Upload folder using huggingface_hub

en/.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1767770315

en/README.md

@@ -0,0 +1,12 @@
+---
+license: apache-2.0
+library_name: transformers
+tags:
+  - intent-classification
+  - bert
+  - english
+---
+
+# SaleIntent (English)
+
+English intent classification model for sales and customer service scenarios.

en/config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A",
+    "1": "B",
+    "2": "C",
+    "3": "F",
+    "4": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A": 0,
+    "B": 1,
+    "C": 2,
+    "F": 3,
+    "X": 4
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

en/configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "other"}

en/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf6ffad1b1a1784a9b44d9ab27477eeeac2acb35cba0f992a6573e174182b32
+size 498622052

en/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c02eb93116db50ef870cc6246e5302ea525cc8db331e21f72556c595bedac6
+size 14244

en/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f086362fd598cad0852e5445dc8a59f8987edd7993f40edd6de3b6614e6c2f
+size 1064

en/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>"
+}

en/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>"
+}

en/trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 5178,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5793742757821553,
+      "grad_norm": 19.770750045776367,
+      "learning_rate": 1.8072614909231365e-05,
+      "loss": 0.4165,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9061889250814332,
+      "eval_f1": 0.6588856644028802,
+      "eval_loss": 0.2571379244327545,
+      "eval_model_preparation_time": 0.0035,
+      "eval_runtime": 7.7488,
+      "eval_samples_per_second": 198.095,
+      "eval_steps_per_second": 12.389,
+      "step": 863
+    },
+    {
+      "epoch": 1.1587485515643106,
+      "grad_norm": 12.198838233947754,
+      "learning_rate": 1.6141367323290847e-05,
+      "loss": 0.2695,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7381228273464657,
+      "grad_norm": 4.078156471252441,
+      "learning_rate": 1.4210119737350329e-05,
+      "loss": 0.2395,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9172638436482085,
+      "eval_f1": 0.7743632259583444,
+      "eval_loss": 0.27239134907722473,
+      "eval_model_preparation_time": 0.0035,
+      "eval_runtime": 7.6987,
+      "eval_samples_per_second": 199.384,
+      "eval_steps_per_second": 12.47,
+      "step": 1726
+    },
+    {
+      "epoch": 2.317497103128621,
+      "grad_norm": 14.144125938415527,
+      "learning_rate": 1.2278872151409811e-05,
+      "loss": 0.2124,
+      "step": 2000
+    },
+    {
+      "epoch": 2.8968713789107765,
+      "grad_norm": 10.107670783996582,
+      "learning_rate": 1.0347624565469293e-05,
+      "loss": 0.1963,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9081433224755701,
+      "eval_f1": 0.7319603089698221,
+      "eval_loss": 0.2672387659549713,
+      "eval_model_preparation_time": 0.0035,
+      "eval_runtime": 7.9308,
+      "eval_samples_per_second": 193.549,
+      "eval_steps_per_second": 12.105,
+      "step": 2589
+    },
+    {
+      "epoch": 3.4762456546929315,
+      "grad_norm": 7.0400590896606445,
+      "learning_rate": 8.416376979528776e-06,
+      "loss": 0.1468,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.923127035830619,
+      "eval_f1": 0.8001705663023119,
+      "eval_loss": 0.29329150915145874,
+      "eval_model_preparation_time": 0.0035,
+      "eval_runtime": 7.7266,
+      "eval_samples_per_second": 198.663,
+      "eval_steps_per_second": 12.425,
+      "step": 3452
+    },
+    {
+      "epoch": 4.055619930475087,
+      "grad_norm": 21.304224014282227,
+      "learning_rate": 6.485129393588259e-06,
+      "loss": 0.1611,
+      "step": 3500
+    },
+    {
+      "epoch": 4.634994206257242,
+      "grad_norm": 0.21730026602745056,
+      "learning_rate": 4.553881807647741e-06,
+      "loss": 0.1149,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9218241042345277,
+      "eval_f1": 0.7887765788808786,
+      "eval_loss": 0.3534080684185028,
+      "eval_model_preparation_time": 0.0035,
+      "eval_runtime": 4.1461,
+      "eval_samples_per_second": 370.225,
+      "eval_steps_per_second": 23.154,
+      "step": 4315
+    },
+    {
+      "epoch": 5.214368482039397,
+      "grad_norm": 1.3788145780563354,
+      "learning_rate": 2.622634221707223e-06,
+      "loss": 0.0984,
+      "step": 4500
+    },
+    {
+      "epoch": 5.793742757821553,
+      "grad_norm": 0.3194971978664398,
+      "learning_rate": 6.913866357667054e-07,
+      "loss": 0.0944,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9179153094462541,
+      "eval_f1": 0.7813271685158736,
+      "eval_loss": 0.39636778831481934,
+      "eval_model_preparation_time": 0.0035,
+      "eval_runtime": 4.1457,
+      "eval_samples_per_second": 370.259,
+      "eval_steps_per_second": 23.156,
+      "step": 5178
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5178,
+  "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": 1.0898616579001344e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

en/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84e3f88b99ca02168e94f3afcb84a32763725debad38771758947c2743ab233
+size 5240