adding model finetuned on MLDoc

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9589999914169312,
+    "eval_loss": 0.15601937472820282,
+    "eval_runtime": 0.9975,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 1002.496,
+    "eval_steps_per_second": 63.157,
+    "train_loss": 0.09686436967269794,
+    "train_runtime": 383.5478,
+    "train_samples": 9458,
+    "train_samples_per_second": 98.637,
+    "train_steps_per_second": 6.174
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "CenIA/albert_tiny_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": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 1248,
+  "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": 4,
+  "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": 0.9589999914169312,
+    "eval_loss": 0.15601937472820282,
+    "eval_runtime": 0.9975,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 1002.496,
+    "eval_steps_per_second": 63.157
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3269b8bd19cf1b225145e4c88e5129ae69ac8d0c5606f5e8ee19885ebe588cf3
+size 21396433

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_tiny_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.09686436967269794,
+    "train_runtime": 383.5478,
+    "train_samples": 9458,
+    "train_samples_per_second": 98.637,
+    "train_steps_per_second": 6.174
+}

trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": 0.15601937472820282,
+  "best_model_checkpoint": "/data/jcanete/all_results/mldoc/albeto_tiny/epochs_4_bs_16_lr_3e-5/checkpoint-2100",
+  "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": 0.29100000858306885,
+      "eval_loss": 1.4215397834777832,
+      "eval_runtime": 0.9993,
+      "eval_samples_per_second": 1000.659,
+      "eval_steps_per_second": 63.042,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.5360000133514404,
+      "eval_loss": 1.0526843070983887,
+      "eval_runtime": 0.9899,
+      "eval_samples_per_second": 1010.212,
+      "eval_steps_per_second": 63.643,
+      "step": 200
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.7480000257492065,
+      "eval_loss": 0.8007577657699585,
+      "eval_runtime": 0.9905,
+      "eval_samples_per_second": 1009.612,
+      "eval_steps_per_second": 63.606,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.7699999809265137,
+      "eval_loss": 0.7043776512145996,
+      "eval_runtime": 1.0018,
+      "eval_samples_per_second": 998.248,
+      "eval_steps_per_second": 62.89,
+      "step": 400
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.3703547297297295e-05,
+      "loss": 0.2646,
+      "step": 500
+    },
+    {
+      "epoch": 0.84,
+      "eval_accuracy": 0.843999981880188,
+      "eval_loss": 0.46549031138420105,
+      "eval_runtime": 1.0012,
+      "eval_samples_per_second": 998.759,
+      "eval_steps_per_second": 62.922,
+      "step": 500
+    },
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.8529999852180481,
+      "eval_loss": 0.46177130937576294,
+      "eval_runtime": 0.9926,
+      "eval_samples_per_second": 1007.431,
+      "eval_steps_per_second": 63.468,
+      "step": 600
+    },
+    {
+      "epoch": 1.18,
+      "eval_accuracy": 0.9089999794960022,
+      "eval_loss": 0.3174803853034973,
+      "eval_runtime": 0.9914,
+      "eval_samples_per_second": 1008.709,
+      "eval_steps_per_second": 63.549,
+      "step": 700
+    },
+    {
+      "epoch": 1.35,
+      "eval_accuracy": 0.9269999861717224,
+      "eval_loss": 0.2770524322986603,
+      "eval_runtime": 0.9992,
+      "eval_samples_per_second": 1000.797,
+      "eval_steps_per_second": 63.05,
+      "step": 800
+    },
+    {
+      "epoch": 1.52,
+      "eval_accuracy": 0.9449999928474426,
+      "eval_loss": 0.2170553058385849,
+      "eval_runtime": 0.9905,
+      "eval_samples_per_second": 1009.635,
+      "eval_steps_per_second": 63.607,
+      "step": 900
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.736908783783784e-05,
+      "loss": 0.0843,
+      "step": 1000
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.9350000023841858,
+      "eval_loss": 0.23940612375736237,
+      "eval_runtime": 0.9908,
+      "eval_samples_per_second": 1009.32,
+      "eval_steps_per_second": 63.587,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.9480000138282776,
+      "eval_loss": 0.20756861567497253,
+      "eval_runtime": 1.0016,
+      "eval_samples_per_second": 998.361,
+      "eval_steps_per_second": 62.897,
+      "step": 1100
+    },
+    {
+      "epoch": 2.03,
+      "eval_accuracy": 0.9419999718666077,
+      "eval_loss": 0.21042801439762115,
+      "eval_runtime": 0.9893,
+      "eval_samples_per_second": 1010.862,
+      "eval_steps_per_second": 63.684,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2,
+      "eval_accuracy": 0.9509999752044678,
+      "eval_loss": 0.18397970497608185,
+      "eval_runtime": 0.9927,
+      "eval_samples_per_second": 1007.38,
+      "eval_steps_per_second": 63.465,
+      "step": 1300
+    },
+    {
+      "epoch": 2.36,
+      "eval_accuracy": 0.9549999833106995,
+      "eval_loss": 0.16272501647472382,
+      "eval_runtime": 0.9936,
+      "eval_samples_per_second": 1006.426,
+      "eval_steps_per_second": 63.405,
+      "step": 1400
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.1047297297297297e-05,
+      "loss": 0.0457,
+      "step": 1500
+    },
+    {
+      "epoch": 2.53,
+      "eval_accuracy": 0.9380000233650208,
+      "eval_loss": 0.21701455116271973,
+      "eval_runtime": 0.992,
+      "eval_samples_per_second": 1008.023,
+      "eval_steps_per_second": 63.505,
+      "step": 1500
+    },
+    {
+      "epoch": 2.7,
+      "eval_accuracy": 0.9419999718666077,
+      "eval_loss": 0.20601776242256165,
+      "eval_runtime": 0.9926,
+      "eval_samples_per_second": 1007.478,
+      "eval_steps_per_second": 63.471,
+      "step": 1600
+    },
+    {
+      "epoch": 2.87,
+      "eval_accuracy": 0.9520000219345093,
+      "eval_loss": 0.1742561310529709,
+      "eval_runtime": 0.9948,
+      "eval_samples_per_second": 1005.234,
+      "eval_steps_per_second": 63.33,
+      "step": 1700
+    },
+    {
+      "epoch": 3.04,
+      "eval_accuracy": 0.9490000009536743,
+      "eval_loss": 0.17574115097522736,
+      "eval_runtime": 0.9934,
+      "eval_samples_per_second": 1006.664,
+      "eval_steps_per_second": 63.42,
+      "step": 1800
+    },
+    {
+      "epoch": 3.21,
+      "eval_accuracy": 0.9399999976158142,
+      "eval_loss": 0.21880225837230682,
+      "eval_runtime": 1.0033,
+      "eval_samples_per_second": 996.71,
+      "eval_steps_per_second": 62.793,
+      "step": 1900
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 4.712837837837838e-06,
+      "loss": 0.0388,
+      "step": 2000
+    },
+    {
+      "epoch": 3.38,
+      "eval_accuracy": 0.9559999704360962,
+      "eval_loss": 0.16699624061584473,
+      "eval_runtime": 0.9915,
+      "eval_samples_per_second": 1008.575,
+      "eval_steps_per_second": 63.54,
+      "step": 2000
+    },
+    {
+      "epoch": 3.55,
+      "eval_accuracy": 0.9589999914169312,
+      "eval_loss": 0.15601937472820282,
+      "eval_runtime": 0.9908,
+      "eval_samples_per_second": 1009.251,
+      "eval_steps_per_second": 63.583,
+      "step": 2100
+    },
+    {
+      "epoch": 3.72,
+      "eval_accuracy": 0.9559999704360962,
+      "eval_loss": 0.1640777885913849,
+      "eval_runtime": 0.9918,
+      "eval_samples_per_second": 1008.262,
+      "eval_steps_per_second": 63.521,
+      "step": 2200
+    },
+    {
+      "epoch": 3.89,
+      "eval_accuracy": 0.9549999833106995,
+      "eval_loss": 0.16484832763671875,
+      "eval_runtime": 1.0391,
+      "eval_samples_per_second": 962.351,
+      "eval_steps_per_second": 60.628,
+      "step": 2300
+    },
+    {
+      "epoch": 4.0,
+      "step": 2368,
+      "total_flos": 124651187836032.0,
+      "train_loss": 0.09686436967269794,
+      "train_runtime": 383.5478,
+      "train_samples_per_second": 98.637,
+      "train_steps_per_second": 6.174
+    }
+  ],
+  "max_steps": 2368,
+  "num_train_epochs": 4,
+  "total_flos": 124651187836032.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b101cb827efbf2428ac696f8952cdeb6a429ee10475c5e291e76cd4327de1e9e
+size 2863