adding model finetuned on MLDoc

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9639999866485596,
+    "eval_loss": 0.15715740621089935,
+    "eval_runtime": 4.3422,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 230.296,
+    "eval_steps_per_second": 14.509,
+    "train_loss": 0.07163469533662538,
+    "train_runtime": 1355.547,
+    "train_samples": 9458,
+    "train_samples_per_second": 27.909,
+    "train_steps_per_second": 1.747
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "CenIA/albert_base_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": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "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": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9639999866485596,
+    "eval_loss": 0.15715740621089935,
+    "eval_runtime": 4.3422,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 230.296,
+    "eval_steps_per_second": 14.509
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812cb1e206989fb55fd538abe04b066ffe408ae26ac87a862eec74bebf8e218a
+size 47273681

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_base_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.07163469533662538,
+    "train_runtime": 1355.547,
+    "train_samples": 9458,
+    "train_samples_per_second": 27.909,
+    "train_steps_per_second": 1.747
+}

trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": 0.15715740621089935,
+  "best_model_checkpoint": "/data/jcanete/all_results/mldoc/albeto_base/epochs_4_bs_16_lr_5e-5/checkpoint-1400",
+  "epoch": 4.0,
+  "global_step": 2368,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.7229999899864197,
+      "eval_loss": 1.0613000392913818,
+      "eval_runtime": 4.4363,
+      "eval_samples_per_second": 225.412,
+      "eval_steps_per_second": 14.201,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.7990000247955322,
+      "eval_loss": 0.672461748123169,
+      "eval_runtime": 4.3549,
+      "eval_samples_per_second": 229.626,
+      "eval_steps_per_second": 14.466,
+      "step": 200
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.8479999899864197,
+      "eval_loss": 0.523521900177002,
+      "eval_runtime": 4.3517,
+      "eval_samples_per_second": 229.796,
+      "eval_steps_per_second": 14.477,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.8930000066757202,
+      "eval_loss": 0.4281160831451416,
+      "eval_runtime": 4.3489,
+      "eval_samples_per_second": 229.946,
+      "eval_steps_per_second": 14.487,
+      "step": 400
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.94847972972973e-05,
+      "loss": 0.1597,
+      "step": 500
+    },
+    {
+      "epoch": 0.84,
+      "eval_accuracy": 0.9039999842643738,
+      "eval_loss": 0.4125765860080719,
+      "eval_runtime": 4.3451,
+      "eval_samples_per_second": 230.146,
+      "eval_steps_per_second": 14.499,
+      "step": 500
+    },
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.9020000100135803,
+      "eval_loss": 0.40425220131874084,
+      "eval_runtime": 4.3435,
+      "eval_samples_per_second": 230.229,
+      "eval_steps_per_second": 14.504,
+      "step": 600
+    },
+    {
+      "epoch": 1.18,
+      "eval_accuracy": 0.9340000152587891,
+      "eval_loss": 0.3148828148841858,
+      "eval_runtime": 4.3516,
+      "eval_samples_per_second": 229.803,
+      "eval_steps_per_second": 14.478,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "eval_accuracy": 0.9399999976158142,
+      "eval_loss": 0.30127567052841187,
+      "eval_runtime": 4.3657,
+      "eval_samples_per_second": 229.057,
+      "eval_steps_per_second": 14.431,
+      "step": 800
+    },
+    {
+      "epoch": 1.52,
+      "eval_accuracy": 0.949999988079071,
+      "eval_loss": 0.18032802641391754,
+      "eval_runtime": 4.3502,
+      "eval_samples_per_second": 229.873,
+      "eval_steps_per_second": 14.482,
+      "step": 900
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.8927364864864863e-05,
+      "loss": 0.0779,
+      "step": 1000
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.906000018119812,
+      "eval_loss": 0.4576403498649597,
+      "eval_runtime": 4.3481,
+      "eval_samples_per_second": 229.983,
+      "eval_steps_per_second": 14.489,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.9229999780654907,
+      "eval_loss": 0.30020907521247864,
+      "eval_runtime": 4.3386,
+      "eval_samples_per_second": 230.489,
+      "eval_steps_per_second": 14.521,
+      "step": 1100
+    },
+    {
+      "epoch": 2.03,
+      "eval_accuracy": 0.9449999928474426,
+      "eval_loss": 0.23847746849060059,
+      "eval_runtime": 4.3357,
+      "eval_samples_per_second": 230.642,
+      "eval_steps_per_second": 14.53,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2,
+      "eval_accuracy": 0.9580000042915344,
+      "eval_loss": 0.2000477910041809,
+      "eval_runtime": 4.3536,
+      "eval_samples_per_second": 229.694,
+      "eval_steps_per_second": 14.471,
+      "step": 1300
+    },
+    {
+      "epoch": 2.36,
+      "eval_accuracy": 0.9639999866485596,
+      "eval_loss": 0.15715740621089935,
+      "eval_runtime": 4.3678,
+      "eval_samples_per_second": 228.95,
+      "eval_steps_per_second": 14.424,
+      "step": 1400
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.8369932432432433e-05,
+      "loss": 0.0475,
+      "step": 1500
+    },
+    {
+      "epoch": 2.53,
+      "eval_accuracy": 0.9620000123977661,
+      "eval_loss": 0.19045613706111908,
+      "eval_runtime": 4.3587,
+      "eval_samples_per_second": 229.426,
+      "eval_steps_per_second": 14.454,
+      "step": 1500
+    },
+    {
+      "epoch": 2.7,
+      "eval_accuracy": 0.9639999866485596,
+      "eval_loss": 0.20174138247966766,
+      "eval_runtime": 4.348,
+      "eval_samples_per_second": 229.989,
+      "eval_steps_per_second": 14.489,
+      "step": 1600
+    },
+    {
+      "epoch": 2.87,
+      "eval_accuracy": 0.9520000219345093,
+      "eval_loss": 0.23974017798900604,
+      "eval_runtime": 4.3452,
+      "eval_samples_per_second": 230.141,
+      "eval_steps_per_second": 14.499,
+      "step": 1700
+    },
+    {
+      "epoch": 3.04,
+      "eval_accuracy": 0.9549999833106995,
+      "eval_loss": 0.1878175288438797,
+      "eval_runtime": 4.3435,
+      "eval_samples_per_second": 230.227,
+      "eval_steps_per_second": 14.504,
+      "step": 1800
+    },
+    {
+      "epoch": 3.21,
+      "eval_accuracy": 0.9520000219345093,
+      "eval_loss": 0.2655267119407654,
+      "eval_runtime": 4.3468,
+      "eval_samples_per_second": 230.053,
+      "eval_steps_per_second": 14.493,
+      "step": 1900
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.0362,
+      "step": 2000
+    },
+    {
+      "epoch": 3.38,
+      "eval_accuracy": 0.9629999995231628,
+      "eval_loss": 0.1756611317396164,
+      "eval_runtime": 4.3509,
+      "eval_samples_per_second": 229.836,
+      "eval_steps_per_second": 14.48,
+      "step": 2000
+    },
+    {
+      "epoch": 3.55,
+      "eval_accuracy": 0.9620000123977661,
+      "eval_loss": 0.19551004469394684,
+      "eval_runtime": 4.3485,
+      "eval_samples_per_second": 229.966,
+      "eval_steps_per_second": 14.488,
+      "step": 2100
+    },
+    {
+      "epoch": 3.72,
+      "eval_accuracy": 0.9559999704360962,
+      "eval_loss": 0.21292370557785034,
+      "eval_runtime": 4.357,
+      "eval_samples_per_second": 229.514,
+      "eval_steps_per_second": 14.459,
+      "step": 2200
+    },
+    {
+      "epoch": 3.89,
+      "eval_accuracy": 0.9559999704360962,
+      "eval_loss": 0.22236208617687225,
+      "eval_runtime": 4.3612,
+      "eval_samples_per_second": 229.297,
+      "eval_steps_per_second": 14.446,
+      "step": 2300
+    },
+    {
+      "epoch": 4.0,
+      "step": 2368,
+      "total_flos": 739476514563456.0,
+      "train_loss": 0.07163469533662538,
+      "train_runtime": 1355.547,
+      "train_samples_per_second": 27.909,
+      "train_steps_per_second": 1.747
+    }
+  ],
+  "max_steps": 2368,
+  "num_train_epochs": 4,
+  "total_flos": 739476514563456.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ba4bc41792dc921e6b818b1569afd0bc40189c659f9aeb1570ac39136e0ced
+size 2863