656020998954773,
+      "eval_precision": 0.8669904433651888,
+      "eval_recall": 0.8702626199087907,
+      "eval_runtime": 2.5726,
+      "eval_samples_per_second": 744.76,
+      "eval_steps_per_second": 46.645,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "step": 1563,
+      "total_flos": 1130082001089408.0,
+      "train_loss": 0.08574806804925451,
+      "train_runtime": 168.5849,
+      "train_samples_per_second": 148.127,
+      "train_steps_per_second": 9.271
+    }
+  ],
+  "max_steps": 1563,
+  "num_train_epochs": 3,
+  "total_flos": 1130082001089408.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc5fafbd9fa4e91e4c2ea2b8aa9dbf18388a9937a8d1e4ecf44addddbb44539
+size 2991