Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,36 @@
+{
+  "_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/config.json

@@ -0,0 +1,36 @@
+{
+  "_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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a536271a342d83b3fe04b6bfb64ec8998125b928002ff95e23d6432c6b02cc
+size 1082673861

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3a1af6352981a268c945726e9c930179f686743d5694717f40715ede7ffda1
+size 541341997

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c217c8da9b1f3f90a790bb2b05f111d916ff143daa3cf19ad27dd02007dcd0c
+size 13553

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2c4f9cae00d2f2dce1381a30f6b5f4854a75960078ce7c852274fe3c646a95
+size 627

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "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

@@ -0,0 +1,34 @@
+{
+  "best_metric": 0.501215296189785,
+  "best_model_checkpoint": "/Users/fperez/dev/data/spanishclassfier_exp/distilbert-base-multilingual-cased-finetuned-with-spanish-tweets-clf/ep_4-lr_5e-5-msl_72-bs_8/checkpoint-543",
+  "epoch": 1.0,
+  "global_step": 543,
+  "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": 1.0168,
+      "step": 543
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5563234277816171,
+      "eval_f1": 0.501215296189785,
+      "eval_loss": 0.9144431948661804,
+      "eval_precision": 0.5239741651933573,
+      "eval_recall": 0.5251116933847957,
+      "eval_runtime": 45.1011,
+      "eval_samples_per_second": 32.083,
+      "eval_steps_per_second": 1.02,
+      "step": 543
+    }
+  ],
+  "max_steps": 2172,
+  "num_train_epochs": 4,
+  "total_flos": 80847951024960.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01afbf37abe3c2d7822792a145a2b3731dedacdc0796249d6a564f36c186545d
+size 3835

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3a1af6352981a268c945726e9c930179f686743d5694717f40715ede7ffda1
+size 541341997

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01afbf37abe3c2d7822792a145a2b3731dedacdc0796249d6a564f36c186545d
+size 3835