adding model finetuned on MLDoc

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9589999914169312,
+    "eval_loss": 0.20911003649234772,
+    "eval_runtime": 24.6119,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 40.631,
+    "eval_steps_per_second": 5.079,
+    "train_loss": 0.1292072490857808,
+    "train_runtime": 3156.6951,
+    "train_samples": 9458,
+    "train_samples_per_second": 8.989,
+    "train_steps_per_second": 0.562
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "CenIA/albert_xlarge_spanish",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.01,
+  "inner_group_num": 1,
+  "intermediate_size": 8192,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 32,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 24,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9589999914169312,
+    "eval_loss": 0.20911003649234772,
+    "eval_runtime": 24.6119,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 40.631,
+    "eval_steps_per_second": 5.079
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e735a49adc1ab5e49253adf89a595d5b764fa8a5797d5f424662730a4fa74a9
+size 235459281

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "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, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "CenIA/albert_xlarge_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.1292072490857808,
+    "train_runtime": 3156.6951,
+    "train_samples": 9458,
+    "train_samples_per_second": 8.989,
+    "train_steps_per_second": 0.562
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": 0.20911003649234772,
+  "best_model_checkpoint": "/data/jcanete/all_results/mldoc/albeto_xlarge/epochs_3_bs_16_lr_5e-6/checkpoint-1500",
+  "epoch": 2.9991546914623837,
+  "global_step": 1773,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.2770000100135803,
+      "eval_loss": 1.3528416156768799,
+      "eval_runtime": 24.2204,
+      "eval_samples_per_second": 41.287,
+      "eval_steps_per_second": 5.161,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.47999998927116394,
+      "eval_loss": 1.0430142879486084,
+      "eval_runtime": 23.7736,
+      "eval_samples_per_second": 42.063,
+      "eval_steps_per_second": 5.258,
+      "step": 200
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.5640000104904175,
+      "eval_loss": 1.0979323387145996,
+      "eval_runtime": 23.5496,
+      "eval_samples_per_second": 42.464,
+      "eval_steps_per_second": 5.308,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.5720000267028809,
+      "eval_loss": 0.9388349652290344,
+      "eval_runtime": 25.4729,
+      "eval_samples_per_second": 39.257,
+      "eval_steps_per_second": 4.907,
+      "step": 400
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.601240834743373e-06,
+      "loss": 0.2676,
+      "step": 500
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.7160000205039978,
+      "eval_loss": 0.6925698518753052,
+      "eval_runtime": 24.8675,
+      "eval_samples_per_second": 40.213,
+      "eval_steps_per_second": 5.027,
+      "step": 500
+    },
+    {
+      "epoch": 1.02,
+      "eval_accuracy": 0.8560000061988831,
+      "eval_loss": 0.673073947429657,
+      "eval_runtime": 25.8013,
+      "eval_samples_per_second": 38.758,
+      "eval_steps_per_second": 4.845,
+      "step": 600
+    },
+    {
+      "epoch": 1.18,
+      "eval_accuracy": 0.9369999766349792,
+      "eval_loss": 0.3746216893196106,
+      "eval_runtime": 25.6232,
+      "eval_samples_per_second": 39.027,
+      "eval_steps_per_second": 4.878,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "eval_accuracy": 0.9350000023841858,
+      "eval_loss": 0.35705798864364624,
+      "eval_runtime": 25.7852,
+      "eval_samples_per_second": 38.782,
+      "eval_steps_per_second": 4.848,
+      "step": 800
+    },
+    {
+      "epoch": 1.52,
+      "eval_accuracy": 0.9409999847412109,
+      "eval_loss": 0.27689608931541443,
+      "eval_runtime": 24.8438,
+      "eval_samples_per_second": 40.252,
+      "eval_steps_per_second": 5.031,
+      "step": 900
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.1912013536379022e-06,
+      "loss": 0.1019,
+      "step": 1000
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.9350000023841858,
+      "eval_loss": 0.291538268327713,
+      "eval_runtime": 26.3153,
+      "eval_samples_per_second": 38.001,
+      "eval_steps_per_second": 4.75,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.9509999752044678,
+      "eval_loss": 0.21956732869148254,
+      "eval_runtime": 24.9343,
+      "eval_samples_per_second": 40.105,
+      "eval_steps_per_second": 5.013,
+      "step": 1100
+    },
+    {
+      "epoch": 2.03,
+      "eval_accuracy": 0.9520000219345093,
+      "eval_loss": 0.2259828746318817,
+      "eval_runtime": 25.7253,
+      "eval_samples_per_second": 38.872,
+      "eval_steps_per_second": 4.859,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2,
+      "eval_accuracy": 0.9509999752044678,
+      "eval_loss": 0.256782591342926,
+      "eval_runtime": 25.7431,
+      "eval_samples_per_second": 38.845,
+      "eval_steps_per_second": 4.856,
+      "step": 1300
+    },
+    {
+      "epoch": 2.37,
+      "eval_accuracy": 0.9549999833106995,
+      "eval_loss": 0.2290709912776947,
+      "eval_runtime": 24.8624,
+      "eval_samples_per_second": 40.221,
+      "eval_steps_per_second": 5.028,
+      "step": 1400
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.81161872532431e-07,
+      "loss": 0.0593,
+      "step": 1500
+    },
+    {
+      "epoch": 2.54,
+      "eval_accuracy": 0.9589999914169312,
+      "eval_loss": 0.20911003649234772,
+      "eval_runtime": 25.438,
+      "eval_samples_per_second": 39.311,
+      "eval_steps_per_second": 4.914,
+      "step": 1500
+    },
+    {
+      "epoch": 2.71,
+      "eval_accuracy": 0.9490000009536743,
+      "eval_loss": 0.2575547695159912,
+      "eval_runtime": 25.2822,
+      "eval_samples_per_second": 39.554,
+      "eval_steps_per_second": 4.944,
+      "step": 1600
+    },
+    {
+      "epoch": 2.88,
+      "eval_accuracy": 0.9509999752044678,
+      "eval_loss": 0.23298123478889465,
+      "eval_runtime": 25.3064,
+      "eval_samples_per_second": 39.516,
+      "eval_steps_per_second": 4.939,
+      "step": 1700
+    },
+    {
+      "epoch": 3.0,
+      "step": 1773,
+      "total_flos": 3375408735295488.0,
+      "train_loss": 0.1292072490857808,
+      "train_runtime": 3156.6951,
+      "train_samples_per_second": 8.989,
+      "train_steps_per_second": 0.562
+    }
+  ],
+  "max_steps": 1773,
+  "num_train_epochs": 3,
+  "total_flos": 3375408735295488.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953c7a5d3ce4d8d3ecb032712f0f30c74b466a219b2e6abc755f878a789a3a67
+size 2991