adding model finetuned on MLDoc

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9319999814033508,
+    "eval_loss": 0.25090140104293823,
+    "eval_runtime": 7.9702,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 125.467,
+    "eval_steps_per_second": 7.904,
+    "train_loss": 0.13927180917413384,
+    "train_runtime": 1029.288,
+    "train_samples": 9458,
+    "train_samples_per_second": 27.567,
+    "train_steps_per_second": 1.725
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "CenIA/albert_large_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": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 4096,
+  "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": 16,
+  "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": 0.9319999814033508,
+    "eval_loss": 0.25090140104293823,
+    "eval_runtime": 7.9702,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 125.467,
+    "eval_steps_per_second": 7.904
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f070dc4144f82fa89ab0a7d6607824ec8c7611447301d444fff4de68102ece6
+size 71279313

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_large_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.13927180917413384,
+    "train_runtime": 1029.288,
+    "train_samples": 9458,
+    "train_samples_per_second": 27.567,
+    "train_steps_per_second": 1.725
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": 0.25090140104293823,
+  "best_model_checkpoint": "/data/jcanete/all_results/mldoc/albeto_large/epochs_3_bs_16_lr_5e-6/checkpoint-1700",
+  "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": 0.28299999237060547,
+      "eval_loss": 1.2837506532669067,
+      "eval_runtime": 8.1555,
+      "eval_samples_per_second": 122.617,
+      "eval_steps_per_second": 7.725,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.531000018119812,
+      "eval_loss": 1.1732338666915894,
+      "eval_runtime": 8.1951,
+      "eval_samples_per_second": 122.024,
+      "eval_steps_per_second": 7.688,
+      "step": 200
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.5540000200271606,
+      "eval_loss": 0.9090207815170288,
+      "eval_runtime": 8.1405,
+      "eval_samples_per_second": 122.843,
+      "eval_steps_per_second": 7.739,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.5619999766349792,
+      "eval_loss": 0.8500489592552185,
+      "eval_runtime": 8.4022,
+      "eval_samples_per_second": 119.017,
+      "eval_steps_per_second": 7.498,
+      "step": 400
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.603603603603604e-06,
+      "loss": 0.2667,
+      "step": 500
+    },
+    {
+      "epoch": 0.84,
+      "eval_accuracy": 0.6660000085830688,
+      "eval_loss": 0.7123118042945862,
+      "eval_runtime": 8.0822,
+      "eval_samples_per_second": 123.728,
+      "eval_steps_per_second": 7.795,
+      "step": 500
+    },
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.7820000052452087,
+      "eval_loss": 0.6517438888549805,
+      "eval_runtime": 8.9908,
+      "eval_samples_per_second": 111.225,
+      "eval_steps_per_second": 7.007,
+      "step": 600
+    },
+    {
+      "epoch": 1.18,
+      "eval_accuracy": 0.8230000138282776,
+      "eval_loss": 0.5667398571968079,
+      "eval_runtime": 8.2149,
+      "eval_samples_per_second": 121.73,
+      "eval_steps_per_second": 7.669,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "eval_accuracy": 0.8650000095367432,
+      "eval_loss": 0.47660863399505615,
+      "eval_runtime": 8.0853,
+      "eval_samples_per_second": 123.682,
+      "eval_steps_per_second": 7.792,
+      "step": 800
+    },
+    {
+      "epoch": 1.52,
+      "eval_accuracy": 0.8799999952316284,
+      "eval_loss": 0.38954979181289673,
+      "eval_runtime": 8.0289,
+      "eval_samples_per_second": 124.55,
+      "eval_steps_per_second": 7.847,
+      "step": 900
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.195945945945946e-06,
+      "loss": 0.1264,
+      "step": 1000
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.8420000076293945,
+      "eval_loss": 0.5382915139198303,
+      "eval_runtime": 8.0917,
+      "eval_samples_per_second": 123.584,
+      "eval_steps_per_second": 7.786,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.9100000262260437,
+      "eval_loss": 0.36202001571655273,
+      "eval_runtime": 7.986,
+      "eval_samples_per_second": 125.219,
+      "eval_steps_per_second": 7.889,
+      "step": 1100
+    },
+    {
+      "epoch": 2.03,
+      "eval_accuracy": 0.9240000247955322,
+      "eval_loss": 0.3379409909248352,
+      "eval_runtime": 8.6218,
+      "eval_samples_per_second": 115.985,
+      "eval_steps_per_second": 7.307,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2,
+      "eval_accuracy": 0.9279999732971191,
+      "eval_loss": 0.29248443245887756,
+      "eval_runtime": 8.2615,
+      "eval_samples_per_second": 121.044,
+      "eval_steps_per_second": 7.626,
+      "step": 1300
+    },
+    {
+      "epoch": 2.36,
+      "eval_accuracy": 0.9240000247955322,
+      "eval_loss": 0.28705379366874695,
+      "eval_runtime": 8.1584,
+      "eval_samples_per_second": 122.573,
+      "eval_steps_per_second": 7.722,
+      "step": 1400
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.882882882882883e-07,
+      "loss": 0.0676,
+      "step": 1500
+    },
+    {
+      "epoch": 2.53,
+      "eval_accuracy": 0.9279999732971191,
+      "eval_loss": 0.2619408965110779,
+      "eval_runtime": 7.9492,
+      "eval_samples_per_second": 125.798,
+      "eval_steps_per_second": 7.925,
+      "step": 1500
+    },
+    {
+      "epoch": 2.7,
+      "eval_accuracy": 0.9279999732971191,
+      "eval_loss": 0.26721176505088806,
+      "eval_runtime": 7.9627,
+      "eval_samples_per_second": 125.585,
+      "eval_steps_per_second": 7.912,
+      "step": 1600
+    },
+    {
+      "epoch": 2.87,
+      "eval_accuracy": 0.9319999814033508,
+      "eval_loss": 0.25090140104293823,
+      "eval_runtime": 8.0714,
+      "eval_samples_per_second": 123.894,
+      "eval_steps_per_second": 7.805,
+      "step": 1700
+    },
+    {
+      "epoch": 3.0,
+      "step": 1776,
+      "total_flos": 982359617226624.0,
+      "train_loss": 0.13927180917413384,
+      "train_runtime": 1029.288,
+      "train_samples_per_second": 27.567,
+      "train_steps_per_second": 1.725
+    }
+  ],
+  "max_steps": 1776,
+  "num_train_epochs": 3,
+  "total_flos": 982359617226624.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7b63643cbc0eeaa406f97fce357ba18e60f4bbc4f6f59a8e3aea6c44bdd7e0
+size 2991