agent-flow-label-v0.4

README.md

@@ -0,0 +1,110 @@
+---
+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-agentflow-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-agentflow-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: 0.1540
+- Accuracy: 0.9616
+- F1: 0.9618
+
+## 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        | 0.07  | 30   | 3.4249          | 0.1510   | 0.0404 |
+| No log        | 0.13  | 60   | 3.3994          | 0.2779   | 0.1759 |
+| No log        | 0.2   | 90   | 3.3313          | 0.3423   | 0.2154 |
+| No log        | 0.27  | 120  | 3.1475          | 0.3977   | 0.3024 |
+| No log        | 0.33  | 150  | 2.8961          | 0.3494   | 0.2370 |
+| No log        | 0.4   | 180  | 2.6867          | 0.5147   | 0.4325 |
+| No log        | 0.47  | 210  | 2.4676          | 0.5728   | 0.4955 |
+| No log        | 0.54  | 240  | 2.2129          | 0.5657   | 0.4588 |
+| No log        | 0.6   | 270  | 1.9712          | 0.6917   | 0.6331 |
+| No log        | 0.67  | 300  | 1.8016          | 0.6533   | 0.5799 |
+| No log        | 0.74  | 330  | 1.5721          | 0.7185   | 0.6524 |
+| No log        | 0.8   | 360  | 1.3381          | 0.8061   | 0.7760 |
+| No log        | 0.87  | 390  | 1.1876          | 0.8543   | 0.8319 |
+| No log        | 0.94  | 420  | 0.9877          | 0.8722   | 0.8577 |
+| No log        | 1.0   | 450  | 0.8819          | 0.8892   | 0.8850 |
+| No log        | 1.07  | 480  | 0.7511          | 0.8972   | 0.8955 |
+| 2.2047        | 1.14  | 510  | 0.5262          | 0.9410   | 0.9408 |
+| 2.2047        | 1.21  | 540  | 0.5107          | 0.9294   | 0.9297 |
+| 2.2047        | 1.27  | 570  | 0.4612          | 0.9285   | 0.9292 |
+| 2.2047        | 1.34  | 600  | 0.3487          | 0.9410   | 0.9407 |
+| 2.2047        | 1.41  | 630  | 0.3137          | 0.9374   | 0.9369 |
+| 2.2047        | 1.47  | 660  | 0.2951          | 0.9223   | 0.9190 |
+| 2.2047        | 1.54  | 690  | 0.2738          | 0.9374   | 0.9377 |
+| 2.2047        | 1.61  | 720  | 0.2472          | 0.9446   | 0.9439 |
+| 2.2047        | 1.67  | 750  | 0.1988          | 0.9535   | 0.9530 |
+| 2.2047        | 1.74  | 780  | 0.2016          | 0.9517   | 0.9519 |
+| 2.2047        | 1.81  | 810  | 0.2158          | 0.9428   | 0.9427 |
+| 2.2047        | 1.88  | 840  | 0.2519          | 0.9330   | 0.9324 |
+| 2.2047        | 1.94  | 870  | 0.2224          | 0.9437   | 0.9436 |
+| 2.2047        | 2.01  | 900  | 0.3032          | 0.9285   | 0.9276 |
+| 2.2047        | 2.08  | 930  | 0.1815          | 0.9544   | 0.9546 |
+| 2.2047        | 2.14  | 960  | 0.2125          | 0.9455   | 0.9455 |
+| 2.2047        | 2.21  | 990  | 0.2198          | 0.9455   | 0.9446 |
+| 0.2888        | 2.28  | 1020 | 0.1869          | 0.9571   | 0.9568 |
+| 0.2888        | 2.34  | 1050 | 0.1705          | 0.9571   | 0.9568 |
+| 0.2888        | 2.41  | 1080 | 0.1927          | 0.9526   | 0.9523 |
+| 0.2888        | 2.48  | 1110 | 0.1700          | 0.9562   | 0.9561 |
+| 0.2888        | 2.54  | 1140 | 0.2162          | 0.9464   | 0.9460 |
+| 0.2888        | 2.61  | 1170 | 0.1540          | 0.9616   | 0.9618 |
+| 0.2888        | 2.68  | 1200 | 0.1752          | 0.9562   | 0.9561 |
+| 0.2888        | 2.75  | 1230 | 0.1476          | 0.9607   | 0.9605 |
+| 0.2888        | 2.81  | 1260 | 0.2575          | 0.9410   | 0.9414 |
+| 0.2888        | 2.88  | 1290 | 0.1574          | 0.9616   | 0.9614 |
+| 0.2888        | 2.95  | 1320 | 0.1574          | 0.9598   | 0.9596 |
+| 0.2888        | 3.01  | 1350 | 0.1640          | 0.9580   | 0.9578 |
+| 0.2888        | 3.08  | 1380 | 0.1627          | 0.9598   | 0.9594 |
+| 0.2888        | 3.15  | 1410 | 0.1866          | 0.9544   | 0.9550 |
+| 0.2888        | 3.21  | 1440 | 0.1610          | 0.9526   | 0.9526 |
+| 0.2888        | 3.28  | 1470 | 0.2134          | 0.9419   | 0.9412 |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,50 @@
+{
+  "_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": "agent_apology_error_mistake",
+    "2": "agent_apology_unsatisfactory",
+    "3": "agent_didnt_understand",
+    "4": "agent_limited_capabilities",
+    "5": "agent_refuses_answer",
+    "6": "image_limitations",
+    "7": "no_information_doesnt_know",
+    "8": "success_and_followup_assistance"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "OTHER": 0,
+    "agent_apology_error_mistake": 1,
+    "agent_apology_unsatisfactory": 2,
+    "agent_didnt_understand": 3,
+    "agent_limited_capabilities": 4,
+    "agent_refuses_answer": 5,
+    "image_limitations": 6,
+    "no_information_doesnt_know": 7,
+    "success_and_followup_assistance": 8
+  },
+  "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:e0ae1ae3a03cf1e18c9ab329791d52b381aa333fad4e8cbc3885a0fb085fc232
+size 121205916

runs/Feb12_11-29-15_eeb74acdeae9/events.out.tfevents.1707737367.eeb74acdeae9.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0213caeb3265068678aea266af46c16d6148a0445531ce6d0d19e5ad36cc6da
+size 23995

runs/Feb12_11-29-15_eeb74acdeae9/events.out.tfevents.1707737881.eeb74acdeae9.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b70aeb8ad5411318ddd02cf3e44ec49a228307c23422677fc8ca4fac11b0ee8
+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 +1,61 @@
+{
+  "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": 256,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "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 sha256:1def2c40b83d641bb90a36f594e188cd44ad8f4579d53fa91dcf4f73013ff3df
+size 4856