adding model finetuned on PAWS-X

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.8769999742507935,
+    "eval_loss": 0.31465813517570496,
+    "eval_runtime": 3.6867,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 542.491,
+    "eval_steps_per_second": 17.088,
+    "train_loss": 0.2719091473465756,
+    "train_runtime": 1265.6788,
+    "train_samples": 49401,
+    "train_samples_per_second": 78.062,
+    "train_steps_per_second": 2.44
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 4096,
+  "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": "4.12.5",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.8769999742507935,
+    "eval_loss": 0.31465813517570496,
+    "eval_runtime": 3.6867,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 542.491,
+    "eval_steps_per_second": 17.088
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0e96bdc581083f47cee1c31bb6d38dddb7e6ebd52d27ca8706006f664d1ad0
+size 71271121

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": 2.0,
+    "train_loss": 0.2719091473465756,
+    "train_runtime": 1265.6788,
+    "train_samples": 49401,
+    "train_samples_per_second": 78.062,
+    "train_steps_per_second": 2.44
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": 0.31465813517570496,
+  "best_model_checkpoint": "/data/jcanete/all_results/pawsx/albeto_large/epochs_2_bs_32_lr_5e-6/checkpoint-2700",
+  "epoch": 2.0,
+  "global_step": 3088,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.7465000152587891,
+      "eval_loss": 0.5256621241569519,
+      "eval_runtime": 3.674,
+      "eval_samples_per_second": 544.365,
+      "eval_steps_per_second": 17.148,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.195272020725389e-06,
+      "loss": 0.5015,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.8044999837875366,
+      "eval_loss": 0.42749786376953125,
+      "eval_runtime": 3.7001,
+      "eval_samples_per_second": 540.533,
+      "eval_steps_per_second": 17.027,
+      "step": 600
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.8335000276565552,
+      "eval_loss": 0.40074634552001953,
+      "eval_runtime": 3.6783,
+      "eval_samples_per_second": 543.722,
+      "eval_steps_per_second": 17.127,
+      "step": 900
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.3856865284974094e-06,
+      "loss": 0.302,
+      "step": 1000
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.8454999923706055,
+      "eval_loss": 0.3730817139148712,
+      "eval_runtime": 3.6669,
+      "eval_samples_per_second": 545.419,
+      "eval_steps_per_second": 17.181,
+      "step": 1200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.5761010362694307e-06,
+      "loss": 0.2552,
+      "step": 1500
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.859000027179718,
+      "eval_loss": 0.33458662033081055,
+      "eval_runtime": 3.679,
+      "eval_samples_per_second": 543.627,
+      "eval_steps_per_second": 17.124,
+      "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "eval_accuracy": 0.8654999732971191,
+      "eval_loss": 0.33431583642959595,
+      "eval_runtime": 3.6739,
+      "eval_samples_per_second": 544.382,
+      "eval_steps_per_second": 17.148,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.7665155440414508e-06,
+      "loss": 0.2051,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "eval_accuracy": 0.871999979019165,
+      "eval_loss": 0.3163151144981384,
+      "eval_runtime": 3.662,
+      "eval_samples_per_second": 546.147,
+      "eval_steps_per_second": 17.204,
+      "step": 2100
+    },
+    {
+      "epoch": 1.55,
+      "eval_accuracy": 0.8784999847412109,
+      "eval_loss": 0.31933271884918213,
+      "eval_runtime": 3.6771,
+      "eval_samples_per_second": 543.901,
+      "eval_steps_per_second": 17.133,
+      "step": 2400
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.585492227979275e-07,
+      "loss": 0.1902,
+      "step": 2500
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.8769999742507935,
+      "eval_loss": 0.31465813517570496,
+      "eval_runtime": 3.6635,
+      "eval_samples_per_second": 545.931,
+      "eval_steps_per_second": 17.197,
+      "step": 2700
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.4896373056994818e-07,
+      "loss": 0.1928,
+      "step": 3000
+    },
+    {
+      "epoch": 1.94,
+      "eval_accuracy": 0.871999979019165,
+      "eval_loss": 0.32511112093925476,
+      "eval_runtime": 3.6606,
+      "eval_samples_per_second": 546.359,
+      "eval_steps_per_second": 17.21,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "step": 3088,
+      "total_flos": 803053584088992.0,
+      "train_loss": 0.2719091473465756,
+      "train_runtime": 1265.6788,
+      "train_samples_per_second": 78.062,
+      "train_steps_per_second": 2.44
+    }
+  ],
+  "max_steps": 3088,
+  "num_train_epochs": 2,
+  "total_flos": 803053584088992.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ffbc4b2bfd960eaa93feecdd7dc52e9d2a09af3c36d2507b2cf1771ff1c627
+size 2863