Upload folder using huggingface_hub

README.md

@@ -0,0 +1,83 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta-base-cpp
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# roberta-base-cpp
+
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0844
+- Accuracy: 0.9550
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.1085        | 0.05  | 1000  | 0.1080          | 0.9183   |
+| 0.0716        | 0.1   | 2000  | 0.2524          | 0.8473   |
+| 0.0615        | 0.15  | 3000  | 0.1182          | 0.9299   |
+| 0.0648        | 0.2   | 4000  | 0.0757          | 0.9498   |
+| 0.0522        | 0.25  | 5000  | 0.1201          | 0.9273   |
+| 0.0377        | 0.3   | 6000  | 0.0846          | 0.9555   |
+| 0.0447        | 0.35  | 7000  | 0.1036          | 0.9323   |
+| 0.0421        | 0.4   | 8000  | 0.1804          | 0.8914   |
+| 0.0364        | 0.45  | 9000  | 0.0494          | 0.9628   |
+| 0.0301        | 0.5   | 10000 | 0.0583          | 0.9689   |
+| 0.0281        | 0.55  | 11000 | 0.0554          | 0.9689   |
+| 0.0362        | 0.6   | 12000 | 0.0898          | 0.9428   |
+| 0.022         | 0.65  | 13000 | 0.0772          | 0.9687   |
+| 0.0221        | 0.7   | 14000 | 0.0706          | 0.9613   |
+| 0.0256        | 0.75  | 15000 | 0.0487          | 0.9719   |
+| 0.0215        | 0.8   | 16000 | 0.0427          | 0.9765   |
+| 0.0162        | 0.85  | 17000 | 0.0437          | 0.9742   |
+| 0.0186        | 0.9   | 18000 | 0.0613          | 0.9680   |
+| 0.0211        | 0.95  | 19000 | 0.0950          | 0.9514   |
+| 0.0136        | 1.0   | 20000 | 0.0844          | 0.9550   |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.8.0+cu126
+- Datasets 4.4.2
+- Tokenizers 0.22.1

checkpoint-16000/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-16000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d5cc0f066a9ff7f9709202c6b1ea302b25d4fc82b916383dba6b74bf14639e
+size 498612824

checkpoint-16000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529961f9c3d396e3bfd95d8632f4c919c1c8d7d7aebb25605e81bf65fca66018
+size 997345931

checkpoint-16000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29be2623b9f70496e9bea6cd43302d895456299b445e94e0c3906aa73899453
+size 14645

checkpoint-16000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e8f14715c120c1b82640d08ff4b50ac8ef3a482a39de36f9dee0ad364309a0
+size 1383

checkpoint-16000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdd55dc4830a374b47a354ba8f1d6b80b053f25bf45716e5f0fe65d5ff8db6b
+size 1465

checkpoint-16000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-16000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-16000/trainer_state.json

@@ -0,0 +1,402 @@
+{
+  "best_global_step": 16000,
+  "best_metric": 0.042671315371990204,
+  "best_model_checkpoint": "./training_output/checkpoint-16000",
+  "epoch": 0.8,
+  "eval_steps": 1000,
+  "global_step": 16000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.8834348917007446,
+      "learning_rate": 1.9501000000000002e-05,
+      "loss": 0.1437,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 9.513919830322266,
+      "learning_rate": 1.9001e-05,
+      "loss": 0.1085,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.91835,
+      "eval_loss": 0.10802757740020752,
+      "eval_runtime": 381.1922,
+      "eval_samples_per_second": 52.467,
+      "eval_steps_per_second": 3.279,
+      "step": 1000
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.013394818641245365,
+      "learning_rate": 1.8501e-05,
+      "loss": 0.0965,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.017180055379867554,
+      "learning_rate": 1.8001000000000003e-05,
+      "loss": 0.0716,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.8473,
+      "eval_loss": 0.25237375497817993,
+      "eval_runtime": 381.1616,
+      "eval_samples_per_second": 52.471,
+      "eval_steps_per_second": 3.279,
+      "step": 2000
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.017619747668504715,
+      "learning_rate": 1.7501e-05,
+      "loss": 0.0658,
+      "step": 2500
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.527113676071167,
+      "learning_rate": 1.7001000000000002e-05,
+      "loss": 0.0615,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15,
+      "eval_accuracy": 0.9299,
+      "eval_loss": 0.11818733811378479,
+      "eval_runtime": 381.4889,
+      "eval_samples_per_second": 52.426,
+      "eval_steps_per_second": 3.277,
+      "step": 3000
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 140.78282165527344,
+      "learning_rate": 1.6501e-05,
+      "loss": 0.056,
+      "step": 3500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9989501237869263,
+      "learning_rate": 1.6001e-05,
+      "loss": 0.0648,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.9498,
+      "eval_loss": 0.07567641884088516,
+      "eval_runtime": 380.8034,
+      "eval_samples_per_second": 52.521,
+      "eval_steps_per_second": 3.283,
+      "step": 4000
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.01812303625047207,
+      "learning_rate": 1.5501000000000003e-05,
+      "loss": 0.0487,
+      "step": 4500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.05552659556269646,
+      "learning_rate": 1.5001000000000001e-05,
+      "loss": 0.0522,
+      "step": 5000
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.92725,
+      "eval_loss": 0.12006673216819763,
+      "eval_runtime": 380.6188,
+      "eval_samples_per_second": 52.546,
+      "eval_steps_per_second": 3.284,
+      "step": 5000
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.14319103956222534,
+      "learning_rate": 1.4501e-05,
+      "loss": 0.0554,
+      "step": 5500
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.012562028132379055,
+      "learning_rate": 1.4001e-05,
+      "loss": 0.0377,
+      "step": 6000
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.95545,
+      "eval_loss": 0.08464282751083374,
+      "eval_runtime": 380.6212,
+      "eval_samples_per_second": 52.546,
+      "eval_steps_per_second": 3.284,
+      "step": 6000
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.0012805273290723562,
+      "learning_rate": 1.3501000000000002e-05,
+      "loss": 0.0327,
+      "step": 6500
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.024555200710892677,
+      "learning_rate": 1.3001000000000001e-05,
+      "loss": 0.0447,
+      "step": 7000
+    },
+    {
+      "epoch": 0.35,
+      "eval_accuracy": 0.93225,
+      "eval_loss": 0.10355959832668304,
+      "eval_runtime": 380.8232,
+      "eval_samples_per_second": 52.518,
+      "eval_steps_per_second": 3.282,
+      "step": 7000
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.10476179420948029,
+      "learning_rate": 1.2501000000000001e-05,
+      "loss": 0.0379,
+      "step": 7500
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.16991844773292542,
+      "learning_rate": 1.2001e-05,
+      "loss": 0.0421,
+      "step": 8000
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.89145,
+      "eval_loss": 0.1804238110780716,
+      "eval_runtime": 380.9125,
+      "eval_samples_per_second": 52.505,
+      "eval_steps_per_second": 3.282,
+      "step": 8000
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.017685526981949806,
+      "learning_rate": 1.1501e-05,
+      "loss": 0.0384,
+      "step": 8500
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 16.736478805541992,
+      "learning_rate": 1.1001000000000002e-05,
+      "loss": 0.0364,
+      "step": 9000
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.96285,
+      "eval_loss": 0.04935265704989433,
+      "eval_runtime": 380.5923,
+      "eval_samples_per_second": 52.55,
+      "eval_steps_per_second": 3.284,
+      "step": 9000
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.08418703079223633,
+      "learning_rate": 1.0501000000000002e-05,
+      "loss": 0.0262,
+      "step": 9500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.19593098759651184,
+      "learning_rate": 1.0001000000000001e-05,
+      "loss": 0.0301,
+      "step": 10000
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.9689,
+      "eval_loss": 0.05831901729106903,
+      "eval_runtime": 380.4459,
+      "eval_samples_per_second": 52.57,
+      "eval_steps_per_second": 3.286,
+      "step": 10000
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.005820299498736858,
+      "learning_rate": 9.501000000000001e-06,
+      "loss": 0.0359,
+      "step": 10500
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.010061199776828289,
+      "learning_rate": 9.001e-06,
+      "loss": 0.0281,
+      "step": 11000
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.96895,
+      "eval_loss": 0.05543893575668335,
+      "eval_runtime": 380.3496,
+      "eval_samples_per_second": 52.583,
+      "eval_steps_per_second": 3.286,
+      "step": 11000
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.07327098399400711,
+      "learning_rate": 8.501e-06,
+      "loss": 0.022,
+      "step": 11500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 32.43045425415039,
+      "learning_rate": 8.001000000000002e-06,
+      "loss": 0.0362,
+      "step": 12000
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.9428,
+      "eval_loss": 0.08979687839746475,
+      "eval_runtime": 380.3892,
+      "eval_samples_per_second": 52.578,
+      "eval_steps_per_second": 3.286,
+      "step": 12000
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.02456793375313282,
+      "learning_rate": 7.501000000000001e-06,
+      "loss": 0.0246,
+      "step": 12500
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.001343235606327653,
+      "learning_rate": 7.001e-06,
+      "loss": 0.022,
+      "step": 13000
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.9687,
+      "eval_loss": 0.0772382989525795,
+      "eval_runtime": 380.3973,
+      "eval_samples_per_second": 52.577,
+      "eval_steps_per_second": 3.286,
+      "step": 13000
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 38.745670318603516,
+      "learning_rate": 6.501000000000001e-06,
+      "loss": 0.0232,
+      "step": 13500
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0009748099255375564,
+      "learning_rate": 6.001e-06,
+      "loss": 0.0221,
+      "step": 14000
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.96125,
+      "eval_loss": 0.07062023133039474,
+      "eval_runtime": 380.5787,
+      "eval_samples_per_second": 52.552,
+      "eval_steps_per_second": 3.284,
+      "step": 14000
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.1631036400794983,
+      "learning_rate": 5.501000000000001e-06,
+      "loss": 0.0197,
+      "step": 14500
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.4217091202735901,
+      "learning_rate": 5.001e-06,
+      "loss": 0.0256,
+      "step": 15000
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.97195,
+      "eval_loss": 0.048726025968790054,
+      "eval_runtime": 380.4177,
+      "eval_samples_per_second": 52.574,
+      "eval_steps_per_second": 3.286,
+      "step": 15000
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.054990075528621674,
+      "learning_rate": 4.501000000000001e-06,
+      "loss": 0.0176,
+      "step": 15500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.00047703919699415565,
+      "learning_rate": 4.001e-06,
+      "loss": 0.0215,
+      "step": 16000
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.97645,
+      "eval_loss": 0.042671315371990204,
+      "eval_runtime": 380.4653,
+      "eval_samples_per_second": 52.567,
+      "eval_steps_per_second": 3.285,
+      "step": 16000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.683910754304e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-16000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4672bef08597eaac4166af409003080f023f24990f8f58c185b2b990119dc93e
+size 5841

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d5cc0f066a9ff7f9709202c6b1ea302b25d4fc82b916383dba6b74bf14639e
+size 498612824

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4672bef08597eaac4166af409003080f023f24990f8f58c185b2b990119dc93e
+size 5841