adding model finetuned on MLDoc

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9739999771118164,
+    "eval_loss": 0.1305142641067505,
+    "eval_runtime": 4.1433,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 241.351,
+    "eval_steps_per_second": 7.723,
+    "train_loss": 0.06248773110879434,
+    "train_runtime": 2406.595,
+    "train_samples": 9458,
+    "train_samples_per_second": 11.79,
+    "train_steps_per_second": 0.369
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "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": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9739999771118164,
+    "eval_loss": 0.1305142641067505,
+    "eval_runtime": 4.1433,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 241.351,
+    "eval_steps_per_second": 7.723
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e201172ef2f495ab4d44986029aab980a8af3a087883da4d48e9bd6fe8b9197
+size 439499949

special_tokens_map.json

@@ -0,0 +1 @@
+{"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, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/data/jcanete/cache/78141ed1e8dcc5ff370950397ca0d1c5c9da478f54ec14544187d8a93eff1a26.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66", "name_or_path": "dccuchile/bert-base-spanish-wwm-uncased", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.06248773110879434,
+    "train_runtime": 2406.595,
+    "train_samples": 9458,
+    "train_samples_per_second": 11.79,
+    "train_steps_per_second": 0.369
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": 0.1305142641067505,
+  "best_model_checkpoint": "/data/jcanete/all_results/mldoc/beto_uncased/epochs_3_bs_32_lr_2e-5/checkpoint-700",
+  "epoch": 3.0,
+  "global_step": 888,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.9110000133514404,
+      "eval_loss": 0.33802908658981323,
+      "eval_runtime": 8.5211,
+      "eval_samples_per_second": 117.356,
+      "eval_steps_per_second": 3.755,
+      "step": 100
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.921999990940094,
+      "eval_loss": 0.2501136362552643,
+      "eval_runtime": 7.3325,
+      "eval_samples_per_second": 136.379,
+      "eval_steps_per_second": 4.364,
+      "step": 200
+    },
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.9570000171661377,
+      "eval_loss": 0.18152756989002228,
+      "eval_runtime": 4.1659,
+      "eval_samples_per_second": 240.043,
+      "eval_steps_per_second": 7.681,
+      "step": 300
+    },
+    {
+      "epoch": 1.35,
+      "eval_accuracy": 0.9649999737739563,
+      "eval_loss": 0.1706397831439972,
+      "eval_runtime": 4.1609,
+      "eval_samples_per_second": 240.333,
+      "eval_steps_per_second": 7.691,
+      "step": 400
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.738738738738739e-06,
+      "loss": 0.0887,
+      "step": 500
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.9610000252723694,
+      "eval_loss": 0.14937655627727509,
+      "eval_runtime": 8.5296,
+      "eval_samples_per_second": 117.239,
+      "eval_steps_per_second": 3.752,
+      "step": 500
+    },
+    {
+      "epoch": 2.03,
+      "eval_accuracy": 0.9660000205039978,
+      "eval_loss": 0.14822959899902344,
+      "eval_runtime": 7.4689,
+      "eval_samples_per_second": 133.888,
+      "eval_steps_per_second": 4.284,
+      "step": 600
+    },
+    {
+      "epoch": 2.36,
+      "eval_accuracy": 0.9739999771118164,
+      "eval_loss": 0.1305142641067505,
+      "eval_runtime": 4.1624,
+      "eval_samples_per_second": 240.248,
+      "eval_steps_per_second": 7.688,
+      "step": 700
+    },
+    {
+      "epoch": 2.7,
+      "eval_accuracy": 0.9639999866485596,
+      "eval_loss": 0.14460867643356323,
+      "eval_runtime": 4.1529,
+      "eval_samples_per_second": 240.797,
+      "eval_steps_per_second": 7.706,
+      "step": 800
+    },
+    {
+      "epoch": 3.0,
+      "step": 888,
+      "total_flos": 6921827938826112.0,
+      "train_loss": 0.06248773110879434,
+      "train_runtime": 2406.595,
+      "train_samples_per_second": 11.79,
+      "train_steps_per_second": 0.369
+    }
+  ],
+  "max_steps": 888,
+  "num_train_epochs": 3,
+  "total_flos": 6921827938826112.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044ba870746a26466cef510763104d7e67b848f167ff5c269897a7b3a7fe78a3
+size 2863