Upload folder using huggingface_hub

.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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,141 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer
+
+This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### 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
+
+### Framework Versions
+- Python: 3.10.15
+- Sentence Transformers: 3.2.0
+- Transformers: 4.45.2
+- PyTorch: 2.5.0+cu124
+- Accelerate: 1.0.1
+- Datasets: 3.0.1
+- Tokenizers: 0.20.1
+
+## Citation
+
+### BibTeX
+
+<!--
+## 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.*
+-->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/root/FlagEmbedding/model/checkpoint-1000",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.45.2",
+    "pytorch": "2.5.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc084f415a8143e0ed902b0fa5a31a46580f31595ac921772f16283c257d9b1
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daaf08a5921c5d8904a82f8567d6fe7978bfb5d781f39e00a89fcf860be09a81
+size 4533972233

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b801ae866328c0fc70d4ceee606053130a7c2c233d3fcbf60cb4cdc20feb8f
+size 14308

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0a3e7fcb2190532bf3ec1d72999db0e0b9b355630fba59249e99dd669c6408
+size 1064

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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": true,
+    "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74659c780d49afad7a7b9799868f75cbd3014fb6c34956e85a793028d38094a
+size 17098251

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6447368421052633,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01644736842105263,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.7345,
+      "step": 10
+    },
+    {
+      "epoch": 0.03289473684210526,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.5846,
+      "step": 20
+    },
+    {
+      "epoch": 0.049342105263157895,
+      "grad_norm": 56.480621337890625,
+      "learning_rate": 9.998355263157894e-06,
+      "loss": 0.8864,
+      "step": 30
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": NaN,
+      "learning_rate": 9.998355263157894e-06,
+      "loss": 0.4863,
+      "step": 40
+    },
+    {
+      "epoch": 0.08223684210526316,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.4998,
+      "step": 50
+    },
+    {
+      "epoch": 0.09868421052631579,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.7638,
+      "step": 60
+    },
+    {
+      "epoch": 0.11513157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.561,
+      "step": 70
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.5553,
+      "step": 80
+    },
+    {
+      "epoch": 0.14802631578947367,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.4243,
+      "step": 90
+    },
+    {
+      "epoch": 0.16447368421052633,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.5658,
+      "step": 100
+    },
+    {
+      "epoch": 0.18092105263157895,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.6598,
+      "step": 110
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.6398,
+      "step": 120
+    },
+    {
+      "epoch": 0.2138157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.5054,
+      "step": 130
+    },
+    {
+      "epoch": 0.23026315789473684,
+      "grad_norm": NaN,
+      "learning_rate": 9.99671052631579e-06,
+      "loss": 0.5486,
+      "step": 140
+    },
+    {
+      "epoch": 0.24671052631578946,
+      "grad_norm": NaN,
+      "learning_rate": 9.99342105263158e-06,
+      "loss": 0.361,
+      "step": 150
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.6621,
+      "step": 160
+    },
+    {
+      "epoch": 0.27960526315789475,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.29605263157894735,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.34539473684210525,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3618421052631579,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3782894736842105,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.41118421052631576,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4276315789473684,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4440789473684211,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.4769736842105263,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.4934210526315789,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.5098684210526315,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5427631578947368,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5592105263157895,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5756578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.6085526315789473,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6414473684210527,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6743421052631579,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6907894736842105,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.7072368421052632,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.7401315789473685,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.756578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7730263157894737,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.805921052631579,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.8223684210526315,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.8388157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8717105263157895,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8881578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.9046052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.9539473684210527,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9703947368421053,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.0032894736842106,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 610
+    },
+    {
+      "epoch": 1.019736842105263,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 620
+    },
+    {
+      "epoch": 1.0361842105263157,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 630
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.069078947368421,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0855263157894737,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.1019736842105263,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.1348684210526316,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.1513157894736843,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.1677631578947367,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.200657894736842,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.2171052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.2335526315789473,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.2664473684210527,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2828947368421053,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.299342105263158,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.3322368421052633,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.3486842105263157,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.3651315789473684,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3980263157894737,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.4144736842105263,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.430921052631579,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.4638157894736843,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.4802631578947367,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.4967105263157894,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.5296052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.5460526315789473,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.5953947368421053,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.611842105263158,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.6282894736842106,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": NaN,
+      "learning_rate": 9.991776315789474e-06,
+      "loss": 0.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6080,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "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 sha256:22f491e3b3d534472aa9bd4d8770f4a67c73de86804b7385ee37f5ad2c607beb
+size 5432