user-flow-label-v0.4

README.md

@@ -0,0 +1,92 @@
+---
+base_model: nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: MiniLMv2-L6-H384-distilled-from-RoBERTa-Large-userflow-distil
+  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. -->
+
+# MiniLMv2-L6-H384-distilled-from-RoBERTa-Large-userflow-distil
+
+This model is a fine-tuned version of [nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6738
+- Accuracy: 0.7236
+- F1: 0.7313
+
+## 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: 7e-05
+- train_batch_size: 10
+- eval_batch_size: 10
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 0.25  | 100  | 2.3745          | 0.3923   | 0.2210 |
+| No log        | 0.51  | 200  | 2.1198          | 0.4126   | 0.2567 |
+| No log        | 0.76  | 300  | 1.8704          | 0.4756   | 0.3979 |
+| No log        | 1.01  | 400  | 1.5780          | 0.5305   | 0.4551 |
+| 2.1769        | 1.26  | 500  | 1.3717          | 0.5650   | 0.5037 |
+| 2.1769        | 1.52  | 600  | 1.2590          | 0.5935   | 0.5543 |
+| 2.1769        | 1.77  | 700  | 1.0973          | 0.6280   | 0.5804 |
+| 2.1769        | 2.02  | 800  | 0.9814          | 0.6423   | 0.5978 |
+| 2.1769        | 2.27  | 900  | 0.9589          | 0.6463   | 0.6152 |
+| 0.9806        | 2.53  | 1000 | 0.9098          | 0.6565   | 0.6483 |
+| 0.9806        | 2.78  | 1100 | 0.8747          | 0.6321   | 0.6194 |
+| 0.9806        | 3.03  | 1200 | 0.8172          | 0.6931   | 0.6902 |
+| 0.9806        | 3.28  | 1300 | 0.7862          | 0.7033   | 0.7017 |
+| 0.9806        | 3.54  | 1400 | 0.7975          | 0.6890   | 0.6952 |
+| 0.4166        | 3.79  | 1500 | 0.7674          | 0.6951   | 0.6913 |
+| 0.4166        | 4.04  | 1600 | 0.7521          | 0.6911   | 0.6997 |
+| 0.4166        | 4.29  | 1700 | 0.7944          | 0.6951   | 0.7055 |
+| 0.4166        | 4.55  | 1800 | 0.7366          | 0.7093   | 0.7127 |
+| 0.4166        | 4.8   | 1900 | 0.7412          | 0.6911   | 0.6944 |
+| 0.2158        | 5.05  | 2000 | 0.7246          | 0.7012   | 0.7083 |
+| 0.2158        | 5.3   | 2100 | 0.7097          | 0.7195   | 0.7253 |
+| 0.2158        | 5.56  | 2200 | 0.6914          | 0.7134   | 0.7197 |
+| 0.2158        | 5.81  | 2300 | 0.6875          | 0.7175   | 0.7266 |
+| 0.2158        | 6.06  | 2400 | 0.6544          | 0.7236   | 0.7296 |
+| 0.1423        | 6.31  | 2500 | 0.6738          | 0.7236   | 0.7313 |
+| 0.1423        | 6.57  | 2600 | 0.6640          | 0.7175   | 0.7253 |
+| 0.1423        | 6.82  | 2700 | 0.6617          | 0.7154   | 0.7233 |
+| 0.1423        | 7.07  | 2800 | 0.6582          | 0.7154   | 0.7205 |
+| 0.1423        | 7.32  | 2900 | 0.6678          | 0.7033   | 0.7093 |
+| 0.1204        | 7.58  | 3000 | 0.6596          | 0.7154   | 0.7197 |
+| 0.1204        | 7.83  | 3100 | 0.6598          | 0.7154   | 0.7217 |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large",
+  "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": 384,
+  "id2label": {
+    "0": "OTHER",
+    "1": "agrees_praising_thanking",
+    "2": "asks_source",
+    "3": "continue",
+    "4": "continue_or_finnish_code",
+    "5": "improve_or_modify_answer",
+    "6": "lack_of_understandment",
+    "7": "model_wrong_or_try_again",
+    "8": "more_listing_or_expand",
+    "9": "repeat_answers_or_question",
+    "10": "request_example",
+    "11": "user_complains_repetition",
+    "12": "user_doubts_answer",
+    "13": "user_goodbye",
+    "14": "user_reminds_question",
+    "15": "user_wants_agent_to_answer",
+    "16": "user_wants_explanation",
+    "17": "user_wants_more_detail",
+    "18": "user_wants_shorter_longer_answer",
+    "19": "user_wants_simplier_explanation",
+    "20": "user_wants_yes_or_no"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "OTHER": 0,
+    "agrees_praising_thanking": 1,
+    "asks_source": 2,
+    "continue": 3,
+    "continue_or_finnish_code": 4,
+    "improve_or_modify_answer": 5,
+    "lack_of_understandment": 6,
+    "model_wrong_or_try_again": 7,
+    "more_listing_or_expand": 8,
+    "repeat_answers_or_question": 9,
+    "request_example": 10,
+    "user_complains_repetition": 11,
+    "user_doubts_answer": 12,
+    "user_goodbye": 13,
+    "user_reminds_question": 14,
+    "user_wants_agent_to_answer": 15,
+    "user_wants_explanation": 16,
+    "user_wants_more_detail": 17,
+    "user_wants_shorter_longer_answer": 18,
+    "user_wants_simplier_explanation": 19,
+    "user_wants_yes_or_no": 20
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "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:d5ded45df2c6c2d48802aff4ea3d7c9492e0ffab954d61759c9615f7deeb3a07
+size 121224404

runs/Feb06_09-45-26_c7341dfc909a/events.out.tfevents.1707212746.c7341dfc909a.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68667af0a3a7928c57a015a45c343fc485bb11bb48407d9f6822edd208711ff4
+size 18775

runs/Feb06_09-45-26_c7341dfc909a/events.out.tfevents.1707213067.c7341dfc909a.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d9b84897e68cef05c043ac11c7b7a30c31f82eeaf841b280a9d78aedaf575b
+size 457

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3abd637467f57faa80b06d37db4cc170a61b093c4ac3eca3269927ee7e804dac
+size 4856