Training in progress, step 1424

.gitignore

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

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "johannes-garstenauer/distilbert-heaps-masked",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "IRRELEVANT",
+    "1": "RELEVANT"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "IRRELEVANT": 0,
+    "RELEVANT": 1
+  },
+  "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": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "vocab_size": 30005
+}

last-checkpoint/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "johannes-garstenauer/distilbert-heaps-masked",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "IRRELEVANT",
+    "1": "RELEVANT"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "IRRELEVANT": 0,
+    "RELEVANT": 1
+  },
+  "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": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "vocab_size": 30005
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2dfdaa2c1a053976e17aaf35eca6f339820b1f27359ecfb32e2625e731cadf7
+size 532524613

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4604f59d0dc6ea503de40a2efa4c9b72ee0798e44628bb0c9b96ba356eabb8
+size 266267309

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78785aa888b9a1572c9d0a6d1821408a078131f880100708df9fb61ef7ead699
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698b859196cca9d636d69f0d9a62efe943289b8516f412a9f4f427df325e8251
+size 627

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "cls_token": "[CLS]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,28 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.15008431703204048,
+  "global_step": 1424,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.96486790331647e-05,
+      "loss": 0.6974,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.92973580663294e-05,
+      "loss": 0.6964,
+      "step": 1000
+    }
+  ],
+  "max_steps": 28464,
+  "num_train_epochs": 3,
+  "total_flos": 2.414509768782643e+16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53366aef919ddcb83897561b0817791b625013476a9a80cc26515ea6fc8fce31
+size 4027

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4604f59d0dc6ea503de40a2efa4c9b72ee0798e44628bb0c9b96ba356eabb8
+size 266267309

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "cls_token": "[CLS]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53366aef919ddcb83897561b0817791b625013476a9a80cc26515ea6fc8fce31
+size 4027