Upload folder using huggingface_hub

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "dccuchile/distilbert-base-spanish-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "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,
+  "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
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "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
+0.597362118441995,False,3.271499237806267e-05,4,16,1000,0.2565075619288112,144.12740564346313
+0.5198963371642762,False,1.0741466184541341e-05,5,16,0,0.07599321456170617,144.151517868042
+0.5946714730314795,False,3.37620447413037e-05,3,8,500,0.18998600872372765,155.90862655639648
+0.4574393106598997,False,1.4671776366845966e-05,1,16,500,0.21137985700516712,145.89185881614685
+0.4709334976994894,False,1.046796947096866e-05,2,16,0,0.026531140748479454,145.94519090652466
+0.47061894490157463,False,4.9540747889715425e-05,1,16,1000,0.06647603436044074,145.85856461524963
+0.4375637251729597,False,2.580653331424728e-05,1,16,1000,0.07837433494112092,145.91601490974426
+0.46680378064714356,False,4.168611764617624e-05,1,16,1000,0.2422358346736178,145.84486627578735
+0.5901139866275458,False,2.7145037133288976e-05,3,8,1000,0.17082315068595946,155.86436223983765
+0.6201819619499414,True,4.985384913085322e-05,3,8,500,0.20061124234729208,155.91449403762817

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8a6c2ddf65034f3989bda9b15c32daa8aa2071501d20802433fd66d47b8b70
+size 535566213

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117117900b2bb5f28c4fc851057856cdaa1cb842e1e0da8648c99381fad01238
+size 269348525

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b318a21d72fee272d9435783a30338821657728fd9fe2d7bee71bf08b42c3a6
+size 627

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.8988341093063354,
+  "best_model_checkpoint": "./results/run-d045ac8a/checkpoint-1764",
+  "epoch": 3.0,
+  "global_step": 2646,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.970769826170644e-08,
+      "loss": 2.104,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5132287012657224,
+      "eval_loss": 0.9356955289840698,
+      "eval_runtime": 3.9376,
+      "eval_samples_per_second": 597.314,
+      "eval_steps_per_second": 74.664,
+      "step": 882
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.823832044239721e-05,
+      "loss": 1.1539,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6100360403521365,
+      "eval_loss": 0.8988341093063354,
+      "eval_runtime": 3.9403,
+      "eval_samples_per_second": 596.902,
+      "eval_steps_per_second": 74.613,
+      "step": 1764
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.5007263065485174e-05,
+      "loss": 0.6207,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6201819619499414,
+      "eval_loss": 1.0120480060577393,
+      "eval_runtime": 3.9533,
+      "eval_samples_per_second": 594.945,
+      "eval_steps_per_second": 74.368,
+      "step": 2646
+    }
+  ],
+  "max_steps": 2646,
+  "num_train_epochs": 3,
+  "total_flos": 1840940131235520.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.985384913085322e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "warmup_steps": 500,
+    "weight_decay": 0.20061124234729208
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8e42a83d520066827abee6a387e6325c3b69fb81ae5e2db9f9fdb4257dcb74
+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": "distilbeto-base",
+    "iterations": 10,
+    "labels": 8,
+    "model": "transformers",
+    "original_pretrained_model": "dccuchile/distilbert-base-spanish-uncased",
+    "pretrained_model": "../assets/safercity/text/models/distilbeto-base",
+    "resources_per_trial": {
+        "gpu": 1
+    },
+    "run_id": "d045ac8a",
+    "task": "",
+    "task_type": "classification",
+    "tokenizer_field": "tweet",
+    "tokenizer_model": "dccuchile/distilbert-base-spanish-uncased",
+    "warmup_steps": 500,
+    "weight_decay": 0.01
+}