Upload model

config.json

@@ -0,0 +1,120 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Cry babies magic tears",
+    "1": "Enchantimals (\u042d\u043d\u0448\u0430\u043d\u0442\u0438\u043c\u0430\u043b\u0441)",
+    "2": "My little pony",
+    "3": "none",
+    "4": "\u0410\u043a\u0443\u043b\u0435\u043d\u043e\u043a",
+    "5": "\u0411\u0430\u0440\u0431\u043e\u0441\u043a\u0438\u043d\u044b",
+    "6": "\u0411\u0440\u0435\u043c\u0435\u043d\u0441\u043a\u0438\u0435 \u043c\u0443\u0437\u044b\u043a\u0430\u043d\u0442\u044b",
+    "7": "\u0411\u0443\u0431\u0430",
+    "8": "\u0411\u044d\u0442\u043c\u0435\u043d",
+    "9": "\u0412\u0441\u043f\u044b\u0448",
+    "10": "\u0413\u043e\u0432\u043e\u0440\u044f\u0449\u0438\u0439 \u0422\u043e\u043c",
+    "11": "\u0413\u0443\u0431\u043a\u0430 \u0411\u043e\u0431",
+    "12": "\u0415\u043d\u043e\u0442\u043a\u0438",
+    "13": "\u0416\u0438\u043b\u0430\u0411\u044b\u043b\u0430 \u0426\u0430\u0440\u0435\u0432\u043d\u0430",
+    "14": "\u0417\u0435\u0431\u0440\u0430 \u0432 \u043a\u043b\u0435\u0442\u043e\u0447\u043a\u0443",
+    "15": "\u041a\u043e\u0442\u0438\u043a \u041c\u043e\u0440\u043c\u043e\u0442\u0438\u043a",
+    "16": "\u041a\u043e\u0448\u0435\u0447\u043a\u0438 \u0441\u043e\u0431\u0430\u0447\u043a\u0438",
+    "17": "\u041a\u0440\u0443\u0442\u0438\u043a\u0441\u044b",
+    "18": "\u041a\u0443\u043a\u0443\u0442\u0438\u043a\u0438",
+    "19": "\u041b\u0443\u043d\u0442\u0438\u043a",
+    "20": "\u041c\u0430\u043b\u044b\u0448\u0430\u0440\u0438\u043a\u0438",
+    "21": "\u041c\u0430\u0448\u0430 \u0438 \u043c\u0435\u0434\u0432\u0435\u0434\u044c",
+    "22": "\u041c\u0438\u043d\u0438-\u043c\u0438\u0448\u043a\u0438",
+    "23": "\u041d\u0443_\u043f\u043e\u0433\u043e\u0434\u0438 \u043a\u0430\u043d\u0438\u043a\u0443\u043b\u044b",
+    "24": "\u041e\u0440\u0430\u043d\u0436\u0435\u0432\u0430\u044f \u043a\u043e\u0440\u043e\u0432\u0430",
+    "25": "\u041f\u0430\u0440\u043e\u0432\u043e\u0437\u0438\u043a\u0438 \u0427\u0430\u0442\u0442\u0438\u043d\u0433\u0442\u043e\u043d",
+    "26": "\u041f\u043e\u0440\u043e\u0440\u043e",
+    "27": "\u041f\u0440\u0438\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f \u041f\u0435\u0442\u0438 \u0438 \u0412\u043e\u043b\u043a\u0430",
+    "28": "\u041f\u0440\u043e\u0441\u0442\u043e\u043a\u0432\u0430\u0448\u0438\u043d\u043e",
+    "29": "\u0421\u0432\u0438\u043d\u043a\u0430 \u041f\u0435\u043f\u043f\u0430",
+    "30": "\u0421\u0438\u043c\u043f\u0441\u043e\u043d\u044b",
+    "31": "\u0421\u0438\u043d\u0438\u0439 \u0442\u0440\u0430\u043a\u0442\u043e\u0440",
+    "32": "\u0421\u043c\u0435\u0448\u0430\u0440\u0438\u043a\u0438",
+    "33": "\u0421\u0443\u043c\u043a\u0430",
+    "34": "\u0422\u0440\u0430\u043d\u0441\u0444\u043e\u0440\u043c\u0435\u0440\u044b",
+    "35": "\u0424\u0438\u043a\u0441\u0438\u043a\u0438",
+    "36": "\u0424\u0438\u043d\u043d\u0438\u043a",
+    "37": "\u0426\u0430\u0440\u0435\u0432\u043d\u044b",
+    "38": "\u0426\u0432\u0435\u0442\u043d\u044f\u0448\u043a\u0438",
+    "39": "\u0427\u0435\u0431\u0443\u0440\u0430\u0448\u043a\u0430",
+    "40": "\u0427\u0435\u0440\u0435\u043f\u0430\u0448\u043a\u0438 \u041d\u0438\u043d\u0434\u0437\u044f",
+    "41": "\u0427\u0438\u043a-\u0427\u0438\u0440\u0438\u043a\u0438\u043d\u043e",
+    "42": "\u0427\u0443\u0434\u0434\u0438\u043a\u0438",
+    "43": "\u0427\u0443\u0447\u0435\u043b\u043e-\u041c\u044f\u0443\u0447\u0435\u043b\u043e",
+    "44": "\u0429\u0435\u043d\u044f\u0447\u0438\u0439 \u043f\u0430\u0442\u0440\u0443\u043b\u044c"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Cry babies magic tears": 0,
+    "Enchantimals (\u042d\u043d\u0448\u0430\u043d\u0442\u0438\u043c\u0430\u043b\u0441)": 1,
+    "My little pony": 2,
+    "none": 3,
+    "\u0410\u043a\u0443\u043b\u0435\u043d\u043e\u043a": 4,
+    "\u0411\u0430\u0440\u0431\u043e\u0441\u043a\u0438\u043d\u044b": 5,
+    "\u0411\u0440\u0435\u043c\u0435\u043d\u0441\u043a\u0438\u0435 \u043c\u0443\u0437\u044b\u043a\u0430\u043d\u0442\u044b": 6,
+    "\u0411\u0443\u0431\u0430": 7,
+    "\u0411\u044d\u0442\u043c\u0435\u043d": 8,
+    "\u0412\u0441\u043f\u044b\u0448": 9,
+    "\u0413\u043e\u0432\u043e\u0440\u044f\u0449\u0438\u0439 \u0422\u043e\u043c": 10,
+    "\u0413\u0443\u0431\u043a\u0430 \u0411\u043e\u0431": 11,
+    "\u0415\u043d\u043e\u0442\u043a\u0438": 12,
+    "\u0416\u0438\u043b\u0430\u0411\u044b\u043b\u0430 \u0426\u0430\u0440\u0435\u0432\u043d\u0430": 13,
+    "\u0417\u0435\u0431\u0440\u0430 \u0432 \u043a\u043b\u0435\u0442\u043e\u0447\u043a\u0443": 14,
+    "\u041a\u043e\u0442\u0438\u043a \u041c\u043e\u0440\u043c\u043e\u0442\u0438\u043a": 15,
+    "\u041a\u043e\u0448\u0435\u0447\u043a\u0438 \u0441\u043e\u0431\u0430\u0447\u043a\u0438": 16,
+    "\u041a\u0440\u0443\u0442\u0438\u043a\u0441\u044b": 17,
+    "\u041a\u0443\u043a\u0443\u0442\u0438\u043a\u0438": 18,
+    "\u041b\u0443\u043d\u0442\u0438\u043a": 19,
+    "\u041c\u0430\u043b\u044b\u0448\u0430\u0440\u0438\u043a\u0438": 20,
+    "\u041c\u0430\u0448\u0430 \u0438 \u043c\u0435\u0434\u0432\u0435\u0434\u044c": 21,
+    "\u041c\u0438\u043d\u0438-\u043c\u0438\u0448\u043a\u0438": 22,
+    "\u041d\u0443_\u043f\u043e\u0433\u043e\u0434\u0438 \u043a\u0430\u043d\u0438\u043a\u0443\u043b\u044b": 23,
+    "\u041e\u0440\u0430\u043d\u0436\u0435\u0432\u0430\u044f \u043a\u043e\u0440\u043e\u0432\u0430": 24,
+    "\u041f\u0430\u0440\u043e\u0432\u043e\u0437\u0438\u043a\u0438 \u0427\u0430\u0442\u0442\u0438\u043d\u0433\u0442\u043e\u043d": 25,
+    "\u041f\u043e\u0440\u043e\u0440\u043e": 26,
+    "\u041f\u0440\u0438\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f \u041f\u0435\u0442\u0438 \u0438 \u0412\u043e\u043b\u043a\u0430": 27,
+    "\u041f\u0440\u043e\u0441\u0442\u043e\u043a\u0432\u0430\u0448\u0438\u043d\u043e": 28,
+    "\u0421\u0432\u0438\u043d\u043a\u0430 \u041f\u0435\u043f\u043f\u0430": 29,
+    "\u0421\u0438\u043c\u043f\u0441\u043e\u043d\u044b": 30,
+    "\u0421\u0438\u043d\u0438\u0439 \u0442\u0440\u0430\u043a\u0442\u043e\u0440": 31,
+    "\u0421\u043c\u0435\u0448\u0430\u0440\u0438\u043a\u0438": 32,
+    "\u0421\u0443\u043c\u043a\u0430": 33,
+    "\u0422\u0440\u0430\u043d\u0441\u0444\u043e\u0440\u043c\u0435\u0440\u044b": 34,
+    "\u0424\u0438\u043a\u0441\u0438\u043a\u0438": 35,
+    "\u0424\u0438\u043d\u043d\u0438\u043a": 36,
+    "\u0426\u0430\u0440\u0435\u0432\u043d\u044b": 37,
+    "\u0426\u0432\u0435\u0442\u043d\u044f\u0448\u043a\u0438": 38,
+    "\u0427\u0435\u0431\u0443\u0440\u0430\u0448\u043a\u0430": 39,
+    "\u0427\u0435\u0440\u0435\u043f\u0430\u0448\u043a\u0438 \u041d\u0438\u043d\u0434\u0437\u044f": 40,
+    "\u0427\u0438\u043a-\u0427\u0438\u0440\u0438\u043a\u0438\u043d\u043e": 41,
+    "\u0427\u0443\u0434\u0434\u0438\u043a\u0438": 42,
+    "\u0427\u0443\u0447\u0435\u043b\u043e-\u041c\u044f\u0443\u0447\u0435\u043b\u043e": 43,
+    "\u0429\u0435\u043d\u044f\u0447\u0438\u0439 \u043f\u0430\u0442\u0440\u0443\u043b\u044c": 44
+  },
+  "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": "4.44.2",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9e8368172f12a3a37df6f7f4799372159d8ff01ad4cb4108746605c16045e3
+size 541449652

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccfefc2ed635fdcd32de11e9b611bc64274fb25f516bebb441b6bfe2f30870ef
+size 1082961338

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4011e64a258e389086014148d92832805adb6ca4a8cf75f201c44ab010de218
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626cb6202d88deec6262134a2a2ba85b839469ff74955c1c820646c5510dcd78
+size 1064

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 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_metric": 0.7899897141616012,
+  "best_model_checkpoint": "/kaggle/working/reels-clf/checkpoint-6258",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 6258,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4793863854266539,
+      "grad_norm": 43369.4140625,
+      "learning_rate": 4.6005113454777885e-05,
+      "loss": 0.2922,
+      "step": 500
+    },
+    {
+      "epoch": 0.9587727708533078,
+      "grad_norm": 16354.4609375,
+      "learning_rate": 4.2010226909555774e-05,
+      "loss": 0.0957,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9896901036983756,
+      "eval_f1": 0.3894120956863034,
+      "eval_loss": 0.0804702639579773,
+      "eval_runtime": 151.5528,
+      "eval_samples_per_second": 110.08,
+      "eval_steps_per_second": 1.722,
+      "step": 1043
+    },
+    {
+      "epoch": 1.4381591562799616,
+      "grad_norm": 592.91064453125,
+      "learning_rate": 3.8015340364333656e-05,
+      "loss": 0.0814,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9175455417066156,
+      "grad_norm": 63719.01171875,
+      "learning_rate": 3.402045381911154e-05,
+      "loss": 0.074,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9937061679554037,
+      "eval_f1": 0.5246078522111747,
+      "eval_loss": 0.06898169219493866,
+      "eval_runtime": 151.5845,
+      "eval_samples_per_second": 110.057,
+      "eval_steps_per_second": 1.722,
+      "step": 2086
+    },
+    {
+      "epoch": 2.396931927133269,
+      "grad_norm": 91346.8984375,
+      "learning_rate": 3.002556727388942e-05,
+      "loss": 0.057,
+      "step": 2500
+    },
+    {
+      "epoch": 2.876318312559923,
+      "grad_norm": 0.34639281034469604,
+      "learning_rate": 2.6030680728667306e-05,
+      "loss": 0.0565,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9947251693340526,
+      "eval_f1": 0.5763717231704362,
+      "eval_loss": 0.07740658521652222,
+      "eval_runtime": 151.2075,
+      "eval_samples_per_second": 110.332,
+      "eval_steps_per_second": 1.726,
+      "step": 3129
+    },
+    {
+      "epoch": 3.3557046979865772,
+      "grad_norm": 0.3635995090007782,
+      "learning_rate": 2.2035794183445192e-05,
+      "loss": 0.0405,
+      "step": 3500
+    },
+    {
+      "epoch": 3.8350910834132312,
+      "grad_norm": 45141.87109375,
+      "learning_rate": 1.8040907638223074e-05,
+      "loss": 0.0347,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9955044056824313,
+      "eval_f1": 0.6777953957165785,
+      "eval_loss": 0.06517060101032257,
+      "eval_runtime": 152.3821,
+      "eval_samples_per_second": 109.481,
+      "eval_steps_per_second": 1.713,
+      "step": 4172
+    },
+    {
+      "epoch": 4.314477468839885,
+      "grad_norm": 0.10806822776794434,
+      "learning_rate": 1.4046021093000961e-05,
+      "loss": 0.0214,
+      "step": 4500
+    },
+    {
+      "epoch": 4.793863854266538,
+      "grad_norm": 0.16395215690135956,
+      "learning_rate": 1.0051134547778844e-05,
+      "loss": 0.0269,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9956242881975664,
+      "eval_f1": 0.7422681606882496,
+      "eval_loss": 0.06420310586690903,
+      "eval_runtime": 151.8009,
+      "eval_samples_per_second": 109.901,
+      "eval_steps_per_second": 1.719,
+      "step": 5215
+    },
+    {
+      "epoch": 5.273250239693192,
+      "grad_norm": 90.11448669433594,
+      "learning_rate": 6.056248002556728e-06,
+      "loss": 0.0169,
+      "step": 5500
+    },
+    {
+      "epoch": 5.752636625119846,
+      "grad_norm": 0.08740052580833435,
+      "learning_rate": 2.0613614573346116e-06,
+      "loss": 0.0213,
+      "step": 6000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9957441707127016,
+      "eval_f1": 0.7899897141616012,
+      "eval_loss": 0.061532892286777496,
+      "eval_runtime": 151.598,
+      "eval_samples_per_second": 110.048,
+      "eval_steps_per_second": 1.722,
+      "step": 6258
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6258,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.307637757681664e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5a1462b574edf84825d43fea94e66e65997f2ae99eeaa883a52bc6a7cb48b3
+size 5176