adding model finetuned on PAWS-X

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8899999856948853,
+    "eval_loss": 0.2880019545555115,
+    "eval_runtime": 1.4081,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1420.308,
+    "eval_steps_per_second": 22.725,
+    "train_loss": 0.18752603909718146,
+    "train_runtime": 736.4947,
+    "train_samples": 49401,
+    "train_samples_per_second": 201.228,
+    "train_steps_per_second": 3.145
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "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": 3.0,
+    "eval_accuracy": 0.8899999856948853,
+    "eval_loss": 0.2880019545555115,
+    "eval_runtime": 1.4081,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1420.308,
+    "eval_steps_per_second": 22.725
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bcb5c19b24d248ed5b6f1bb266ffc5e56218ca22e8f2ede38dd0e091c92a07
+size 47267537

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": 3.0,
+    "train_loss": 0.18752603909718146,
+    "train_runtime": 736.4947,
+    "train_samples": 49401,
+    "train_samples_per_second": 201.228,
+    "train_steps_per_second": 3.145
+}

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": 0.2880019545555115,
+  "best_model_checkpoint": "/data/jcanete/all_results/pawsx/albeto_base/epochs_3_bs_64_lr_5e-5/checkpoint-1500",
+  "epoch": 3.0,
+  "global_step": 2316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.8234999775886536,
+      "eval_loss": 0.4035343527793884,
+      "eval_runtime": 2.5624,
+      "eval_samples_per_second": 780.524,
+      "eval_steps_per_second": 12.488,
+      "step": 300
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.924870466321244e-05,
+      "loss": 0.3623,
+      "step": 500
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.8634999990463257,
+      "eval_loss": 0.3268177807331085,
+      "eval_runtime": 1.4365,
+      "eval_samples_per_second": 1392.272,
+      "eval_steps_per_second": 22.276,
+      "step": 600
+    },
+    {
+      "epoch": 1.17,
+      "eval_accuracy": 0.8774999976158142,
+      "eval_loss": 0.3128760755062103,
+      "eval_runtime": 1.4694,
+      "eval_samples_per_second": 1361.101,
+      "eval_steps_per_second": 21.778,
+      "step": 900
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.8454231433506046e-05,
+      "loss": 0.2024,
+      "step": 1000
+    },
+    {
+      "epoch": 1.55,
+      "eval_accuracy": 0.8759999871253967,
+      "eval_loss": 0.31563544273376465,
+      "eval_runtime": 2.7664,
+      "eval_samples_per_second": 722.974,
+      "eval_steps_per_second": 11.568,
+      "step": 1200
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.7659758203799656e-05,
+      "loss": 0.1576,
+      "step": 1500
+    },
+    {
+      "epoch": 1.94,
+      "eval_accuracy": 0.8899999856948853,
+      "eval_loss": 0.2880019545555115,
+      "eval_runtime": 1.5048,
+      "eval_samples_per_second": 1329.124,
+      "eval_steps_per_second": 21.266,
+      "step": 1500
+    },
+    {
+      "epoch": 2.33,
+      "eval_accuracy": 0.8820000290870667,
+      "eval_loss": 0.3631149232387543,
+      "eval_runtime": 1.466,
+      "eval_samples_per_second": 1364.255,
+      "eval_steps_per_second": 21.828,
+      "step": 1800
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 6.865284974093264e-06,
+      "loss": 0.0951,
+      "step": 2000
+    },
+    {
+      "epoch": 2.72,
+      "eval_accuracy": 0.8870000243186951,
+      "eval_loss": 0.3527218997478485,
+      "eval_runtime": 2.7631,
+      "eval_samples_per_second": 723.813,
+      "eval_steps_per_second": 11.581,
+      "step": 2100
+    },
+    {
+      "epoch": 3.0,
+      "step": 2316,
+      "total_flos": 712974847684320.0,
+      "train_loss": 0.18752603909718146,
+      "train_runtime": 736.4947,
+      "train_samples_per_second": 201.228,
+      "train_steps_per_second": 3.145
+    }
+  ],
+  "max_steps": 2316,
+  "num_train_epochs": 3,
+  "total_flos": 712974847684320.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1d531d62594cde696dd0e70bcb16efb90955ed9278ed24ffc16a3bf34edf96
+size 2863