adding model finetuned on POS

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9915840240182692,
+    "eval_f1": 0.9903327607558025,
+    "eval_loss": 0.03334970399737358,
+    "eval_precision": 0.9900361414508496,
+    "eval_recall": 0.9906295578509919,
+    "eval_runtime": 2.9623,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 558.347,
+    "eval_steps_per_second": 35.108,
+    "train_loss": 0.06446368148206999,
+    "train_runtime": 136.8646,
+    "train_samples": 14305,
+    "train_samples_per_second": 209.039,
+    "train_steps_per_second": 13.079
+}

config.json

@@ -0,0 +1,69 @@
+{
+  "_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": "pos",
+  "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",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": 2.0,
+    "eval_accuracy": 0.9915840240182692,
+    "eval_f1": 0.9903327607558025,
+    "eval_loss": 0.03334970399737358,
+    "eval_precision": 0.9900361414508496,
+    "eval_recall": 0.9906295578509919,
+    "eval_runtime": 2.9623,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 558.347,
+    "eval_steps_per_second": 35.108
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f513d61e2bec19fc6534c338a51374fdb5906fb991982ed464ffc31e76361b8c
+size 496351025

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": 2.0,
+    "train_loss": 0.06446368148206999,
+    "train_runtime": 136.8646,
+    "train_samples": 14305,
+    "train_samples_per_second": 209.039,
+    "train_steps_per_second": 13.079
+}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": 0.03334970399737358,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/pos/bertin_roberta_base/epochs_2_bs_16_lr_5e-5/checkpoint-1600",
+  "epoch": 2.0,
+  "global_step": 1790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.983631166259442,
+      "eval_f1": 0.9806329240291506,
+      "eval_loss": 0.06692877411842346,
+      "eval_precision": 0.9799676769289092,
+      "eval_recall": 0.9812990749435576,
+      "eval_runtime": 2.9547,
+      "eval_samples_per_second": 559.789,
+      "eval_steps_per_second": 35.198,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.9877353518900014,
+      "eval_f1": 0.9855665575341371,
+      "eval_loss": 0.0487518236041069,
+      "eval_precision": 0.9847605369716554,
+      "eval_recall": 0.9863738986234041,
+      "eval_runtime": 2.9562,
+      "eval_samples_per_second": 559.497,
+      "eval_steps_per_second": 35.18,
+      "step": 400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.606145251396648e-05,
+      "loss": 0.17,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.9896197639694022,
+      "eval_f1": 0.9876868689894844,
+      "eval_loss": 0.0419081449508667,
+      "eval_precision": 0.9873417721518988,
+      "eval_recall": 0.9880322071487083,
+      "eval_runtime": 2.9607,
+      "eval_samples_per_second": 558.66,
+      "eval_steps_per_second": 35.127,
+      "step": 600
+    },
+    {
+      "epoch": 0.89,
+      "eval_accuracy": 0.9898912470655872,
+      "eval_f1": 0.9883067213884146,
+      "eval_loss": 0.039409052580595016,
+      "eval_precision": 0.987902259841891,
+      "eval_recall": 0.9887115142554594,
+      "eval_runtime": 2.9548,
+      "eval_samples_per_second": 559.772,
+      "eval_steps_per_second": 35.197,
+      "step": 800
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.2094972067039108e-05,
+      "loss": 0.0356,
+      "step": 1000
+    },
+    {
+      "epoch": 1.12,
+      "eval_accuracy": 0.9899072166594803,
+      "eval_f1": 0.9888547117804499,
+      "eval_loss": 0.03804260864853859,
+      "eval_precision": 0.9885585351730197,
+      "eval_recall": 0.989151065912769,
+      "eval_runtime": 2.9587,
+      "eval_samples_per_second": 559.024,
+      "eval_steps_per_second": 35.15,
+      "step": 1000
+    },
+    {
+      "epoch": 1.34,
+      "eval_accuracy": 0.9901786997556652,
+      "eval_f1": 0.9885585351730197,
+      "eval_loss": 0.04127265512943268,
+      "eval_precision": 0.9879667138951528,
+      "eval_recall": 0.989151065912769,
+      "eval_runtime": 3.0133,
+      "eval_samples_per_second": 548.892,
+      "eval_steps_per_second": 34.513,
+      "step": 1200
+    },
+    {
+      "epoch": 1.56,
+      "eval_accuracy": 0.9912646321404047,
+      "eval_f1": 0.9899833221814985,
+      "eval_loss": 0.035211607813835144,
+      "eval_precision": 0.9896769298350705,
+      "eval_recall": 0.9902899042976164,
+      "eval_runtime": 2.9833,
+      "eval_samples_per_second": 554.427,
+      "eval_steps_per_second": 34.861,
+      "step": 1400
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.128491620111732e-06,
+      "loss": 0.0176,
+      "step": 1500
+    },
+    {
+      "epoch": 1.79,
+      "eval_accuracy": 0.9915840240182692,
+      "eval_f1": 0.9903327607558025,
+      "eval_loss": 0.03334970399737358,
+      "eval_precision": 0.9900361414508496,
+      "eval_recall": 0.9906295578509919,
+      "eval_runtime": 2.9696,
+      "eval_samples_per_second": 556.981,
+      "eval_steps_per_second": 35.022,
+      "step": 1600
+    },
+    {
+      "epoch": 2.0,
+      "step": 1790,
+      "total_flos": 1190583063933120.0,
+      "train_loss": 0.06446368148206999,
+      "train_runtime": 136.8646,
+      "train_samples_per_second": 209.039,
+      "train_steps_per_second": 13.079
+    }
+  ],
+  "max_steps": 1790,
+  "num_train_epochs": 2,
+  "total_flos": 1190583063933120.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac5cf597aeb52364501a2450d2e5034f403a18065bca6c9e196c68418b9606c7
+size 2991