Upload folder using huggingface_hub

1_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 256, "out_features": 128, "bias": false, "activation_function": "torch.nn.modules.linear.Identity"}

1_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f3c9d897ea17d55c0706229cf2975d889e959e8c6b1e57b291b64f3af88834
+size 131160

README.md

@@ -0,0 +1,460 @@
+---
+language:
+- en
+tags:
+- ColBERT
+- PyLate
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:798036
+- loss:Distillation
+base_model: dbmdz/electra-small-turkish-cased-discriminator
+datasets:
+- Speedsy/ms-marco-tr-bge
+pipeline_tag: sentence-similarity
+library_name: PyLate
+---
+
+# PyLate model based on dbmdz/electra-small-turkish-cased-discriminator
+
+This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [dbmdz/electra-small-turkish-cased-discriminator](https://huggingface.co/dbmdz/electra-small-turkish-cased-discriminator) on the [train](https://huggingface.co/datasets/Speedsy/ms-marco-tr-bge) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
+
+## Model Details
+
+### Model Description
+- **Model Type:** PyLate model
+- **Base model:** [dbmdz/electra-small-turkish-cased-discriminator](https://huggingface.co/dbmdz/electra-small-turkish-cased-discriminator) <!-- at revision 6e0249165ebce3a4c15aae466387cb2127a7f076 -->
+- **Document Length:** 180 tokens
+- **Query Length:** 32 tokens
+- **Output Dimensionality:** 128 tokens
+- **Similarity Function:** MaxSim
+- **Training Dataset:**
+    - [train](https://huggingface.co/datasets/Speedsy/ms-marco-tr-bge)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [PyLate Documentation](https://lightonai.github.io/pylate/)
+- **Repository:** [PyLate on GitHub](https://github.com/lightonai/pylate)
+- **Hugging Face:** [PyLate models on Hugging Face](https://huggingface.co/models?library=PyLate)
+
+### Full Model Architecture
+
+```
+ColBERT(
+  (0): Transformer({'max_seq_length': 179, 'do_lower_case': False}) with Transformer model: ElectraModel 
+  (1): Dense({'in_features': 256, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+)
+```
+
+## Usage
+First install the PyLate library:
+
+```bash
+pip install -U pylate
+```
+
+### Retrieval
+
+PyLate provides a streamlined interface to index and retrieve documents using ColBERT models. The index leverages the Voyager HNSW index to efficiently handle document embeddings and enable fast retrieval.
+
+#### Indexing documents
+
+First, load the ColBERT model and initialize the Voyager index, then encode and index your documents:
+
+```python
+from pylate import indexes, models, retrieve
+
+# Step 1: Load the ColBERT model
+model = models.ColBERT(
+    model_name_or_path=pylate_model_id,
+)
+
+# Step 2: Initialize the Voyager index
+index = indexes.Voyager(
+    index_folder="pylate-index",
+    index_name="index",
+    override=True,  # This overwrites the existing index if any
+)
+
+# Step 3: Encode the documents
+documents_ids = ["1", "2", "3"]
+documents = ["document 1 text", "document 2 text", "document 3 text"]
+
+documents_embeddings = model.encode(
+    documents,
+    batch_size=32,
+    is_query=False,  # Ensure that it is set to False to indicate that these are documents, not queries
+    show_progress_bar=True,
+)
+
+# Step 4: Add document embeddings to the index by providing embeddings and corresponding ids
+index.add_documents(
+    documents_ids=documents_ids,
+    documents_embeddings=documents_embeddings,
+)
+```
+
+Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it:
+
+```python
+# To load an index, simply instantiate it with the correct folder/name and without overriding it
+index = indexes.Voyager(
+    index_folder="pylate-index",
+    index_name="index",
+)
+```
+
+#### Retrieving top-k documents for queries
+
+Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries.
+To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores:
+
+```python
+# Step 1: Initialize the ColBERT retriever
+retriever = retrieve.ColBERT(index=index)
+
+# Step 2: Encode the queries
+queries_embeddings = model.encode(
+    ["query for document 3", "query for document 1"],
+    batch_size=32,
+    is_query=True,  #  # Ensure that it is set to False to indicate that these are queries
+    show_progress_bar=True,
+)
+
+# Step 3: Retrieve top-k documents
+scores = retriever.retrieve(
+    queries_embeddings=queries_embeddings,
+    k=10,  # Retrieve the top 10 matches for each query
+)
+```
+
+### Reranking
+If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank:
+
+```python
+from pylate import rank, models
+
+queries = [
+    "query A",
+    "query B",
+]
+
+documents = [
+    ["document A", "document B"],
+    ["document 1", "document C", "document B"],
+]
+
+documents_ids = [
+    [1, 2],
+    [1, 3, 2],
+]
+
+model = models.ColBERT(
+    model_name_or_path=pylate_model_id,
+)
+
+queries_embeddings = model.encode(
+    queries,
+    is_query=True,
+)
+
+documents_embeddings = model.encode(
+    documents,
+    is_query=False,
+)
+
+reranked_documents = rank.rerank(
+    documents_ids=documents_ids,
+    queries_embeddings=queries_embeddings,
+    documents_embeddings=documents_embeddings,
+)
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### train
+
+* Dataset: [train](https://huggingface.co/datasets/Speedsy/ms-marco-tr-bge) at [b9b0f7f](https://huggingface.co/datasets/Speedsy/ms-marco-tr-bge/tree/b9b0f7fd13c3ce3b632a3a1cd37f6ddbf8a040f5)
+* Size: 798,036 training samples
+* Columns: <code>query_id</code>, <code>document_ids</code>, and <code>scores</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query_id                                                                        | document_ids                        | scores                              |
+  |:--------|:--------------------------------------------------------------------------------|:------------------------------------|:------------------------------------|
+  | type    | string                                                                          | list                                | list                                |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 6.23 tokens</li><li>max: 8 tokens</li></ul> | <ul><li>size: 32 elements</li></ul> | <ul><li>size: 32 elements</li></ul> |
+* Samples:
+  | query_id             | document_ids                                                              | scores                                                                                                     |
+  |:---------------------|:--------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------|
+  | <code>817836</code>  | <code>['2716076', '6741935', '2681109', '5562684', '3507339', ...]</code> | <code>[1.0, 0.7059561610221863, 0.21702419221401215, 0.38270196318626404, 0.20812414586544037, ...]</code> |
+  | <code>1045170</code> | <code>['5088671', '2953295', '8783471', '4268439', '6339935', ...]</code> | <code>[1.0, 0.6493034362792969, 0.0692221149802208, 0.17963139712810516, 0.6697239875793457, ...]</code>   |
+  | <code>1154488</code> | <code>['6498614', '3770829', '1060712', '2590533', '7672044', ...]</code> | <code>[0.9497447609901428, 0.6662212610244751, 0.7423420548439026, 1.0, 0.6580896973609924, ...]</code>    |
+* Loss: <code>pylate.losses.distillation.Distillation</code>
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 16
+- `learning_rate`: 3e-05
+- `num_train_epochs`: 1
+- `bf16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 8
+- `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`: 3e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `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_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `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
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `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`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss |
+|:------:|:-----:|:-------------:|
+| 0.0100 | 500   | 0.0466        |
+| 0.0200 | 1000  | 0.0426        |
+| 0.0301 | 1500  | 0.0382        |
+| 0.0401 | 2000  | 0.036         |
+| 0.0501 | 2500  | 0.0337        |
+| 0.0601 | 3000  | 0.0314        |
+| 0.0702 | 3500  | 0.0304        |
+| 0.0802 | 4000  | 0.03          |
+| 0.0902 | 4500  | 0.0292        |
+| 0.1002 | 5000  | 0.0286        |
+| 0.1103 | 5500  | 0.0284        |
+| 0.1203 | 6000  | 0.028         |
+| 0.1303 | 6500  | 0.0277        |
+| 0.1403 | 7000  | 0.0275        |
+| 0.1504 | 7500  | 0.027         |
+| 0.1604 | 8000  | 0.0267        |
+| 0.1704 | 8500  | 0.0265        |
+| 0.1804 | 9000  | 0.0263        |
+| 0.1905 | 9500  | 0.0264        |
+| 0.2005 | 10000 | 0.0263        |
+| 0.2105 | 10500 | 0.026         |
+| 0.2205 | 11000 | 0.0255        |
+| 0.2306 | 11500 | 0.0258        |
+| 0.2406 | 12000 | 0.0256        |
+| 0.2506 | 12500 | 0.0255        |
+| 0.2606 | 13000 | 0.0255        |
+| 0.2707 | 13500 | 0.0251        |
+| 0.2807 | 14000 | 0.025         |
+| 0.2907 | 14500 | 0.025         |
+| 0.3007 | 15000 | 0.0247        |
+| 0.3108 | 15500 | 0.0248        |
+| 0.3208 | 16000 | 0.0245        |
+| 0.3308 | 16500 | 0.0245        |
+| 0.3408 | 17000 | 0.0243        |
+| 0.3509 | 17500 | 0.0245        |
+| 0.3609 | 18000 | 0.024         |
+| 0.3709 | 18500 | 0.0241        |
+
+
+### Framework Versions
+- Python: 3.11.12
+- Sentence Transformers: 3.4.1
+- PyLate: 1.1.7
+- Transformers: 4.48.2
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.5.2
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084"
+}
+```
+
+#### PyLate
+```bibtex
+@misc{PyLate,
+title={PyLate: Flexible Training and Retrieval for Late Interaction Models},
+author={Chaffin, Antoine and Sourty, Raphaël},
+url={https://github.com/lightonai/pylate},
+year={2024}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "[D] ": 32001,
+  "[Q] ": 32000
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "dbmdz/electra-small-turkish-cased-discriminator",
+  "_num_labels": 2,
+  "architectures": [
+    "ElectraModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32002
+}

config_sentence_transformers.json

@@ -0,0 +1,49 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.2",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "MaxSim",
+  "query_prefix": "[Q] ",
+  "document_prefix": "[D] ",
+  "query_length": 32,
+  "document_length": 180,
+  "attend_to_expansion_tokens": false,
+  "skiplist_words": [
+    "!",
+    "\"",
+    "#",
+    "$",
+    "%",
+    "&",
+    "'",
+    "(",
+    ")",
+    "*",
+    "+",
+    ",",
+    "-",
+    ".",
+    "/",
+    ":",
+    ";",
+    "<",
+    "=",
+    ">",
+    "?",
+    "@",
+    "[",
+    "\\",
+    "]",
+    "^",
+    "_",
+    "`",
+    "{",
+    "|",
+    "}",
+    "~"
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367d47e46acca0b6db7ea8a33ba1e67bc4c1b1a87a7a230722f1cdd77838693c
+size 54711784

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Dense",
+    "type": "pylate.models.Dense.Dense"
+  }
+]

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691906454c33c9d148e04de3737954edbf433ddb493a946940de426cb0f81e2a
+size 109809018

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ec4bc7dbdd7e16c998e311d6ab7642bcd9880a9147e419c7c747654ec1017f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2358655ee72a5dc00545d9763476db9bd5b71c2d436fbfcff268ce73130fafe8
+size 1064

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 179,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[MASK]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,75 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[Q] ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "[D] ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[MASK]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,292 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.37090500822005695,
+  "eval_steps": 500,
+  "global_step": 18500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01002445968162316,
+      "grad_norm": 0.21047678589820862,
+      "learning_rate": 2.969926620955131e-05,
+      "loss": 0.0466,
+      "step": 500
+    },
+    {
+      "epoch": 0.02004891936324632,
+      "grad_norm": 0.3244280219078064,
+      "learning_rate": 2.939853241910261e-05,
+      "loss": 0.0426,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03007337904486948,
+      "grad_norm": 0.3163236379623413,
+      "learning_rate": 2.9097798628653917e-05,
+      "loss": 0.0382,
+      "step": 1500
+    },
+    {
+      "epoch": 0.04009783872649264,
+      "grad_norm": 0.21580693125724792,
+      "learning_rate": 2.879706483820522e-05,
+      "loss": 0.036,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0501222984081158,
+      "grad_norm": 0.25340843200683594,
+      "learning_rate": 2.849633104775653e-05,
+      "loss": 0.0337,
+      "step": 2500
+    },
+    {
+      "epoch": 0.06014675808973896,
+      "grad_norm": 0.23738078773021698,
+      "learning_rate": 2.819559725730783e-05,
+      "loss": 0.0314,
+      "step": 3000
+    },
+    {
+      "epoch": 0.07017121777136212,
+      "grad_norm": 0.15767431259155273,
+      "learning_rate": 2.7894863466859138e-05,
+      "loss": 0.0304,
+      "step": 3500
+    },
+    {
+      "epoch": 0.08019567745298528,
+      "grad_norm": 0.14462140202522278,
+      "learning_rate": 2.7594129676410442e-05,
+      "loss": 0.03,
+      "step": 4000
+    },
+    {
+      "epoch": 0.09022013713460844,
+      "grad_norm": 0.1084773987531662,
+      "learning_rate": 2.729339588596175e-05,
+      "loss": 0.0292,
+      "step": 4500
+    },
+    {
+      "epoch": 0.1002445968162316,
+      "grad_norm": 0.1659129112958908,
+      "learning_rate": 2.699266209551305e-05,
+      "loss": 0.0286,
+      "step": 5000
+    },
+    {
+      "epoch": 0.11026905649785476,
+      "grad_norm": 0.13866464793682098,
+      "learning_rate": 2.6691928305064358e-05,
+      "loss": 0.0284,
+      "step": 5500
+    },
+    {
+      "epoch": 0.12029351617947792,
+      "grad_norm": 0.18351516127586365,
+      "learning_rate": 2.6391194514615663e-05,
+      "loss": 0.028,
+      "step": 6000
+    },
+    {
+      "epoch": 0.13031797586110108,
+      "grad_norm": 0.12797561287879944,
+      "learning_rate": 2.609046072416697e-05,
+      "loss": 0.0277,
+      "step": 6500
+    },
+    {
+      "epoch": 0.14034243554272424,
+      "grad_norm": 0.1829468458890915,
+      "learning_rate": 2.578972693371827e-05,
+      "loss": 0.0275,
+      "step": 7000
+    },
+    {
+      "epoch": 0.1503668952243474,
+      "grad_norm": 0.10733053088188171,
+      "learning_rate": 2.548899314326958e-05,
+      "loss": 0.027,
+      "step": 7500
+    },
+    {
+      "epoch": 0.16039135490597056,
+      "grad_norm": 0.12314225733280182,
+      "learning_rate": 2.5188259352820883e-05,
+      "loss": 0.0267,
+      "step": 8000
+    },
+    {
+      "epoch": 0.17041581458759372,
+      "grad_norm": 0.1012982577085495,
+      "learning_rate": 2.488752556237219e-05,
+      "loss": 0.0265,
+      "step": 8500
+    },
+    {
+      "epoch": 0.18044027426921688,
+      "grad_norm": 0.1413574069738388,
+      "learning_rate": 2.4586791771923492e-05,
+      "loss": 0.0263,
+      "step": 9000
+    },
+    {
+      "epoch": 0.19046473395084004,
+      "grad_norm": 0.15352074801921844,
+      "learning_rate": 2.42860579814748e-05,
+      "loss": 0.0264,
+      "step": 9500
+    },
+    {
+      "epoch": 0.2004891936324632,
+      "grad_norm": 0.11118650436401367,
+      "learning_rate": 2.3985324191026104e-05,
+      "loss": 0.0263,
+      "step": 10000
+    },
+    {
+      "epoch": 0.21051365331408636,
+      "grad_norm": 0.1239309310913086,
+      "learning_rate": 2.368459040057741e-05,
+      "loss": 0.026,
+      "step": 10500
+    },
+    {
+      "epoch": 0.22053811299570952,
+      "grad_norm": 0.09220115840435028,
+      "learning_rate": 2.3383856610128712e-05,
+      "loss": 0.0255,
+      "step": 11000
+    },
+    {
+      "epoch": 0.23056257267733268,
+      "grad_norm": 0.12439100444316864,
+      "learning_rate": 2.308312281968002e-05,
+      "loss": 0.0258,
+      "step": 11500
+    },
+    {
+      "epoch": 0.24058703235895584,
+      "grad_norm": 0.12189625203609467,
+      "learning_rate": 2.2782389029231324e-05,
+      "loss": 0.0256,
+      "step": 12000
+    },
+    {
+      "epoch": 0.25061149204057903,
+      "grad_norm": 0.14276236295700073,
+      "learning_rate": 2.2481655238782632e-05,
+      "loss": 0.0255,
+      "step": 12500
+    },
+    {
+      "epoch": 0.26063595172220216,
+      "grad_norm": 0.11102870106697083,
+      "learning_rate": 2.2180921448333933e-05,
+      "loss": 0.0255,
+      "step": 13000
+    },
+    {
+      "epoch": 0.27066041140382535,
+      "grad_norm": 0.12738683819770813,
+      "learning_rate": 2.188018765788524e-05,
+      "loss": 0.0251,
+      "step": 13500
+    },
+    {
+      "epoch": 0.2806848710854485,
+      "grad_norm": 0.14391563832759857,
+      "learning_rate": 2.1579453867436545e-05,
+      "loss": 0.025,
+      "step": 14000
+    },
+    {
+      "epoch": 0.29070933076707167,
+      "grad_norm": 0.12654729187488556,
+      "learning_rate": 2.1278720076987853e-05,
+      "loss": 0.025,
+      "step": 14500
+    },
+    {
+      "epoch": 0.3007337904486948,
+      "grad_norm": 0.1650782972574234,
+      "learning_rate": 2.0977986286539154e-05,
+      "loss": 0.0247,
+      "step": 15000
+    },
+    {
+      "epoch": 0.310758250130318,
+      "grad_norm": 0.1010371670126915,
+      "learning_rate": 2.067725249609046e-05,
+      "loss": 0.0248,
+      "step": 15500
+    },
+    {
+      "epoch": 0.3207827098119411,
+      "grad_norm": 0.08663147687911987,
+      "learning_rate": 2.0376518705641766e-05,
+      "loss": 0.0245,
+      "step": 16000
+    },
+    {
+      "epoch": 0.3308071694935643,
+      "grad_norm": 0.11956797540187836,
+      "learning_rate": 2.0075784915193073e-05,
+      "loss": 0.0245,
+      "step": 16500
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.07630161195993423,
+      "learning_rate": 1.9775051124744374e-05,
+      "loss": 0.0243,
+      "step": 17000
+    },
+    {
+      "epoch": 0.35085608885681063,
+      "grad_norm": 0.10799304395914078,
+      "learning_rate": 1.9474317334295682e-05,
+      "loss": 0.0245,
+      "step": 17500
+    },
+    {
+      "epoch": 0.36088054853843377,
+      "grad_norm": 0.12928515672683716,
+      "learning_rate": 1.9173583543846986e-05,
+      "loss": 0.024,
+      "step": 18000
+    },
+    {
+      "epoch": 0.37090500822005695,
+      "grad_norm": 0.13743112981319427,
+      "learning_rate": 1.8872849753398294e-05,
+      "loss": 0.0241,
+      "step": 18500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 49878,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eda17bad99315f3ee90c0862eaf62aee3bfd35ee7f02532babb38292d929cdc
+size 5688