Training in progress, step 5389

.gitignore

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

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "johannes-garstenauer/distilbert-heaps-masked",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_hidden_states": true,
+  "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 +1,25 @@
+{
+  "_name_or_path": "johannes-garstenauer/distilbert-heaps-masked",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_hidden_states": true,
+  "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 sha256:23719cc438192326451a903f440d053aa33f3c2e984adc816ec78be438349839
+size 133845061

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd648598bcaf3d9c14c0605e7fb9ecb4df8357dc9417bc0cd8171d36e7f5edf
+size 266267309

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f276595b716abd321d5915abef0421b68fb7820619489e46144f6687239f65
+size 14511

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa764eed4ab1462730516bcea65ff7bf789d738ccbaf54ba8bc14a9145688ba8
+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 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25,
+  "global_step": 5389,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.539006450176285e-05,
+      "loss": 0.1086,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.5271729003525703e-05,
+      "loss": 0.0983,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.5153393505288553e-05,
+      "loss": 0.0981,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.5035058007051402e-05,
+      "loss": 0.094,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.491672250881425e-05,
+      "loss": 0.0934,
+      "step": 2500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.47983870105771e-05,
+      "loss": 0.0935,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.4680051512339954e-05,
+      "loss": 0.0958,
+      "step": 3500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.4561716014102803e-05,
+      "loss": 0.0955,
+      "step": 4000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.4443380515865653e-05,
+      "loss": 0.0926,
+      "step": 4500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.4325045017628505e-05,
+      "loss": 0.0937,
+      "step": 5000
+    }
+  ],
+  "max_steps": 107780,
+  "num_train_epochs": 5,
+  "total_flos": 9.137495185371955e+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 sha256:8e388335397a1b822cc77a0c25d7835299e60b585867dd69956f0483b3ff20da
+size 4027

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd648598bcaf3d9c14c0605e7fb9ecb4df8357dc9417bc0cd8171d36e7f5edf
+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 sha256:8e388335397a1b822cc77a0c25d7835299e60b585867dd69956f0483b3ff20da
+size 4027