Push best model used for final benchmarks (single-trial)

checkpoint-1648/config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Seguro",
+    "1": "Inseguro"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Inseguro": 1,
+    "Seguro": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

checkpoint-1648/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fe504166f73f588da43eea04bea82e5f447b1cb80503821123b452634d6917
+size 1337640872

checkpoint-1648/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb5568ec50d7d2adaa8bd92336c3d8916957998dc5bf584485cce082024170e
+size 2675522558

checkpoint-1648/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3a49aa6ba0b334be9336e9745e0ca906d7deed618aa53d1fb3e479f9611b3c
+size 14645

checkpoint-1648/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5d8d9d4bad86de0a2e5d55b08b70345344466be951bfd2a614c6f8d29c9696
+size 1465

checkpoint-1648/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-1648/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-1648/trainer_state.json

@@ -0,0 +1,276 @@
+{
+  "best_global_step": 1648,
+  "best_metric": 0.8505448040331761,
+  "best_model_checkpoint": "outputs/final-run/checkpoint-1648",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1648,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06071645415907711,
+      "grad_norm": 3.4285213947296143,
+      "learning_rate": 4.9993183714305955e-05,
+      "loss": 0.5245,
+      "step": 50
+    },
+    {
+      "epoch": 0.12143290831815422,
+      "grad_norm": 5.290835857391357,
+      "learning_rate": 4.997217948372208e-05,
+      "loss": 0.4587,
+      "step": 100
+    },
+    {
+      "epoch": 0.18214936247723132,
+      "grad_norm": 3.585462808609009,
+      "learning_rate": 4.993699639509482e-05,
+      "loss": 0.453,
+      "step": 150
+    },
+    {
+      "epoch": 0.24286581663630843,
+      "grad_norm": 4.0983781814575195,
+      "learning_rate": 4.9887654424895166e-05,
+      "loss": 0.4216,
+      "step": 200
+    },
+    {
+      "epoch": 0.3035822707953855,
+      "grad_norm": 3.8998911380767822,
+      "learning_rate": 4.982418158881122e-05,
+      "loss": 0.4285,
+      "step": 250
+    },
+    {
+      "epoch": 0.36429872495446264,
+      "grad_norm": 4.210261821746826,
+      "learning_rate": 4.974661392584119e-05,
+      "loss": 0.4026,
+      "step": 300
+    },
+    {
+      "epoch": 0.42501517911353975,
+      "grad_norm": 3.36633038520813,
+      "learning_rate": 4.965499547783105e-05,
+      "loss": 0.4329,
+      "step": 350
+    },
+    {
+      "epoch": 0.48573163327261687,
+      "grad_norm": 2.854060411453247,
+      "learning_rate": 4.954937826446812e-05,
+      "loss": 0.4026,
+      "step": 400
+    },
+    {
+      "epoch": 0.546448087431694,
+      "grad_norm": 6.558586120605469,
+      "learning_rate": 4.942982225374503e-05,
+      "loss": 0.3964,
+      "step": 450
+    },
+    {
+      "epoch": 0.607164541590771,
+      "grad_norm": 2.528074264526367,
+      "learning_rate": 4.9296395327910704e-05,
+      "loss": 0.4012,
+      "step": 500
+    },
+    {
+      "epoch": 0.6678809957498482,
+      "grad_norm": 4.349924087524414,
+      "learning_rate": 4.914917324492781e-05,
+      "loss": 0.4066,
+      "step": 550
+    },
+    {
+      "epoch": 0.7285974499089253,
+      "grad_norm": 3.6735544204711914,
+      "learning_rate": 4.8988239595458375e-05,
+      "loss": 0.3935,
+      "step": 600
+    },
+    {
+      "epoch": 0.7893139040680024,
+      "grad_norm": 6.960324287414551,
+      "learning_rate": 4.881368575540219e-05,
+      "loss": 0.3985,
+      "step": 650
+    },
+    {
+      "epoch": 0.8500303582270795,
+      "grad_norm": 3.3093438148498535,
+      "learning_rate": 4.8625610834014855e-05,
+      "loss": 0.3989,
+      "step": 700
+    },
+    {
+      "epoch": 0.9107468123861566,
+      "grad_norm": 5.57237434387207,
+      "learning_rate": 4.8424121617634884e-05,
+      "loss": 0.3891,
+      "step": 750
+    },
+    {
+      "epoch": 0.9714632665452337,
+      "grad_norm": 3.110380172729492,
+      "learning_rate": 4.820933250905191e-05,
+      "loss": 0.395,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.840531561461794,
+      "eval_loss": 0.3875822424888611,
+      "eval_runtime": 20.914,
+      "eval_samples_per_second": 279.861,
+      "eval_steps_per_second": 8.75,
+      "step": 824
+    },
+    {
+      "epoch": 1.03157255616272,
+      "grad_norm": 2.6884355545043945,
+      "learning_rate": 4.798136546255038e-05,
+      "loss": 0.3457,
+      "step": 850
+    },
+    {
+      "epoch": 1.0922890103217973,
+      "grad_norm": 2.6975221633911133,
+      "learning_rate": 4.774034991466558e-05,
+      "loss": 0.3023,
+      "step": 900
+    },
+    {
+      "epoch": 1.1530054644808743,
+      "grad_norm": 5.767589092254639,
+      "learning_rate": 4.7486422710691366e-05,
+      "loss": 0.3078,
+      "step": 950
+    },
+    {
+      "epoch": 1.2137219186399515,
+      "grad_norm": 2.4795429706573486,
+      "learning_rate": 4.7219728026981314e-05,
+      "loss": 0.3182,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2744383727990285,
+      "grad_norm": 5.684678077697754,
+      "learning_rate": 4.694041728908733e-05,
+      "loss": 0.334,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3351548269581057,
+      "grad_norm": 3.5333316326141357,
+      "learning_rate": 4.66486490857824e-05,
+      "loss": 0.3219,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3958712811171827,
+      "grad_norm": 3.1211774349212646,
+      "learning_rate": 4.6344589079016e-05,
+      "loss": 0.3128,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4565877352762597,
+      "grad_norm": 1.7684446573257446,
+      "learning_rate": 4.6028409909853585e-05,
+      "loss": 0.3164,
+      "step": 1200
+    },
+    {
+      "epoch": 1.517304189435337,
+      "grad_norm": 3.983856201171875,
+      "learning_rate": 4.570029110045335e-05,
+      "loss": 0.3258,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5780206435944142,
+      "grad_norm": 3.0387632846832275,
+      "learning_rate": 4.536041895213605e-05,
+      "loss": 0.3313,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6387370977534912,
+      "grad_norm": 2.6425206661224365,
+      "learning_rate": 4.500898643960567e-05,
+      "loss": 0.3277,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6994535519125682,
+      "grad_norm": 2.7575416564941406,
+      "learning_rate": 4.4646193101381076e-05,
+      "loss": 0.3403,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7601700060716454,
+      "grad_norm": 3.061953544616699,
+      "learning_rate": 4.427224492650079e-05,
+      "loss": 0.3224,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8208864602307226,
+      "grad_norm": 249.0540008544922,
+      "learning_rate": 4.3887354237565295e-05,
+      "loss": 0.3342,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8816029143897997,
+      "grad_norm": 2.6976475715637207,
+      "learning_rate": 4.349173957018313e-05,
+      "loss": 0.3271,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9423193685488767,
+      "grad_norm": 2.1902174949645996,
+      "learning_rate": 4.308562554888948e-05,
+      "loss": 0.3496,
+      "step": 1600
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8505448040331761,
+      "eval_loss": 0.3897036612033844,
+      "eval_runtime": 20.8762,
+      "eval_samples_per_second": 280.367,
+      "eval_steps_per_second": 8.766,
+      "step": 1648
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6592,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.817524140115149e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1648/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8851cb20b4fa7ffbf0eda9b4b9f2d0d41ebc4663b6c7192a0d599abd412b594
+size 5841

config.json

@@ -33,7 +33,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.55.4",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 29794

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185859979e0d2444b781032685e0dcf0e756e9b4799ab6032797d5c224d2b7bc
+oid sha256:03fe504166f73f588da43eea04bea82e5f447b1cb80503821123b452634d6917
 size 1337640872

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8bde0abbbb8127a4f6bce9b18228d6edbcc8c6b17f39a78f21ceabe9ffcf8f
-size 5368
+oid sha256:d8851cb20b4fa7ffbf0eda9b4b9f2d0d41ebc4663b6c7192a0d599abd412b594
+size 5841