Auto-deploy from Colab training

Information-Retrieval_evaluation_kepja227-val_results.csv

@@ -1,2 +1,3 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.6178451178451179,0.7154882154882155,0.7643097643097643,0.6178451178451179,0.6178451178451179,0.23063973063973064,0.6919191919191919,0.14309764309764308,0.7154882154882155,0.07643097643097643,0.7643097643097643,0.6643652129763241,0.6882122849202972,0.6698747760816915
+-1,-1,0.6178451178451179,0.7154882154882155,0.765993265993266,0.6178451178451179,0.6178451178451179,0.2312008978675645,0.6936026936026936,0.14309764309764308,0.7154882154882155,0.0765993265993266,0.765993265993266,0.6629776601998825,0.6874444630726724,0.6680560214049706

README.md

@@ -298,43 +298,43 @@ model-index:
       value: 0.6178451178451179
       name: Cosine Accuracy@1
     - type: cosine_accuracy@5
-      value: 0.7171717171717171
+      value: 0.7154882154882155
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.7643097643097643
+      value: 0.765993265993266
       name: Cosine Accuracy@10
     - type: cosine_precision@1
       value: 0.6178451178451179
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.23063973063973064
+      value: 0.2312008978675645
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.14343434343434341
+      value: 0.14309764309764308
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07643097643097643
+      value: 0.0765993265993266
       name: Cosine Precision@10
     - type: cosine_recall@1
       value: 0.6178451178451179
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.6919191919191919
+      value: 0.6936026936026936
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.7171717171717171
+      value: 0.7154882154882155
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.7643097643097643
+      value: 0.765993265993266
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.6880049482414763
+      value: 0.6874797322596491
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.6641006627117738
+      value: 0.6630217519106407
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.6696084664815586
+      value: 0.6681043890199253
       name: Cosine Map@100
 ---
 
@@ -434,22 +434,22 @@ You can finetune this model on your own dataset.
 * Dataset: `kepja227-val`
 * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
 
-| Metric              | Value     |
-|:--------------------|:----------|
-| cosine_accuracy@1   | 0.6178    |
-| cosine_accuracy@5   | 0.7172    |
-| cosine_accuracy@10  | 0.7643    |
-| cosine_precision@1  | 0.6178    |
-| cosine_precision@3  | 0.2306    |
-| cosine_precision@5  | 0.1434    |
-| cosine_precision@10 | 0.0764    |
-| cosine_recall@1     | 0.6178    |
-| cosine_recall@3     | 0.6919    |
-| cosine_recall@5     | 0.7172    |
-| cosine_recall@10    | 0.7643    |
-| **cosine_ndcg@10**  | **0.688** |
-| cosine_mrr@10       | 0.6641    |
-| cosine_map@100      | 0.6696    |
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6178     |
+| cosine_accuracy@5   | 0.7155     |
+| cosine_accuracy@10  | 0.766      |
+| cosine_precision@1  | 0.6178     |
+| cosine_precision@3  | 0.2312     |
+| cosine_precision@5  | 0.1431     |
+| cosine_precision@10 | 0.0766     |
+| cosine_recall@1     | 0.6178     |
+| cosine_recall@3     | 0.6936     |
+| cosine_recall@5     | 0.7155     |
+| cosine_recall@10    | 0.766      |
+| **cosine_ndcg@10**  | **0.6875** |
+| cosine_mrr@10       | 0.663      |
+| cosine_map@100      | 0.6681     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -493,110 +493,127 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
-- `per_device_train_batch_size`: 64
-- `fp16`: True
 - `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
 - `per_device_eval_batch_size`: 64
+- `fp16`: True
 - `multi_dataset_batch_sampler`: round_robin
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
 - `per_device_train_batch_size`: 64
-- `num_train_epochs`: 3
-- `max_steps`: -1
+- `per_device_eval_batch_size`: 64
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
 - `learning_rate`: 5e-05
-- `lr_scheduler_type`: linear
-- `lr_scheduler_kwargs`: None
-- `warmup_steps`: 0
-- `optim`: adamw_torch_fused
-- `optim_args`: None
 - `weight_decay`: 0.0
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
-- `optim_target_modules`: None
-- `gradient_accumulation_steps`: 1
-- `average_tokens_across_devices`: True
 - `max_grad_norm`: 1
-- `label_smoothing_factor`: 0.0
-- `bf16`: False
-- `fp16`: True
-- `bf16_full_eval`: False
-- `fp16_full_eval`: False
-- `tf32`: None
-- `gradient_checkpointing`: False
-- `gradient_checkpointing_kwargs`: None
-- `torch_compile`: False
-- `torch_compile_backend`: None
-- `torch_compile_mode`: None
-- `use_liger_kernel`: False
-- `liger_kernel_config`: None
-- `use_cache`: False
-- `neftune_noise_alpha`: None
-- `torch_empty_cache_steps`: None
-- `auto_find_batch_size`: False
-- `log_on_each_node`: True
-- `logging_nan_inf_filter`: True
-- `include_num_input_tokens_seen`: no
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
 - `log_level`: passive
 - `log_level_replica`: warning
-- `disable_tqdm`: False
-- `project`: huggingface
-- `trackio_space_id`: None
-- `trackio_bucket_id`: None
-- `trackio_static_space_id`: None
-- `eval_strategy`: steps
-- `per_device_eval_batch_size`: 64
-- `prediction_loss_only`: True
-- `eval_on_start`: False
-- `eval_do_concat_batches`: True
-- `eval_use_gather_object`: False
-- `eval_accumulation_steps`: None
-- `include_for_metrics`: []
-- `batch_eval_metrics`: False
-- `save_only_model`: False
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
 - `save_on_each_node`: False
-- `enable_jit_checkpoint`: False
-- `push_to_hub`: False
-- `hub_private_repo`: None
-- `hub_model_id`: None
-- `hub_strategy`: every_save
-- `hub_always_push`: False
-- `hub_revision`: None
-- `load_best_model_at_end`: False
-- `ignore_data_skip`: False
+- `save_only_model`: False
 - `restore_callback_states_from_checkpoint`: False
-- `full_determinism`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
 - `seed`: 42
 - `data_seed`: None
-- `use_cpu`: False
-- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
-- `parallelism_config`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
 - `dataloader_drop_last`: False
 - `dataloader_num_workers`: 0
-- `dataloader_pin_memory`: True
-- `dataloader_persistent_workers`: False
 - `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
 - `remove_unused_columns`: True
 - `label_names`: None
-- `train_sampling_strategy`: random
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
 - `length_column_name`: length
 - `ddp_find_unused_parameters`: None
 - `ddp_bucket_cap_mb`: None
 - `ddp_broadcast_buffers`: False
-- `ddp_static_graph`: None
-- `ddp_backend`: None
-- `ddp_timeout`: 1800
-- `fsdp`: []
-- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
-- `deepspeed`: None
-- `debug`: []
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
 - `skip_memory_metrics`: True
-- `do_predict`: False
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
 - `resume_from_checkpoint`: None
-- `warmup_ratio`: None
-- `local_rank`: -1
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
 - `prompts`: None
 - `batch_sampler`: batch_sampler
 - `multi_dataset_batch_sampler`: round_robin
@@ -607,20 +624,19 @@ You can finetune this model on your own dataset.
 | Epoch  | Step | kepja227-val_cosine_ndcg@10 |
 |:------:|:----:|:---------------------------:|
 | 1.0    | 83   | 0.6752                      |
-| 1.2048 | 100  | 0.6745                      |
-| 2.0    | 166  | 0.6845                      |
-| 2.4096 | 200  | 0.6868                      |
-| 3.0    | 249  | 0.6880                      |
+| 1.2048 | 100  | 0.6752                      |
+| 2.0    | 166  | 0.6830                      |
+| 2.4096 | 200  | 0.6875                      |
 
 
 ### Framework Versions
 - Python: 3.12.13
 - Sentence Transformers: 3.4.1
-- Transformers: 5.8.1
+- Transformers: 4.46.3
 - PyTorch: 2.10.0+cu128
-- Accelerate: 1.13.0
+- Accelerate: 1.0.1
 - Datasets: 4.8.5
-- Tokenizers: 0.22.2
+- Tokenizers: 0.20.3
 
 ## Citation
 

config.json

@@ -1,19 +1,15 @@
 {
-  "add_cross_attention": false,
+  "_name_or_path": "LazarusNLP/all-indo-e5-small-v4",
   "architectures": [
     "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": null,
   "classifier_dropout": null,
-  "dtype": "float32",
-  "eos_token_id": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 384,
   "initializer_range": 0.02,
   "intermediate_size": 1536,
-  "is_decoder": false,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
@@ -21,9 +17,9 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "tie_word_embeddings": true,
   "tokenizer_class": "XLMRobertaTokenizer",
-  "transformers_version": "5.8.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 250037

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
     "sentence_transformers": "3.4.1",
-    "transformers": "5.8.1",
+    "transformers": "4.46.3",
     "pytorch": "2.10.0+cu128"
   },
   "prompts": {},

eval/Information-Retrieval_evaluation_kepja227-val_results.csv

@@ -2,3 +2,6 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precis
 1.0,83,0.6094276094276094,0.7121212121212122,0.7424242424242424,0.6094276094276094,0.6094276094276094,0.22783389450056113,0.6835016835016835,0.14242424242424243,0.7121212121212122,0.07424242424242423,0.7424242424242424,0.6539034525145636,0.6752454423997064,0.6598796166523606
 2.0,166,0.6144781144781145,0.7171717171717171,0.7609427609427609,0.6144781144781145,0.6144781144781145,0.2312008978675645,0.6936026936026936,0.14343434343434344,0.7171717171717171,0.07609427609427609,0.7609427609427609,0.6604530757308534,0.6845046094524185,0.6658012423505567
 3.0,249,0.6178451178451179,0.7171717171717171,0.7643097643097643,0.6178451178451179,0.6178451178451179,0.23063973063973064,0.6919191919191919,0.14343434343434341,0.7171717171717171,0.07643097643097643,0.7643097643097643,0.6641006627117738,0.6880049482414763,0.6696084664815586
+1.0,83,0.6094276094276094,0.7121212121212122,0.7424242424242424,0.6094276094276094,0.6094276094276094,0.22783389450056113,0.6835016835016835,0.14242424242424243,0.7121212121212122,0.07424242424242423,0.7424242424242424,0.6539034525145636,0.6752454423997064,0.6598584649589793
+2.0,166,0.6127946127946128,0.7121212121212122,0.7609427609427609,0.6127946127946128,0.6127946127946128,0.23063973063973064,0.6919191919191919,0.14242424242424243,0.7121212121212122,0.0760942760942761,0.7609427609427609,0.6586707017262573,0.6829636660543899,0.664480258532924
+3.0,249,0.6161616161616161,0.7121212121212122,0.765993265993266,0.6161616161616161,0.6161616161616161,0.2295173961840628,0.6885521885521886,0.14242424242424243,0.7121212121212122,0.0765993265993266,0.765993265993266,0.6615039281705949,0.6863028940673471,0.6667244811711553

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4e8895d2cdef5dea5ecfbb13754ffb854047bcbcad98336f28c22c4dd00071
+oid sha256:014a0cddcc8d316d7806ee74c85c4917f30243e280055b095b5c67dd78652cd8
 size 470637416

special_tokens_map.json

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb02bfe42ffe0fe115de5c74f76c6480d730e60cc1f6ae567ff4d82cb305a113
-size 17082988
+oid sha256:2b95ee17661f8dfbbceaba374f6d277a6b5d8e1898c070a16331622024f58c67
+size 17083053

tokenizer_config.json

@@ -1,12 +1,50 @@
 {
-  "add_prefix_space": true,
-  "backend": "tokenizers",
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "is_local": false,
-  "local_files_only": false,
   "mask_token": "<mask>",
   "max_length": 128,
   "model_max_length": 128,