Training in progress, step 500, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,88 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "baseet complete",
+    "1": "baseet mukhala",
+    "2": "hazaj majzuu",
+    "3": "kamel ahuth",
+    "4": "kamel complete",
+    "5": "kamel majzuu",
+    "6": "khafif complete",
+    "7": "khafif majzuu",
+    "8": "madeed majzuu",
+    "9": "mudari majzuu",
+    "10": "mujtath majzuu",
+    "11": "munsarih complete",
+    "12": "muqtadab majzuu",
+    "13": "mutadarak complete",
+    "14": "mutadarak mashture",
+    "15": "mutaqarib complete",
+    "16": "rajaz complete",
+    "17": "rajaz majzuu",
+    "18": "rajaz mashture",
+    "19": "ramel complete",
+    "20": "ramel majzuu",
+    "21": "saree complete",
+    "22": "taweel complete",
+    "23": "wafer complete",
+    "24": "wafer majzuu"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "baseet complete": 0,
+    "baseet mukhala": 1,
+    "hazaj majzuu": 2,
+    "kamel ahuth": 3,
+    "kamel complete": 4,
+    "kamel majzuu": 5,
+    "khafif complete": 6,
+    "khafif majzuu": 7,
+    "madeed majzuu": 8,
+    "mudari majzuu": 9,
+    "mujtath majzuu": 10,
+    "munsarih complete": 11,
+    "muqtadab majzuu": 12,
+    "mutadarak complete": 13,
+    "mutadarak mashture": 14,
+    "mutaqarib complete": 15,
+    "rajaz complete": 16,
+    "rajaz majzuu": 17,
+    "rajaz mashture": 18,
+    "ramel complete": 19,
+    "ramel majzuu": 20,
+    "saree complete": 21,
+    "taweel complete": 22,
+    "wafer complete": 23,
+    "wafer majzuu": 24
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "submeter_input_format": "first_hemistich S second_hemistich",
+  "submeter_missing_second_marker": "E",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89dd239cb7939bd9844fcceac25e185b07aa9fed51dd7ec0057d407e6a00fe31
+size 651465828

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418f05c51bade664d3943f331ed8f561ee678e4fbf9554acd527a820b0deae4d
+size 1303053067

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef702cf5950b1f0c810bc9b544e0aaf73ce3dca2eb24db9e77e742da94cb9341
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da218e627961cb498ff5a95d62676f19d811740f288365b7675bc65108eef972
+size 1465

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_global_step": 500,
+  "best_metric": 0.765245945945946,
+  "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-500",
+  "epoch": 0.08648274669203494,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08648274669203494,
+      "grad_norm": 25.747224807739258,
+      "learning_rate": 4.856162804104693e-05,
+      "loss": 1.2986,
+      "step": 500
+    },
+    {
+      "epoch": 0.08648274669203494,
+      "eval_accuracy": 0.765245945945946,
+      "eval_loss": 0.756655216217041,
+      "eval_macro_f1": 0.2987486877044399,
+      "eval_runtime": 418.3804,
+      "eval_samples_per_second": 884.363,
+      "eval_steps_per_second": 3.456,
+      "eval_weighted_f1": 0.7565798837380349,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 17346,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2105323118592000.0,
+  "train_batch_size": 128,
+  "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:b72ba77cf4a8bdc54f108081b7aa5eea8cd135da46fb18b1892aa6c935c428c2
+size 5969