Loading the model via web interface

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "allegro/herbert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NOT_IPHONE",
+    "1": "IS_IPHONE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "IS_IPHONE": 1,
+    "NOT_IPHONE": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "HerbertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b2a8b4a25100df420b78d18aab4cb5c05abd26dccbcfc9eb7c83ddece5a1db
+size 995671645

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36720498cfaecbf76c3e9f9b5bf4ff983a567be077dc9d10a74b2dcc9cc2e4d6
+size 497848749

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a77f2cb26a9d23ca033a0949d6e05bb8e721fda1c985eff95c53186ff0786b38
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f2980e83c6203ef9d1ca1d253755359d63e8f8c8c968d4ef244c4b9df61a7d
+size 623

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lowercase_and_remove_accent": false,
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "allegro/herbert-base-cased",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": "/home/konrad/.cache/huggingface/transformers/a77c29d6c21e653166565b0d51ea0a46b918191512e0ae894422060267a0f436.b8e113717eb1828d09e47de853cf49c8fad05ebdce24df2614cd942dc23e2a77",
+  "tokenizer_class": "HerbertTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": 0.00993927288800478,
+  "best_model_checkpoint": "/home/konrad/Data/iphone_model/checkpoint-54",
+  "epoch": 2.0,
+  "global_step": 54,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.03437919169664383,
+      "eval_runtime": 0.9326,
+      "eval_samples_per_second": 193.004,
+      "eval_steps_per_second": 12.867,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.00993927288800478,
+      "eval_runtime": 0.928,
+      "eval_samples_per_second": 193.966,
+      "eval_steps_per_second": 12.931,
+      "step": 54
+    }
+  ],
+  "max_steps": 54,
+  "num_train_epochs": 2,
+  "total_flos": 14830830190800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:115327cc5a928c3b2470afc6e9eb23636cfa0609eb102a2964d3f819a1395ebd
+size 3311