adding model finetuned on PAWS-X

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9075000286102295,
+    "eval_loss": 0.2576049864292145,
+    "eval_runtime": 10.2119,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 195.849,
+    "eval_steps_per_second": 6.169,
+    "train_loss": 0.17779028992166998,
+    "train_runtime": 4326.2693,
+    "train_samples": 49401,
+    "train_samples_per_second": 34.257,
+    "train_steps_per_second": 1.071
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "CenIA/albert_xlarge_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": 2048,
+  "initializer_range": 0.01,
+  "inner_group_num": 1,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 32,
+  "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": 3.0,
+    "eval_accuracy": 0.9075000286102295,
+    "eval_loss": 0.2576049864292145,
+    "eval_runtime": 10.2119,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 195.849,
+    "eval_steps_per_second": 6.169
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d6a86180fe18ac873a838007fac0e874b0cc66c4abaed3e4c22027572eacb9
+size 235442897

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_xlarge_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.17779028992166998,
+    "train_runtime": 4326.2693,
+    "train_samples": 49401,
+    "train_samples_per_second": 34.257,
+    "train_steps_per_second": 1.071
+}

trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_metric": 0.2576049864292145,
+  "best_model_checkpoint": "/data/jcanete/all_results/pawsx/albeto_xlarge/epochs_3_bs_32_lr_5e-6/checkpoint-1200",
+  "epoch": 3.0,
+  "global_step": 4632,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.7799999713897705,
+      "eval_loss": 0.4942445755004883,
+      "eval_runtime": 10.4303,
+      "eval_samples_per_second": 191.749,
+      "eval_steps_per_second": 6.04,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.465673575129534e-06,
+      "loss": 0.4488,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.8755000233650208,
+      "eval_loss": 0.3036494255065918,
+      "eval_runtime": 10.411,
+      "eval_samples_per_second": 192.104,
+      "eval_steps_per_second": 6.051,
+      "step": 600
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.8794999718666077,
+      "eval_loss": 0.29540833830833435,
+      "eval_runtime": 10.4508,
+      "eval_samples_per_second": 191.372,
+      "eval_steps_per_second": 6.028,
+      "step": 900
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.925949913644214e-06,
+      "loss": 0.2328,
+      "step": 1000
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.9075000286102295,
+      "eval_loss": 0.2576049864292145,
+      "eval_runtime": 10.4132,
+      "eval_samples_per_second": 192.063,
+      "eval_steps_per_second": 6.05,
+      "step": 1200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.386226252158895e-06,
+      "loss": 0.2015,
+      "step": 1500
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.8995000123977661,
+      "eval_loss": 0.2740257680416107,
+      "eval_runtime": 10.4482,
+      "eval_samples_per_second": 191.42,
+      "eval_steps_per_second": 6.03,
+      "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "eval_accuracy": 0.9020000100135803,
+      "eval_loss": 0.2881057858467102,
+      "eval_runtime": 10.4618,
+      "eval_samples_per_second": 191.171,
+      "eval_steps_per_second": 6.022,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.8465025906735755e-06,
+      "loss": 0.1539,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "eval_accuracy": 0.906499981880188,
+      "eval_loss": 0.2683846056461334,
+      "eval_runtime": 10.4536,
+      "eval_samples_per_second": 191.321,
+      "eval_steps_per_second": 6.027,
+      "step": 2100
+    },
+    {
+      "epoch": 1.55,
+      "eval_accuracy": 0.906000018119812,
+      "eval_loss": 0.34197333455085754,
+      "eval_runtime": 10.4733,
+      "eval_samples_per_second": 190.961,
+      "eval_steps_per_second": 6.015,
+      "step": 2400
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.3078583765112265e-06,
+      "loss": 0.1428,
+      "step": 2500
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.906499981880188,
+      "eval_loss": 0.3059616684913635,
+      "eval_runtime": 10.4777,
+      "eval_samples_per_second": 190.882,
+      "eval_steps_per_second": 6.013,
+      "step": 2700
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.7681347150259068e-06,
+      "loss": 0.1399,
+      "step": 3000
+    },
+    {
+      "epoch": 1.94,
+      "eval_accuracy": 0.9020000100135803,
+      "eval_loss": 0.2935360372066498,
+      "eval_runtime": 10.5064,
+      "eval_samples_per_second": 190.361,
+      "eval_steps_per_second": 5.996,
+      "step": 3000
+    },
+    {
+      "epoch": 2.14,
+      "eval_accuracy": 0.909500002861023,
+      "eval_loss": 0.3417232036590576,
+      "eval_runtime": 10.4876,
+      "eval_samples_per_second": 190.702,
+      "eval_steps_per_second": 6.007,
+      "step": 3300
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.2284110535405874e-06,
+      "loss": 0.1069,
+      "step": 3500
+    },
+    {
+      "epoch": 2.33,
+      "eval_accuracy": 0.8999999761581421,
+      "eval_loss": 0.4427025616168976,
+      "eval_runtime": 10.5396,
+      "eval_samples_per_second": 189.761,
+      "eval_steps_per_second": 5.977,
+      "step": 3600
+    },
+    {
+      "epoch": 2.53,
+      "eval_accuracy": 0.9039999842643738,
+      "eval_loss": 0.40283679962158203,
+      "eval_runtime": 10.5439,
+      "eval_samples_per_second": 189.684,
+      "eval_steps_per_second": 5.975,
+      "step": 3900
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 6.886873920552678e-07,
+      "loss": 0.1009,
+      "step": 4000
+    },
+    {
+      "epoch": 2.72,
+      "eval_accuracy": 0.9024999737739563,
+      "eval_loss": 0.4096806049346924,
+      "eval_runtime": 10.4683,
+      "eval_samples_per_second": 191.052,
+      "eval_steps_per_second": 6.018,
+      "step": 4200
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.5004317789291884e-07,
+      "loss": 0.0936,
+      "step": 4500
+    },
+    {
+      "epoch": 2.91,
+      "eval_accuracy": 0.9070000052452087,
+      "eval_loss": 0.4148932099342346,
+      "eval_runtime": 10.465,
+      "eval_samples_per_second": 191.113,
+      "eval_steps_per_second": 6.02,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "step": 4632,
+      "total_flos": 4794349372791840.0,
+      "train_loss": 0.17779028992166998,
+      "train_runtime": 4326.2693,
+      "train_samples_per_second": 34.257,
+      "train_steps_per_second": 1.071
+    }
+  ],
+  "max_steps": 4632,
+  "num_train_epochs": 3,
+  "total_flos": 4794349372791840.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2585956d6222beedc9fcd435b684018f501d9f0a7c42a645cb986213474b53
+size 2863