adding model finetuned on PAWS-X

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.7749999761581421,
+    "eval_loss": 0.4636478126049042,
+    "eval_runtime": 0.7753,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2579.631,
+    "eval_steps_per_second": 81.258,
+    "train_loss": 0.35224579220608726,
+    "train_runtime": 2738.1778,
+    "train_samples": 49401,
+    "train_samples_per_second": 72.166,
+    "train_steps_per_second": 2.256
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "CenIA/distillbert-base-spanish-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "vocab_size": 31002
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.7749999761581421,
+    "eval_loss": 0.4636478126049042,
+    "eval_runtime": 0.7753,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2579.631,
+    "eval_steps_per_second": 81.258
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c689041160d348a9a0d5a025da59406f41dc34a3f8dcd8fbbb4dd0e7432748
+size 269334641

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "CenIA/distillbert-base-spanish-uncased", "tokenizer_class": "DistilBertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.35224579220608726,
+    "train_runtime": 2738.1778,
+    "train_samples": 49401,
+    "train_samples_per_second": 72.166,
+    "train_steps_per_second": 2.256
+}

trainer_state.json

@@ -0,0 +1,277 @@
+{
+  "best_metric": 0.4636478126049042,
+  "best_model_checkpoint": "/data/jcanete/all_results/pawsx/distillbeto/epochs_4_bs_32_lr_5e-5/checkpoint-2100",
+  "epoch": 4.0,
+  "global_step": 6176,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.5805000066757202,
+      "eval_loss": 0.6699569225311279,
+      "eval_runtime": 0.7381,
+      "eval_samples_per_second": 2709.802,
+      "eval_steps_per_second": 85.359,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.596826424870467e-05,
+      "loss": 0.6641,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.6809999942779541,
+      "eval_loss": 0.5914173722267151,
+      "eval_runtime": 0.7361,
+      "eval_samples_per_second": 2717.087,
+      "eval_steps_per_second": 85.588,
+      "step": 600
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.7275000214576721,
+      "eval_loss": 0.5336065888404846,
+      "eval_runtime": 0.7255,
+      "eval_samples_per_second": 2756.65,
+      "eval_steps_per_second": 86.834,
+      "step": 900
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.192033678756477e-05,
+      "loss": 0.5478,
+      "step": 1000
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.746999979019165,
+      "eval_loss": 0.5002644062042236,
+      "eval_runtime": 0.7294,
+      "eval_samples_per_second": 2741.855,
+      "eval_steps_per_second": 86.368,
+      "step": 1200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.787240932642487e-05,
+      "loss": 0.4937,
+      "step": 1500
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.7515000104904175,
+      "eval_loss": 0.493168443441391,
+      "eval_runtime": 0.7379,
+      "eval_samples_per_second": 2710.282,
+      "eval_steps_per_second": 85.374,
+      "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "eval_accuracy": 0.7570000290870667,
+      "eval_loss": 0.5791745781898499,
+      "eval_runtime": 0.7412,
+      "eval_samples_per_second": 2698.347,
+      "eval_steps_per_second": 84.998,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.3832577720207255e-05,
+      "loss": 0.3997,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "eval_accuracy": 0.7749999761581421,
+      "eval_loss": 0.4636478126049042,
+      "eval_runtime": 0.7343,
+      "eval_samples_per_second": 2723.768,
+      "eval_steps_per_second": 85.799,
+      "step": 2100
+    },
+    {
+      "epoch": 1.55,
+      "eval_accuracy": 0.7730000019073486,
+      "eval_loss": 0.4842735230922699,
+      "eval_runtime": 0.728,
+      "eval_samples_per_second": 2747.191,
+      "eval_steps_per_second": 86.537,
+      "step": 2400
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.978465025906736e-05,
+      "loss": 0.3796,
+      "step": 2500
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.7789999842643738,
+      "eval_loss": 0.4961821436882019,
+      "eval_runtime": 0.7387,
+      "eval_samples_per_second": 2707.452,
+      "eval_steps_per_second": 85.285,
+      "step": 2700
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.5736722797927466e-05,
+      "loss": 0.3598,
+      "step": 3000
+    },
+    {
+      "epoch": 1.94,
+      "eval_accuracy": 0.7879999876022339,
+      "eval_loss": 0.46712586283683777,
+      "eval_runtime": 0.7391,
+      "eval_samples_per_second": 2705.908,
+      "eval_steps_per_second": 85.236,
+      "step": 3000
+    },
+    {
+      "epoch": 2.14,
+      "eval_accuracy": 0.7885000109672546,
+      "eval_loss": 0.5191779732704163,
+      "eval_runtime": 0.7313,
+      "eval_samples_per_second": 2734.943,
+      "eval_steps_per_second": 86.151,
+      "step": 3300
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.1688795336787565e-05,
+      "loss": 0.2884,
+      "step": 3500
+    },
+    {
+      "epoch": 2.33,
+      "eval_accuracy": 0.7925000190734863,
+      "eval_loss": 0.5480718612670898,
+      "eval_runtime": 0.7293,
+      "eval_samples_per_second": 2742.348,
+      "eval_steps_per_second": 86.384,
+      "step": 3600
+    },
+    {
+      "epoch": 2.53,
+      "eval_accuracy": 0.7735000252723694,
+      "eval_loss": 0.5514509081840515,
+      "eval_runtime": 0.735,
+      "eval_samples_per_second": 2721.166,
+      "eval_steps_per_second": 85.717,
+      "step": 3900
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.7640867875647667e-05,
+      "loss": 0.27,
+      "step": 4000
+    },
+    {
+      "epoch": 2.72,
+      "eval_accuracy": 0.7879999876022339,
+      "eval_loss": 0.5070611238479614,
+      "eval_runtime": 0.7377,
+      "eval_samples_per_second": 2710.994,
+      "eval_steps_per_second": 85.396,
+      "step": 4200
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.3601036269430053e-05,
+      "loss": 0.2665,
+      "step": 4500
+    },
+    {
+      "epoch": 2.91,
+      "eval_accuracy": 0.7875000238418579,
+      "eval_loss": 0.5371026992797852,
+      "eval_runtime": 0.7291,
+      "eval_samples_per_second": 2743.286,
+      "eval_steps_per_second": 86.413,
+      "step": 4500
+    },
+    {
+      "epoch": 3.11,
+      "eval_accuracy": 0.7910000085830688,
+      "eval_loss": 0.624961793422699,
+      "eval_runtime": 0.7282,
+      "eval_samples_per_second": 2746.606,
+      "eval_steps_per_second": 86.518,
+      "step": 4800
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 9.553108808290157e-06,
+      "loss": 0.2171,
+      "step": 5000
+    },
+    {
+      "epoch": 3.3,
+      "eval_accuracy": 0.7940000295639038,
+      "eval_loss": 0.5903840065002441,
+      "eval_runtime": 0.7375,
+      "eval_samples_per_second": 2712.014,
+      "eval_steps_per_second": 85.428,
+      "step": 5100
+    },
+    {
+      "epoch": 3.5,
+      "eval_accuracy": 0.7850000262260437,
+      "eval_loss": 0.598899781703949,
+      "eval_runtime": 0.7383,
+      "eval_samples_per_second": 2709.079,
+      "eval_steps_per_second": 85.336,
+      "step": 5400
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 5.50518134715026e-06,
+      "loss": 0.2083,
+      "step": 5500
+    },
+    {
+      "epoch": 3.69,
+      "eval_accuracy": 0.7910000085830688,
+      "eval_loss": 0.5919374227523804,
+      "eval_runtime": 0.7401,
+      "eval_samples_per_second": 2702.433,
+      "eval_steps_per_second": 85.127,
+      "step": 5700
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.4653497409326426e-06,
+      "loss": 0.1906,
+      "step": 6000
+    },
+    {
+      "epoch": 3.89,
+      "eval_accuracy": 0.7864999771118164,
+      "eval_loss": 0.6115372180938721,
+      "eval_runtime": 0.7292,
+      "eval_samples_per_second": 2742.712,
+      "eval_steps_per_second": 86.395,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "step": 6176,
+      "total_flos": 4946498250063360.0,
+      "train_loss": 0.35224579220608726,
+      "train_runtime": 2738.1778,
+      "train_samples_per_second": 72.166,
+      "train_steps_per_second": 2.256
+    }
+  ],
+  "max_steps": 6176,
+  "num_train_epochs": 4,
+  "total_flos": 4946498250063360.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75616072a877c7ebd6616fcc0a774d79f47e92472fcb7cf9f488cc3657444f51
+size 2863