adding model finetuned on mldoc

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9649999737739563,
+    "eval_loss": 0.14659787714481354,
+    "eval_runtime": 1.8722,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 534.122,
+    "eval_steps_per_second": 17.092,
+    "train_loss": 0.07292293032278886,
+    "train_runtime": 179.7572,
+    "train_samples": 9458,
+    "train_samples_per_second": 210.462,
+    "train_steps_per_second": 6.587
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "dccuchile/albert-base-10-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": 10,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9649999737739563,
+    "eval_loss": 0.14659787714481354,
+    "eval_runtime": 1.8722,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 534.122,
+    "eval_steps_per_second": 17.092
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9871f9d0177a75c7e1c538e3476473cdd3aefff9c2b758df6292f230affd8c1
+size 47272325

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "dccuchile/albert-base-10-spanish",
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.07292293032278886,
+    "train_runtime": 179.7572,
+    "train_samples": 9458,
+    "train_samples_per_second": 210.462,
+    "train_steps_per_second": 6.587
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": 0.14659787714481354,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/mldoc/albeto_base_10/epochs_4_bs_32_lr_5e-5/checkpoint-700",
+  "epoch": 4.0,
+  "global_step": 1184,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.746999979019165,
+      "eval_loss": 0.6933977007865906,
+      "eval_runtime": 1.8687,
+      "eval_samples_per_second": 535.118,
+      "eval_steps_per_second": 17.124,
+      "step": 100
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.8700000047683716,
+      "eval_loss": 0.4119150638580322,
+      "eval_runtime": 1.8696,
+      "eval_samples_per_second": 534.864,
+      "eval_steps_per_second": 17.116,
+      "step": 200
+    },
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.9269999861717224,
+      "eval_loss": 0.28070709109306335,
+      "eval_runtime": 1.8707,
+      "eval_samples_per_second": 534.572,
+      "eval_steps_per_second": 17.106,
+      "step": 300
+    },
+    {
+      "epoch": 1.35,
+      "eval_accuracy": 0.9279999732971191,
+      "eval_loss": 0.25755012035369873,
+      "eval_runtime": 1.8729,
+      "eval_samples_per_second": 533.927,
+      "eval_steps_per_second": 17.086,
+      "step": 400
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.8927364864864863e-05,
+      "loss": 0.1279,
+      "step": 500
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.9440000057220459,
+      "eval_loss": 0.25176554918289185,
+      "eval_runtime": 1.8715,
+      "eval_samples_per_second": 534.323,
+      "eval_steps_per_second": 17.098,
+      "step": 500
+    },
+    {
+      "epoch": 2.03,
+      "eval_accuracy": 0.9620000123977661,
+      "eval_loss": 0.1778251677751541,
+      "eval_runtime": 1.8729,
+      "eval_samples_per_second": 533.922,
+      "eval_steps_per_second": 17.086,
+      "step": 600
+    },
+    {
+      "epoch": 2.36,
+      "eval_accuracy": 0.9649999737739563,
+      "eval_loss": 0.14659787714481354,
+      "eval_runtime": 1.872,
+      "eval_samples_per_second": 534.185,
+      "eval_steps_per_second": 17.094,
+      "step": 700
+    },
+    {
+      "epoch": 2.7,
+      "eval_accuracy": 0.9539999961853027,
+      "eval_loss": 0.19388286769390106,
+      "eval_runtime": 1.8707,
+      "eval_samples_per_second": 534.552,
+      "eval_steps_per_second": 17.106,
+      "step": 800
+    },
+    {
+      "epoch": 3.04,
+      "eval_accuracy": 0.9620000123977661,
+      "eval_loss": 0.16352728009223938,
+      "eval_runtime": 1.8714,
+      "eval_samples_per_second": 534.363,
+      "eval_steps_per_second": 17.1,
+      "step": 900
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.0377,
+      "step": 1000
+    },
+    {
+      "epoch": 3.38,
+      "eval_accuracy": 0.9430000185966492,
+      "eval_loss": 0.22912634909152985,
+      "eval_runtime": 1.8706,
+      "eval_samples_per_second": 534.593,
+      "eval_steps_per_second": 17.107,
+      "step": 1000
+    },
+    {
+      "epoch": 3.72,
+      "eval_accuracy": 0.953000009059906,
+      "eval_loss": 0.1914745718240738,
+      "eval_runtime": 1.8687,
+      "eval_samples_per_second": 535.118,
+      "eval_steps_per_second": 17.124,
+      "step": 1100
+    },
+    {
+      "epoch": 4.0,
+      "step": 1184,
+      "total_flos": 824085797689344.0,
+      "train_loss": 0.07292293032278886,
+      "train_runtime": 179.7572,
+      "train_samples_per_second": 210.462,
+      "train_steps_per_second": 6.587
+    }
+  ],
+  "max_steps": 1184,
+  "num_train_epochs": 4,
+  "total_flos": 824085797689344.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de604a5285733dd090bbdec57cdcf6e991793ac06ac3a2a5d9b778da2977075
+size 3515