End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,77 @@
+---
+license: bigscience-bloom-rail-1.0
+base_model: bigscience/bloomz-560m
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: BLOOM-Meta4Types-ft-ES
+  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. -->
+
+# BLOOM-Meta4Types-ft-ES
+
+This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6658
+- Roc Auc: 0.6521
+- Hamming Loss: 0.2255
+- F1 Score: 0.5792
+- Accuracy: 0.5098
+- Precision: 0.5611
+- Recall: 0.6085
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Roc Auc | Hamming Loss | F1 Score | Accuracy | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------------:|:--------:|:--------:|:---------:|:------:|
+| No log        | 1.0   | 204  | 1.4085          | 0.5227  | 0.3775       | 0.0874   | 0.0490   | 0.9333    | 0.0500 |
+| No log        | 2.0   | 408  | 1.3092          | 0.5569  | 0.4036       | 0.3425   | 0.2353   | 0.7464    | 0.4360 |
+| 1.9965        | 3.0   | 612  | 1.2200          | 0.5497  | 0.2304       | 0.4634   | 0.4510   | 0.7327    | 0.5574 |
+| 1.9965        | 4.0   | 816  | 1.4996          | 0.5843  | 0.3235       | 0.3965   | 0.3922   | 0.4177    | 0.4519 |
+| 0.6193        | 5.0   | 1020 | 1.0759          | 0.5823  | 0.2271       | 0.4488   | 0.5098   | 0.6180    | 0.4070 |
+| 0.6193        | 6.0   | 1224 | 1.8243          | 0.5808  | 0.2614       | 0.4892   | 0.3775   | 0.5688    | 0.5824 |
+| 0.6193        | 7.0   | 1428 | 1.6658          | 0.6521  | 0.2255       | 0.5792   | 0.5098   | 0.5611    | 0.6085 |
+| 0.202         | 8.0   | 1632 | 2.0491          | 0.5856  | 0.2075       | 0.4864   | 0.5441   | 0.5844    | 0.4447 |
+| 0.202         | 9.0   | 1836 | 2.2174          | 0.6241  | 0.1944       | 0.5733   | 0.5588   | 0.6183    | 0.5504 |
+| 0.0338        | 10.0  | 2040 | 2.1754          | 0.6265  | 0.1993       | 0.5693   | 0.5539   | 0.6197    | 0.5399 |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "bigscience/bloomz-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "problem_type": "multi_label_classification",
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181a72a997f07e531d902cee75d74a2ce9a7aabc2663a6aeb26a460773f553fe
+size 2236904672

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae95e8c782e419456cf0ae52d465317dca8c4535e4088405a5712eeda1b3670c
+size 14500763

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8199e9398d3c2cfaef2fe7d6e0732a64381853f308020103438e49a67e810b2
+size 5176