upload model

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
+  "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",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "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": "4.23.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
+}

hyperparameters.csv

@@ -0,0 +1,11 @@
+objective,best,learning_rate,num_train_epochs,per_device_train_batch_size,warmup_steps,weight_decay,time_this_iter_s
+0.6331198486192046,False,4.852135288839538e-05,5,8,1000,0.1759370237120074,300.3797607421875
+0.5332256888334244,False,2.8545916286088344e-05,4,16,250,0.04553082334923364,282.6073889732361
+0.5252117727656963,False,3.20388365693834e-05,5,8,1000,0.07432435161831266,302.52899074554443
+0.6374082978762154,True,2.796445810732742e-05,4,8,500,0.21340361893154028,300.44139099121094
+0.5407608100998937,False,3.208423458510781e-05,3,16,250,0.16242308751065626,282.61042952537537
+0.5380564263224751,False,1.792675165496557e-05,2,8,500,0.1599939313426146,302.53033447265625
+0.5375266107138353,False,3.8001358870056086e-05,4,8,1000,0.16967901879559275,302.5936050415039
+0.6229397036524638,False,4.0623219812735634e-05,3,16,0,0.08733698076322681,280.6228218078613
+0.5931718087375519,False,2.8861899351678586e-05,2,16,0,0.22607052443337083,281.02607893943787
+0.5105321046880006,False,2.821667441825732e-05,5,16,1000,0.11698700097614871,282.89386224746704

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b81de35c86462c75d8c3ecbf3389c840e4751246d28b596778b7ee1c4fcd74
+size 879023813

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b35323663ff487c26041b3b83df0e8f78b6100714e3ba00455c582e70127c6
+size 439500917

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b5743511062cb47358a6dfb856b1cb5d3af7d4323822c50e79922af37203b8
+size 627

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": 0.8237528800964355,
+  "best_model_checkpoint": "./results/run-14f8e466/checkpoint-882",
+  "epoch": 4.0,
+  "global_step": 3528,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.592891621465484e-08,
+      "loss": 2.1634,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5537101472531625,
+      "eval_loss": 0.8237528800964355,
+      "eval_runtime": 9.1428,
+      "eval_samples_per_second": 257.253,
+      "eval_steps_per_second": 32.157,
+      "step": 882
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.3346813109419988e-05,
+      "loss": 1.1017,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6235863967477107,
+      "eval_loss": 0.8632814288139343,
+      "eval_runtime": 9.1334,
+      "eval_samples_per_second": 257.516,
+      "eval_steps_per_second": 32.19,
+      "step": 1764
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.411152311360512e-05,
+      "loss": 0.5733,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6471466926746001,
+      "eval_loss": 1.2097604274749756,
+      "eval_runtime": 9.1352,
+      "eval_samples_per_second": 257.466,
+      "eval_steps_per_second": 32.183,
+      "step": 2646
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 4.87623311779025e-06,
+      "loss": 0.2885,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.6374082978762154,
+      "eval_loss": 1.457223653793335,
+      "eval_runtime": 9.1351,
+      "eval_samples_per_second": 257.47,
+      "eval_steps_per_second": 32.184,
+      "step": 3528
+    }
+  ],
+  "max_steps": 3528,
+  "num_train_epochs": 4,
+  "total_flos": 5484511364643360.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.796445810732742e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "warmup_steps": 500,
+    "weight_decay": 0.21340361893154028
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154040c2f69e216fb0cf9f5316b1a42ad0b75fcd3974504bddf0f571135699fd
+size 3387

training_resume.json

@@ -0,0 +1,29 @@
+{
+    "batch_train_size": 16,
+    "batch_val_size": 32,
+    "corpus": "text",
+    "dataset": "safercity",
+    "epochs": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "folder": "beto",
+    "iterations": 10,
+    "labels": 8,
+    "model": "transformers",
+    "original_pretrained_model": "dccuchile/bert-base-spanish-wwm-cased",
+    "pretrained_model": "../assets/safercity/text/models/beto",
+    "resources_per_trial": {
+        "gpu": 1
+    },
+    "run_id": "14f8e466",
+    "task": "",
+    "task_type": "classification",
+    "tokenizer_field": "tweet",
+    "tokenizer_model": "dccuchile/bert-base-spanish-wwm-cased",
+    "warmup_steps": 500,
+    "weight_decay": 0.01
+}