adding model finetuned on MLDoc

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9710000157356262,
+    "eval_loss": 0.13781137764453888,
+    "eval_runtime": 2.1129,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 473.282,
+    "eval_steps_per_second": 29.817,
+    "train_loss": 0.077526035609546,
+    "train_runtime": 3451.0165,
+    "train_samples": 9458,
+    "train_samples_per_second": 8.222,
+    "train_steps_per_second": 0.515
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "CenIA/distillbert-base-spanish-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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": "4.15.0",
+  "vocab_size": 31002
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9710000157356262,
+    "eval_loss": 0.13781137764453888,
+    "eval_runtime": 2.1129,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 473.282,
+    "eval_steps_per_second": 29.817
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e5387e4752cca2931333dd92b4f90baf0eed4f92834caa2f3595a1cf7914d1
+size 269340785

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": 3.0,
+    "train_loss": 0.077526035609546,
+    "train_runtime": 3451.0165,
+    "train_samples": 9458,
+    "train_samples_per_second": 8.222,
+    "train_steps_per_second": 0.515
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": 0.13781137764453888,
+  "best_model_checkpoint": "/data/jcanete/all_results/mldoc/distillbeto/epochs_3_bs_16_lr_2e-5/checkpoint-900",
+  "epoch": 3.0,
+  "global_step": 1776,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.7329999804496765,
+      "eval_loss": 0.9082120656967163,
+      "eval_runtime": 2.085,
+      "eval_samples_per_second": 479.613,
+      "eval_steps_per_second": 30.216,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.8560000061988831,
+      "eval_loss": 0.47957685589790344,
+      "eval_runtime": 2.0816,
+      "eval_samples_per_second": 480.41,
+      "eval_steps_per_second": 30.266,
+      "step": 200
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.9480000138282776,
+      "eval_loss": 0.23153278231620789,
+      "eval_runtime": 2.0846,
+      "eval_samples_per_second": 479.697,
+      "eval_steps_per_second": 30.221,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.9309999942779541,
+      "eval_loss": 0.25234749913215637,
+      "eval_runtime": 2.0857,
+      "eval_samples_per_second": 479.464,
+      "eval_steps_per_second": 30.206,
+      "step": 400
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.4391891891891894e-05,
+      "loss": 0.1569,
+      "step": 500
+    },
+    {
+      "epoch": 0.84,
+      "eval_accuracy": 0.9539999961853027,
+      "eval_loss": 0.18860605359077454,
+      "eval_runtime": 2.0884,
+      "eval_samples_per_second": 478.832,
+      "eval_steps_per_second": 30.166,
+      "step": 500
+    },
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.9020000100135803,
+      "eval_loss": 0.3387507200241089,
+      "eval_runtime": 2.0825,
+      "eval_samples_per_second": 480.196,
+      "eval_steps_per_second": 30.252,
+      "step": 600
+    },
+    {
+      "epoch": 1.18,
+      "eval_accuracy": 0.9610000252723694,
+      "eval_loss": 0.16218014061450958,
+      "eval_runtime": 2.0844,
+      "eval_samples_per_second": 479.763,
+      "eval_steps_per_second": 30.225,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "eval_accuracy": 0.9509999752044678,
+      "eval_loss": 0.18978460133075714,
+      "eval_runtime": 2.0789,
+      "eval_samples_per_second": 481.026,
+      "eval_steps_per_second": 30.305,
+      "step": 800
+    },
+    {
+      "epoch": 1.52,
+      "eval_accuracy": 0.9710000157356262,
+      "eval_loss": 0.13781137764453888,
+      "eval_runtime": 2.0825,
+      "eval_samples_per_second": 480.201,
+      "eval_steps_per_second": 30.253,
+      "step": 900
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.772522522522522e-06,
+      "loss": 0.0617,
+      "step": 1000
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.9610000252723694,
+      "eval_loss": 0.1706898957490921,
+      "eval_runtime": 2.0817,
+      "eval_samples_per_second": 480.376,
+      "eval_steps_per_second": 30.264,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.9599999785423279,
+      "eval_loss": 0.1884380429983139,
+      "eval_runtime": 2.08,
+      "eval_samples_per_second": 480.775,
+      "eval_steps_per_second": 30.289,
+      "step": 1100
+    },
+    {
+      "epoch": 2.03,
+      "eval_accuracy": 0.9570000171661377,
+      "eval_loss": 0.20238688588142395,
+      "eval_runtime": 2.0822,
+      "eval_samples_per_second": 480.271,
+      "eval_steps_per_second": 30.257,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2,
+      "eval_accuracy": 0.9589999914169312,
+      "eval_loss": 0.1709979772567749,
+      "eval_runtime": 2.0789,
+      "eval_samples_per_second": 481.035,
+      "eval_steps_per_second": 30.305,
+      "step": 1300
+    },
+    {
+      "epoch": 2.36,
+      "eval_accuracy": 0.9610000252723694,
+      "eval_loss": 0.1705155074596405,
+      "eval_runtime": 2.0769,
+      "eval_samples_per_second": 481.48,
+      "eval_steps_per_second": 30.333,
+      "step": 1400
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 3.141891891891892e-06,
+      "loss": 0.0353,
+      "step": 1500
+    },
+    {
+      "epoch": 2.53,
+      "eval_accuracy": 0.9570000171661377,
+      "eval_loss": 0.18021175265312195,
+      "eval_runtime": 2.0858,
+      "eval_samples_per_second": 479.427,
+      "eval_steps_per_second": 30.204,
+      "step": 1500
+    },
+    {
+      "epoch": 2.7,
+      "eval_accuracy": 0.9520000219345093,
+      "eval_loss": 0.19292205572128296,
+      "eval_runtime": 2.0769,
+      "eval_samples_per_second": 481.487,
+      "eval_steps_per_second": 30.334,
+      "step": 1600
+    },
+    {
+      "epoch": 2.87,
+      "eval_accuracy": 0.9570000171661377,
+      "eval_loss": 0.1787494271993637,
+      "eval_runtime": 2.0981,
+      "eval_samples_per_second": 476.617,
+      "eval_steps_per_second": 30.027,
+      "step": 1700
+    },
+    {
+      "epoch": 3.0,
+      "step": 1776,
+      "total_flos": 3142677580766976.0,
+      "train_loss": 0.077526035609546,
+      "train_runtime": 3451.0165,
+      "train_samples_per_second": 8.222,
+      "train_steps_per_second": 0.515
+    }
+  ],
+  "max_steps": 1776,
+  "num_train_epochs": 3,
+  "total_flos": 3142677580766976.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637313ac57b5fb0399a2045f9e6e7de5a414a069434f6f288f81bcfb6305f008
+size 2991