End of training

last-checkpoint/config.json

@@ -1,36 +0,0 @@
-{
-  "_name_or_path": "distilbert-base-multilingual-cased",
-  "activation": "gelu",
-  "architectures": [
-    "DistilBertForSequenceClassification"
-  ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
-  "id2label": {
-    "0": "P",
-    "1": "NEU",
-    "2": "N"
-  },
-  "initializer_range": 0.02,
-  "label2id": {
-    "N": 2,
-    "NEU": 1,
-    "P": 0
-  },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
-  "pad_token_id": 0,
-  "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.0",
-  "vocab_size": 119547
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c9b08eb3bd43ed93dbcb8c2596efae585382d0ffa0bc801326206dea663cef0
-size 1082673861

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4f0a615ffdab692a6b7cdb171da5d1e966e393872aa466fa1892e126d11858ee
-size 541341997

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fa76fe52fd649c3885f94de74fa828974782e09ea5a116494bafe08931499b21
-size 13553

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aa65b58ab89e6113985723068f5721b82cd7855ba30b3811b50b5d914c50e528
-size 627

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer_config.json

@@ -1,17 +0,0 @@
-{
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "max_length": 72,
-  "model_max_length": 512,
-  "name_or_path": "distilbert-base-multilingual-cased",
-  "pad_token": "[PAD]",
-  "padding": "max_length",
-  "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "truncation": true,
-  "unk_token": "[UNK]"
-}

last-checkpoint/trainer_state.json

@@ -1,70 +0,0 @@
-{
-  "best_metric": 0.6050104105453544,
-  "best_model_checkpoint": "/Users/fperez/dev/data/spanishclassfier_exp/distilbert-base-multilingual-cased-finetuned-with-spanish-tweets-clf-cleaned-ds/ep_4-lr_5e-5-msl_72-bs_8/checkpoint-1629",
-  "epoch": 3.0,
-  "global_step": 1629,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "learning_rate": 3.7500000000000003e-05,
-      "loss": 1.018,
-      "step": 543
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.5535590877677954,
-      "eval_f1": 0.4949397774870696,
-      "eval_loss": 0.942139744758606,
-      "eval_precision": 0.5346677326820676,
-      "eval_recall": 0.5146316846159721,
-      "eval_runtime": 80.7708,
-      "eval_samples_per_second": 17.915,
-      "eval_steps_per_second": 0.57,
-      "step": 543
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 2.5e-05,
-      "loss": 0.8079,
-      "step": 1086
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5957152729785764,
-      "eval_f1": 0.575132441321117,
-      "eval_loss": 0.9275487661361694,
-      "eval_precision": 0.5920976186364554,
-      "eval_recall": 0.5724889819336446,
-      "eval_runtime": 41.3201,
-      "eval_samples_per_second": 35.019,
-      "eval_steps_per_second": 1.113,
-      "step": 1086
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 1.25e-05,
-      "loss": 0.521,
-      "step": 1629
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.6033172080165861,
-      "eval_f1": 0.6050104105453544,
-      "eval_loss": 1.1208082437515259,
-      "eval_precision": 0.6145903381180479,
-      "eval_recall": 0.602289094420588,
-      "eval_runtime": 46.7494,
-      "eval_samples_per_second": 30.952,
-      "eval_steps_per_second": 0.984,
-      "step": 1629
-    }
-  ],
-  "max_steps": 2172,
-  "num_train_epochs": 4,
-  "total_flos": 242543853074880.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:547db2c34b063e23ee11f17e4bff5def40cf9fa9cf46e3e436df969a7238cc1c
-size 3835