Commit
•
5d64586
1
Parent(s):
6819c8c
Initial Commit
Browse files- README.md +56 -0
- config.json +43 -0
- generation_config.json +7 -0
- gitattributes.txt +35 -0
- model.safetensors.index.json +693 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- trainer_state.json +3719 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- VILA
|
| 7 |
+
- VLM
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# VILA Model Card
|
| 11 |
+
|
| 12 |
+
## Model details
|
| 13 |
+
|
| 14 |
+
**Model type:**
|
| 15 |
+
VILA is a visual language model (VLM) pretrained with interleaved image-text data at scale, enabling multi-image VLM. VILA is deployable on the edge, including Jetson Orin and laptop by AWQ 4bit quantization through TinyChat framework. We find: (1) image-text pairs are not enough, interleaved image-text is essential; (2) unfreezing LLM during interleaved image-text pre-training enables in-context learning; (3)re-blending text-only instruction data is crucial to boost both VLM and text-only performance. VILA unveils appealing capabilities, including: multi-image reasoning, in-context learning, visual chain-of-thought, and better world knowledge.
|
| 16 |
+
|
| 17 |
+
**Model date:**
|
| 18 |
+
VILA-2.7b was trained in Feb 2024.
|
| 19 |
+
|
| 20 |
+
**Paper or resources for more information:**
|
| 21 |
+
https://github.com/Efficient-Large-Model/VILA
|
| 22 |
+
|
| 23 |
+
```
|
| 24 |
+
@misc{lin2023vila,
|
| 25 |
+
title={VILA: On Pre-training for Visual Language Models},
|
| 26 |
+
author={Ji Lin and Hongxu Yin and Wei Ping and Yao Lu and Pavlo Molchanov and Andrew Tao and Huizi Mao and Jan Kautz and Mohammad Shoeybi and Song Han},
|
| 27 |
+
year={2023},
|
| 28 |
+
eprint={2312.07533},
|
| 29 |
+
archivePrefix={arXiv},
|
| 30 |
+
primaryClass={cs.CV}
|
| 31 |
+
}
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
## License
|
| 35 |
+
- The code is released under the Apache 2.0 license as found in the [LICENSE](./LICENSE) file.
|
| 36 |
+
- The pretrained weights are released under the [CC-BY-NC-SA-4.0 license](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en).
|
| 37 |
+
- The service is a research preview intended for non-commercial use only, and is subject to the following licenses and terms:
|
| 38 |
+
- [Model License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA
|
| 39 |
+
- [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI
|
| 40 |
+
- [Dataset Licenses](https://github.com/Efficient-Large-Model/VILA/blob/main/data_prepare/LICENSE) for each one used during training.
|
| 41 |
+
|
| 42 |
+
**Where to send questions or comments about the model:**
|
| 43 |
+
https://github.com/Efficient-Large-Model/VILA/issues
|
| 44 |
+
|
| 45 |
+
## Intended use
|
| 46 |
+
**Primary intended uses:**
|
| 47 |
+
The primary use of VILA is research on large multimodal models and chatbots.
|
| 48 |
+
|
| 49 |
+
**Primary intended users:**
|
| 50 |
+
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
|
| 51 |
+
|
| 52 |
+
## Training dataset
|
| 53 |
+
See [Dataset Preparation](https://github.com/Efficient-Large-Model/VILA/blob/main/data_prepare/README.md) for more details.
|
| 54 |
+
|
| 55 |
+
## Evaluation dataset
|
| 56 |
+
A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.
|
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./checkpoints/vila-sheared-llama-2.7b-256gpus-mmc4-coyo",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaLlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"freeze_mm_mlp_adapter": false,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2560,
|
| 13 |
+
"image_aspect_ratio": "pad",
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 6912,
|
| 16 |
+
"max_position_embeddings": 4096,
|
| 17 |
+
"mm_hidden_size": 1024,
|
| 18 |
+
"mm_projector_lr": null,
|
| 19 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 20 |
+
"mm_use_im_patch_token": false,
|
| 21 |
+
"mm_use_im_start_end": false,
|
| 22 |
+
"mm_vision_select_feature": "patch",
|
| 23 |
+
"mm_vision_select_layer": -2,
|
| 24 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
| 25 |
+
"model_type": "llava_llama",
|
| 26 |
+
"num_attention_heads": 20,
|
| 27 |
+
"num_hidden_layers": 32,
|
| 28 |
+
"num_key_value_heads": 20,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pretraining_tp": 1,
|
| 31 |
+
"rms_norm_eps": 1e-05,
|
| 32 |
+
"rope_scaling": null,
|
| 33 |
+
"rope_theta": 10000.0,
|
| 34 |
+
"tie_word_embeddings": false,
|
| 35 |
+
"tokenizer_model_max_length": 4096,
|
| 36 |
+
"tokenizer_padding_side": "right",
|
| 37 |
+
"torch_dtype": "bfloat16",
|
| 38 |
+
"transformers_version": "4.38.1",
|
| 39 |
+
"tune_mm_mlp_adapter": false,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"use_mm_proj": true,
|
| 42 |
+
"vocab_size": 32000
|
| 43 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.38.1"
|
| 7 |
+
}
|
gitattributes.txt
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,693 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6028495872
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.norm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors"
|
| 692 |
+
}
|
| 693 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 4096,
|
| 36 |
+
"pad_token": "<unk>",
|
| 37 |
+
"padding_side": "right",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3719 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 527,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 18.569529999247134,
|
| 14 |
+
"learning_rate": 6.25e-06,
|
| 15 |
+
"loss": 2.2344,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0,
|
| 20 |
+
"grad_norm": 17.774880014109563,
|
| 21 |
+
"learning_rate": 1.25e-05,
|
| 22 |
+
"loss": 2.2188,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 16.126910180369833,
|
| 28 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 29 |
+
"loss": 2.0938,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 4.004205399706303,
|
| 35 |
+
"learning_rate": 2.5e-05,
|
| 36 |
+
"loss": 1.5625,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"grad_norm": 4.475863116578534,
|
| 42 |
+
"learning_rate": 3.125e-05,
|
| 43 |
+
"loss": 1.5547,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01,
|
| 48 |
+
"grad_norm": 3.9418457877357183,
|
| 49 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 50 |
+
"loss": 1.5312,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"grad_norm": 3.35497476295258,
|
| 56 |
+
"learning_rate": 4.375e-05,
|
| 57 |
+
"loss": 1.5312,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.02,
|
| 62 |
+
"grad_norm": 2.0238486012287824,
|
| 63 |
+
"learning_rate": 5e-05,
|
| 64 |
+
"loss": 1.4453,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"grad_norm": 1.3025920158121342,
|
| 70 |
+
"learning_rate": 5.6250000000000005e-05,
|
| 71 |
+
"loss": 1.4062,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02,
|
| 76 |
+
"grad_norm": 2.1578221590331648,
|
| 77 |
+
"learning_rate": 6.25e-05,
|
| 78 |
+
"loss": 1.4141,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02,
|
| 83 |
+
"grad_norm": 1.639048247445056,
|
| 84 |
+
"learning_rate": 6.875e-05,
|
| 85 |
+
"loss": 1.3906,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.02,
|
| 90 |
+
"grad_norm": 1.0758955455274364,
|
| 91 |
+
"learning_rate": 7.500000000000001e-05,
|
| 92 |
+
"loss": 1.3672,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.02,
|
| 97 |
+
"grad_norm": 0.9988841624058318,
|
| 98 |
+
"learning_rate": 8.125000000000001e-05,
|
| 99 |
+
"loss": 1.3516,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03,
|
| 104 |
+
"grad_norm": 1.036582323851064,
|
| 105 |
+
"learning_rate": 8.75e-05,
|
| 106 |
+
"loss": 1.3438,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.03,
|
| 111 |
+
"grad_norm": 1.0040586950026587,
|
| 112 |
+
"learning_rate": 9.375e-05,
|
| 113 |
+
"loss": 1.3438,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.03,
|
| 118 |
+
"grad_norm": 0.8112402128458829,
|
| 119 |
+
"learning_rate": 0.0001,
|
| 120 |
+
"loss": 1.3047,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.03,
|
| 125 |
+
"grad_norm": 0.806608090114202,
|
| 126 |
+
"learning_rate": 9.999905507663936e-05,
|
| 127 |
+
"loss": 1.3203,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.03,
|
| 132 |
+
"grad_norm": 0.8164159045230494,
|
| 133 |
+
"learning_rate": 9.99962203422726e-05,
|
| 134 |
+
"loss": 1.2812,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04,
|
| 139 |
+
"grad_norm": 0.7335139492736167,
|
| 140 |
+
"learning_rate": 9.9991495904044e-05,
|
| 141 |
+
"loss": 1.2969,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.04,
|
| 146 |
+
"grad_norm": 0.799772371827826,
|
| 147 |
+
"learning_rate": 9.998488194052287e-05,
|
| 148 |
+
"loss": 1.2734,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.04,
|
| 153 |
+
"grad_norm": 0.6718755777667486,
|
| 154 |
+
"learning_rate": 9.997637870169672e-05,
|
| 155 |
+
"loss": 1.2734,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.04,
|
| 160 |
+
"grad_norm": 0.7599864750693303,
|
| 161 |
+
"learning_rate": 9.996598650896192e-05,
|
| 162 |
+
"loss": 1.2578,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.04,
|
| 167 |
+
"grad_norm": 0.6886726902695142,
|
| 168 |
+
"learning_rate": 9.995370575511151e-05,
|
| 169 |
+
"loss": 1.2656,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.05,
|
| 174 |
+
"grad_norm": 0.6823417918062775,
|
| 175 |
+
"learning_rate": 9.993953690432031e-05,
|
| 176 |
+
"loss": 1.2734,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.05,
|
| 181 |
+
"grad_norm": 0.6382222948594751,
|
| 182 |
+
"learning_rate": 9.99234804921275e-05,
|
| 183 |
+
"loss": 1.2422,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.05,
|
| 188 |
+
"grad_norm": 0.6452753693126838,
|
| 189 |
+
"learning_rate": 9.990553712541617e-05,
|
| 190 |
+
"loss": 1.2422,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.05,
|
| 195 |
+
"grad_norm": 0.5904936283655213,
|
| 196 |
+
"learning_rate": 9.988570748239062e-05,
|
| 197 |
+
"loss": 1.2266,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.05,
|
| 202 |
+
"grad_norm": 0.5640365175871925,
|
| 203 |
+
"learning_rate": 9.986399231255056e-05,
|
| 204 |
+
"loss": 1.2031,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.06,
|
| 209 |
+
"grad_norm": 0.514358456822939,
|
| 210 |
+
"learning_rate": 9.984039243666283e-05,
|
| 211 |
+
"loss": 1.2344,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.06,
|
| 216 |
+
"grad_norm": 0.636209974460906,
|
| 217 |
+
"learning_rate": 9.981490874673039e-05,
|
| 218 |
+
"loss": 1.1953,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06,
|
| 223 |
+
"grad_norm": 0.5479990507502773,
|
| 224 |
+
"learning_rate": 9.978754220595861e-05,
|
| 225 |
+
"loss": 1.2031,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.06,
|
| 230 |
+
"grad_norm": 0.5561261900343224,
|
| 231 |
+
"learning_rate": 9.975829384871884e-05,
|
| 232 |
+
"loss": 1.2344,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.06,
|
| 237 |
+
"grad_norm": 0.4948569883144301,
|
| 238 |
+
"learning_rate": 9.97271647805093e-05,
|
| 239 |
+
"loss": 1.2109,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.06,
|
| 244 |
+
"grad_norm": 0.5167119119909488,
|
| 245 |
+
"learning_rate": 9.969415617791336e-05,
|
| 246 |
+
"loss": 1.2266,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.07,
|
| 251 |
+
"grad_norm": 0.508354119180698,
|
| 252 |
+
"learning_rate": 9.965926928855499e-05,
|
| 253 |
+
"loss": 1.2109,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.07,
|
| 258 |
+
"grad_norm": 0.5326133584880987,
|
| 259 |
+
"learning_rate": 9.962250543105167e-05,
|
| 260 |
+
"loss": 1.1797,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.07,
|
| 265 |
+
"grad_norm": 0.47996354720772333,
|
| 266 |
+
"learning_rate": 9.95838659949645e-05,
|
| 267 |
+
"loss": 1.1719,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.07,
|
| 272 |
+
"grad_norm": 0.4584403899961059,
|
| 273 |
+
"learning_rate": 9.954335244074574e-05,
|
| 274 |
+
"loss": 1.1797,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.07,
|
| 279 |
+
"grad_norm": 0.478024134726985,
|
| 280 |
+
"learning_rate": 9.950096629968352e-05,
|
| 281 |
+
"loss": 1.1953,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.08,
|
| 286 |
+
"grad_norm": 0.4831225145909792,
|
| 287 |
+
"learning_rate": 9.945670917384403e-05,
|
| 288 |
+
"loss": 1.1797,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.08,
|
| 293 |
+
"grad_norm": 0.47054504799219404,
|
| 294 |
+
"learning_rate": 9.941058273601096e-05,
|
| 295 |
+
"loss": 1.1719,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.08,
|
| 300 |
+
"grad_norm": 0.4940788339187542,
|
| 301 |
+
"learning_rate": 9.936258872962228e-05,
|
| 302 |
+
"loss": 1.1719,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.08,
|
| 307 |
+
"grad_norm": 0.44655071198353546,
|
| 308 |
+
"learning_rate": 9.931272896870426e-05,
|
| 309 |
+
"loss": 1.1953,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.08,
|
| 314 |
+
"grad_norm": 0.4620978351861828,
|
| 315 |
+
"learning_rate": 9.926100533780303e-05,
|
| 316 |
+
"loss": 1.1797,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.09,
|
| 321 |
+
"grad_norm": 0.4777738095085538,
|
| 322 |
+
"learning_rate": 9.920741979191331e-05,
|
| 323 |
+
"loss": 1.1641,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.09,
|
| 328 |
+
"grad_norm": 0.46687195896903444,
|
| 329 |
+
"learning_rate": 9.91519743564044e-05,
|
| 330 |
+
"loss": 1.1562,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.09,
|
| 335 |
+
"grad_norm": 0.4572029233269296,
|
| 336 |
+
"learning_rate": 9.909467112694384e-05,
|
| 337 |
+
"loss": 1.1719,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.09,
|
| 342 |
+
"grad_norm": 0.4379619610466461,
|
| 343 |
+
"learning_rate": 9.903551226941801e-05,
|
| 344 |
+
"loss": 1.1562,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.09,
|
| 349 |
+
"grad_norm": 0.4625672515990539,
|
| 350 |
+
"learning_rate": 9.897450001985039e-05,
|
| 351 |
+
"loss": 1.1406,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.09,
|
| 356 |
+
"grad_norm": 0.45763509639124433,
|
| 357 |
+
"learning_rate": 9.891163668431695e-05,
|
| 358 |
+
"loss": 1.1719,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.1,
|
| 363 |
+
"grad_norm": 0.4759593297993926,
|
| 364 |
+
"learning_rate": 9.88469246388591e-05,
|
| 365 |
+
"loss": 1.1484,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.1,
|
| 370 |
+
"grad_norm": 0.47690674058291993,
|
| 371 |
+
"learning_rate": 9.878036632939374e-05,
|
| 372 |
+
"loss": 1.2031,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.1,
|
| 377 |
+
"grad_norm": 0.44532349751989236,
|
| 378 |
+
"learning_rate": 9.871196427162092e-05,
|
| 379 |
+
"loss": 1.1172,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.1,
|
| 384 |
+
"grad_norm": 0.452106382176349,
|
| 385 |
+
"learning_rate": 9.86417210509288e-05,
|
| 386 |
+
"loss": 1.1094,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.1,
|
| 391 |
+
"grad_norm": 0.452753191760464,
|
| 392 |
+
"learning_rate": 9.85696393222957e-05,
|
| 393 |
+
"loss": 1.1953,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.11,
|
| 398 |
+
"grad_norm": 0.45441530517528445,
|
| 399 |
+
"learning_rate": 9.849572181019007e-05,
|
| 400 |
+
"loss": 1.1406,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.11,
|
| 405 |
+
"grad_norm": 0.5007896403646297,
|
| 406 |
+
"learning_rate": 9.84199713084672e-05,
|
| 407 |
+
"loss": 1.1406,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.11,
|
| 412 |
+
"grad_norm": 0.4608644722591853,
|
| 413 |
+
"learning_rate": 9.834239068026387e-05,
|
| 414 |
+
"loss": 1.1328,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.11,
|
| 419 |
+
"grad_norm": 0.4968111745587068,
|
| 420 |
+
"learning_rate": 9.826298285789002e-05,
|
| 421 |
+
"loss": 1.1328,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.11,
|
| 426 |
+
"grad_norm": 0.44573050581792,
|
| 427 |
+
"learning_rate": 9.818175084271786e-05,
|
| 428 |
+
"loss": 1.125,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.12,
|
| 433 |
+
"grad_norm": 0.46589557608902915,
|
| 434 |
+
"learning_rate": 9.809869770506856e-05,
|
| 435 |
+
"loss": 1.1328,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.12,
|
| 440 |
+
"grad_norm": 0.45678602237538535,
|
| 441 |
+
"learning_rate": 9.80138265840961e-05,
|
| 442 |
+
"loss": 1.1328,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.12,
|
| 447 |
+
"grad_norm": 0.43959375518292026,
|
| 448 |
+
"learning_rate": 9.792714068766872e-05,
|
| 449 |
+
"loss": 1.125,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.12,
|
| 454 |
+
"grad_norm": 0.41984631355693813,
|
| 455 |
+
"learning_rate": 9.783864329224752e-05,
|
| 456 |
+
"loss": 1.1406,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.12,
|
| 461 |
+
"grad_norm": 0.43389373514903795,
|
| 462 |
+
"learning_rate": 9.774833774276278e-05,
|
| 463 |
+
"loss": 1.1172,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.13,
|
| 468 |
+
"grad_norm": 0.4336892341975021,
|
| 469 |
+
"learning_rate": 9.765622745248739e-05,
|
| 470 |
+
"loss": 1.1406,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.13,
|
| 475 |
+
"grad_norm": 0.4410380396458464,
|
| 476 |
+
"learning_rate": 9.7562315902908e-05,
|
| 477 |
+
"loss": 1.1172,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.13,
|
| 482 |
+
"grad_norm": 0.5141753129119535,
|
| 483 |
+
"learning_rate": 9.746660664359326e-05,
|
| 484 |
+
"loss": 1.1172,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.13,
|
| 489 |
+
"grad_norm": 0.46159702650365997,
|
| 490 |
+
"learning_rate": 9.736910329205978e-05,
|
| 491 |
+
"loss": 1.1328,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.13,
|
| 496 |
+
"grad_norm": 0.45575998013176866,
|
| 497 |
+
"learning_rate": 9.726980953363536e-05,
|
| 498 |
+
"loss": 1.1328,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.13,
|
| 503 |
+
"grad_norm": 0.4458400134106401,
|
| 504 |
+
"learning_rate": 9.716872912131964e-05,
|
| 505 |
+
"loss": 1.1172,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.14,
|
| 510 |
+
"grad_norm": 0.4403442516042718,
|
| 511 |
+
"learning_rate": 9.706586587564237e-05,
|
| 512 |
+
"loss": 1.1406,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.14,
|
| 517 |
+
"grad_norm": 0.4513799624319814,
|
| 518 |
+
"learning_rate": 9.696122368451886e-05,
|
| 519 |
+
"loss": 1.1406,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.14,
|
| 524 |
+
"grad_norm": 0.4348698465314392,
|
| 525 |
+
"learning_rate": 9.685480650310318e-05,
|
| 526 |
+
"loss": 1.1641,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.14,
|
| 531 |
+
"grad_norm": 0.4498345537005005,
|
| 532 |
+
"learning_rate": 9.674661835363858e-05,
|
| 533 |
+
"loss": 1.125,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.14,
|
| 538 |
+
"grad_norm": 0.43144309981302603,
|
| 539 |
+
"learning_rate": 9.663666332530541e-05,
|
| 540 |
+
"loss": 1.1172,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.15,
|
| 545 |
+
"grad_norm": 0.4399921408069473,
|
| 546 |
+
"learning_rate": 9.652494557406666e-05,
|
| 547 |
+
"loss": 1.125,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.15,
|
| 552 |
+
"grad_norm": 0.47704120684842194,
|
| 553 |
+
"learning_rate": 9.641146932251089e-05,
|
| 554 |
+
"loss": 1.1328,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.15,
|
| 559 |
+
"grad_norm": 0.44749472258572454,
|
| 560 |
+
"learning_rate": 9.62962388596925e-05,
|
| 561 |
+
"loss": 1.1406,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.15,
|
| 566 |
+
"grad_norm": 0.4413794417064817,
|
| 567 |
+
"learning_rate": 9.617925854096975e-05,
|
| 568 |
+
"loss": 1.1406,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.15,
|
| 573 |
+
"grad_norm": 0.42859705779561913,
|
| 574 |
+
"learning_rate": 9.606053278784009e-05,
|
| 575 |
+
"loss": 1.1172,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.16,
|
| 580 |
+
"grad_norm": 0.45418306254807467,
|
| 581 |
+
"learning_rate": 9.5940066087773e-05,
|
| 582 |
+
"loss": 1.1016,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.16,
|
| 587 |
+
"grad_norm": 0.43688517954319694,
|
| 588 |
+
"learning_rate": 9.581786299404045e-05,
|
| 589 |
+
"loss": 1.1172,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.16,
|
| 594 |
+
"grad_norm": 0.4397567687148274,
|
| 595 |
+
"learning_rate": 9.569392812554478e-05,
|
| 596 |
+
"loss": 1.1172,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.16,
|
| 601 |
+
"grad_norm": 0.46690101219263686,
|
| 602 |
+
"learning_rate": 9.556826616664407e-05,
|
| 603 |
+
"loss": 1.1328,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.16,
|
| 608 |
+
"grad_norm": 0.4756162905348212,
|
| 609 |
+
"learning_rate": 9.544088186697515e-05,
|
| 610 |
+
"loss": 1.1172,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.17,
|
| 615 |
+
"grad_norm": 0.4366895335330985,
|
| 616 |
+
"learning_rate": 9.531178004127403e-05,
|
| 617 |
+
"loss": 1.1172,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.17,
|
| 622 |
+
"grad_norm": 0.46048461137548086,
|
| 623 |
+
"learning_rate": 9.518096556919396e-05,
|
| 624 |
+
"loss": 1.125,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.17,
|
| 629 |
+
"grad_norm": 0.45095033069608803,
|
| 630 |
+
"learning_rate": 9.504844339512095e-05,
|
| 631 |
+
"loss": 1.1016,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.17,
|
| 636 |
+
"grad_norm": 0.440538034417393,
|
| 637 |
+
"learning_rate": 9.491421852798696e-05,
|
| 638 |
+
"loss": 1.1016,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.17,
|
| 643 |
+
"grad_norm": 0.4472029761648666,
|
| 644 |
+
"learning_rate": 9.477829604108044e-05,
|
| 645 |
+
"loss": 1.0938,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.17,
|
| 650 |
+
"grad_norm": 0.4369667303362839,
|
| 651 |
+
"learning_rate": 9.464068107185476e-05,
|
| 652 |
+
"loss": 1.0781,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.18,
|
| 657 |
+
"grad_norm": 0.5249913549114,
|
| 658 |
+
"learning_rate": 9.450137882173384e-05,
|
| 659 |
+
"loss": 1.0703,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.18,
|
| 664 |
+
"grad_norm": 0.4465738523446084,
|
| 665 |
+
"learning_rate": 9.436039455591573e-05,
|
| 666 |
+
"loss": 1.0859,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.18,
|
| 671 |
+
"grad_norm": 0.43766479595594365,
|
| 672 |
+
"learning_rate": 9.421773360317347e-05,
|
| 673 |
+
"loss": 1.1016,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.18,
|
| 678 |
+
"grad_norm": 0.4240043286719592,
|
| 679 |
+
"learning_rate": 9.407340135565374e-05,
|
| 680 |
+
"loss": 1.0938,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.18,
|
| 685 |
+
"grad_norm": 0.42744921800889424,
|
| 686 |
+
"learning_rate": 9.392740326867304e-05,
|
| 687 |
+
"loss": 1.1172,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.19,
|
| 692 |
+
"grad_norm": 0.458478203908347,
|
| 693 |
+
"learning_rate": 9.377974486051147e-05,
|
| 694 |
+
"loss": 1.1172,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.19,
|
| 699 |
+
"grad_norm": 0.4320194692065847,
|
| 700 |
+
"learning_rate": 9.363043171220423e-05,
|
| 701 |
+
"loss": 1.0859,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.19,
|
| 706 |
+
"grad_norm": 0.42941401875819113,
|
| 707 |
+
"learning_rate": 9.347946946733055e-05,
|
| 708 |
+
"loss": 1.0938,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.19,
|
| 713 |
+
"grad_norm": 0.4345817070644086,
|
| 714 |
+
"learning_rate": 9.332686383180055e-05,
|
| 715 |
+
"loss": 1.0781,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.19,
|
| 720 |
+
"grad_norm": 0.42729040555243186,
|
| 721 |
+
"learning_rate": 9.31726205736394e-05,
|
| 722 |
+
"loss": 1.1094,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.2,
|
| 727 |
+
"grad_norm": 0.4676759430208925,
|
| 728 |
+
"learning_rate": 9.301674552276942e-05,
|
| 729 |
+
"loss": 1.0859,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.2,
|
| 734 |
+
"grad_norm": 0.437120596292176,
|
| 735 |
+
"learning_rate": 9.28592445707897e-05,
|
| 736 |
+
"loss": 1.1094,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.2,
|
| 741 |
+
"grad_norm": 0.44408267981562327,
|
| 742 |
+
"learning_rate": 9.270012367075336e-05,
|
| 743 |
+
"loss": 1.1094,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.2,
|
| 748 |
+
"grad_norm": 0.4408320908096716,
|
| 749 |
+
"learning_rate": 9.253938883694267e-05,
|
| 750 |
+
"loss": 1.0859,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.2,
|
| 755 |
+
"grad_norm": 0.4153884549704849,
|
| 756 |
+
"learning_rate": 9.237704614464156e-05,
|
| 757 |
+
"loss": 1.0781,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.2,
|
| 762 |
+
"grad_norm": 0.44536034771337696,
|
| 763 |
+
"learning_rate": 9.221310172990616e-05,
|
| 764 |
+
"loss": 1.0781,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.21,
|
| 769 |
+
"grad_norm": 0.42677756463500066,
|
| 770 |
+
"learning_rate": 9.204756178933274e-05,
|
| 771 |
+
"loss": 1.0703,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.21,
|
| 776 |
+
"grad_norm": 0.4378028436016707,
|
| 777 |
+
"learning_rate": 9.18804325798236e-05,
|
| 778 |
+
"loss": 1.0938,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.21,
|
| 783 |
+
"grad_norm": 0.42237143257723425,
|
| 784 |
+
"learning_rate": 9.17117204183505e-05,
|
| 785 |
+
"loss": 1.1094,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.21,
|
| 790 |
+
"grad_norm": 0.43243228227443636,
|
| 791 |
+
"learning_rate": 9.154143168171592e-05,
|
| 792 |
+
"loss": 1.0859,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.21,
|
| 797 |
+
"grad_norm": 0.41404933017475487,
|
| 798 |
+
"learning_rate": 9.136957280631212e-05,
|
| 799 |
+
"loss": 1.0938,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.22,
|
| 804 |
+
"grad_norm": 0.4409966487573737,
|
| 805 |
+
"learning_rate": 9.119615028787771e-05,
|
| 806 |
+
"loss": 1.0625,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.22,
|
| 811 |
+
"grad_norm": 0.40666941809648666,
|
| 812 |
+
"learning_rate": 9.102117068125226e-05,
|
| 813 |
+
"loss": 1.0703,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.22,
|
| 818 |
+
"grad_norm": 0.4436737155967258,
|
| 819 |
+
"learning_rate": 9.08446406001285e-05,
|
| 820 |
+
"loss": 1.0859,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.22,
|
| 825 |
+
"grad_norm": 0.4274067363700415,
|
| 826 |
+
"learning_rate": 9.06665667168023e-05,
|
| 827 |
+
"loss": 1.0547,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.22,
|
| 832 |
+
"grad_norm": 0.40913040466042055,
|
| 833 |
+
"learning_rate": 9.048695576192058e-05,
|
| 834 |
+
"loss": 1.0625,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.23,
|
| 839 |
+
"grad_norm": 0.4937917107991283,
|
| 840 |
+
"learning_rate": 9.030581452422679e-05,
|
| 841 |
+
"loss": 1.1172,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.23,
|
| 846 |
+
"grad_norm": 0.4404941593953187,
|
| 847 |
+
"learning_rate": 9.012314985030445e-05,
|
| 848 |
+
"loss": 1.0781,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.23,
|
| 853 |
+
"grad_norm": 0.39523077054498146,
|
| 854 |
+
"learning_rate": 8.993896864431826e-05,
|
| 855 |
+
"loss": 1.0625,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.23,
|
| 860 |
+
"grad_norm": 0.4373478392227282,
|
| 861 |
+
"learning_rate": 8.975327786775315e-05,
|
| 862 |
+
"loss": 1.0703,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.23,
|
| 867 |
+
"grad_norm": 0.4577216496829238,
|
| 868 |
+
"learning_rate": 8.956608453915125e-05,
|
| 869 |
+
"loss": 1.1016,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.24,
|
| 874 |
+
"grad_norm": 0.4276538666446135,
|
| 875 |
+
"learning_rate": 8.937739573384653e-05,
|
| 876 |
+
"loss": 1.0781,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.24,
|
| 881 |
+
"grad_norm": 0.4362035096548072,
|
| 882 |
+
"learning_rate": 8.918721858369738e-05,
|
| 883 |
+
"loss": 1.0703,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.24,
|
| 888 |
+
"grad_norm": 0.4493303937073408,
|
| 889 |
+
"learning_rate": 8.899556027681709e-05,
|
| 890 |
+
"loss": 1.0703,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.24,
|
| 895 |
+
"grad_norm": 0.4434149185545328,
|
| 896 |
+
"learning_rate": 8.880242805730208e-05,
|
| 897 |
+
"loss": 1.0938,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.24,
|
| 902 |
+
"grad_norm": 0.43950175470648284,
|
| 903 |
+
"learning_rate": 8.860782922495822e-05,
|
| 904 |
+
"loss": 1.0703,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.24,
|
| 909 |
+
"grad_norm": 0.426071957636363,
|
| 910 |
+
"learning_rate": 8.841177113502482e-05,
|
| 911 |
+
"loss": 1.0703,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.25,
|
| 916 |
+
"grad_norm": 0.450291923405564,
|
| 917 |
+
"learning_rate": 8.821426119789662e-05,
|
| 918 |
+
"loss": 1.0781,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.25,
|
| 923 |
+
"grad_norm": 0.40557626842779504,
|
| 924 |
+
"learning_rate": 8.801530687884378e-05,
|
| 925 |
+
"loss": 1.0781,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.25,
|
| 930 |
+
"grad_norm": 0.4702580576149972,
|
| 931 |
+
"learning_rate": 8.781491569772966e-05,
|
| 932 |
+
"loss": 1.0547,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.25,
|
| 937 |
+
"grad_norm": 0.44111964762493167,
|
| 938 |
+
"learning_rate": 8.761309522872657e-05,
|
| 939 |
+
"loss": 1.0469,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.25,
|
| 944 |
+
"grad_norm": 0.41670105323821127,
|
| 945 |
+
"learning_rate": 8.740985310002956e-05,
|
| 946 |
+
"loss": 1.0859,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.26,
|
| 951 |
+
"grad_norm": 0.4475226900837088,
|
| 952 |
+
"learning_rate": 8.720519699356804e-05,
|
| 953 |
+
"loss": 1.0859,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.26,
|
| 958 |
+
"grad_norm": 0.43566177490537383,
|
| 959 |
+
"learning_rate": 8.699913464471543e-05,
|
| 960 |
+
"loss": 1.0859,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.26,
|
| 965 |
+
"grad_norm": 0.45325103614908197,
|
| 966 |
+
"learning_rate": 8.679167384199684e-05,
|
| 967 |
+
"loss": 1.0625,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.26,
|
| 972 |
+
"grad_norm": 0.42259820068503184,
|
| 973 |
+
"learning_rate": 8.658282242679461e-05,
|
| 974 |
+
"loss": 1.0859,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.26,
|
| 979 |
+
"grad_norm": 0.42782456224560983,
|
| 980 |
+
"learning_rate": 8.637258829305199e-05,
|
| 981 |
+
"loss": 1.0938,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.27,
|
| 986 |
+
"grad_norm": 0.42070148732795626,
|
| 987 |
+
"learning_rate": 8.616097938697475e-05,
|
| 988 |
+
"loss": 1.0859,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.27,
|
| 993 |
+
"grad_norm": 0.4103382323854611,
|
| 994 |
+
"learning_rate": 8.594800370673083e-05,
|
| 995 |
+
"loss": 1.1016,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.27,
|
| 1000 |
+
"grad_norm": 0.4273680868793077,
|
| 1001 |
+
"learning_rate": 8.573366930214806e-05,
|
| 1002 |
+
"loss": 1.0859,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.27,
|
| 1007 |
+
"grad_norm": 0.41570068283778067,
|
| 1008 |
+
"learning_rate": 8.551798427440986e-05,
|
| 1009 |
+
"loss": 1.0469,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.27,
|
| 1014 |
+
"grad_norm": 0.4189560948484794,
|
| 1015 |
+
"learning_rate": 8.53009567757491e-05,
|
| 1016 |
+
"loss": 1.0938,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.28,
|
| 1021 |
+
"grad_norm": 0.40232705129491403,
|
| 1022 |
+
"learning_rate": 8.50825950091399e-05,
|
| 1023 |
+
"loss": 1.0469,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.28,
|
| 1028 |
+
"grad_norm": 0.45728641315276936,
|
| 1029 |
+
"learning_rate": 8.486290722798764e-05,
|
| 1030 |
+
"loss": 1.0625,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.28,
|
| 1035 |
+
"grad_norm": 0.43979948317554834,
|
| 1036 |
+
"learning_rate": 8.464190173581699e-05,
|
| 1037 |
+
"loss": 1.0938,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.28,
|
| 1042 |
+
"grad_norm": 0.4374598465086451,
|
| 1043 |
+
"learning_rate": 8.441958688595801e-05,
|
| 1044 |
+
"loss": 1.0625,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.28,
|
| 1049 |
+
"grad_norm": 0.4352920608233416,
|
| 1050 |
+
"learning_rate": 8.419597108123054e-05,
|
| 1051 |
+
"loss": 1.0547,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.28,
|
| 1056 |
+
"grad_norm": 0.42744190205787813,
|
| 1057 |
+
"learning_rate": 8.397106277362647e-05,
|
| 1058 |
+
"loss": 1.0703,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.29,
|
| 1063 |
+
"grad_norm": 0.6185631612514999,
|
| 1064 |
+
"learning_rate": 8.374487046399036e-05,
|
| 1065 |
+
"loss": 1.0781,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.29,
|
| 1070 |
+
"grad_norm": 0.4214859539037842,
|
| 1071 |
+
"learning_rate": 8.35174027016981e-05,
|
| 1072 |
+
"loss": 1.0703,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.29,
|
| 1077 |
+
"grad_norm": 0.4300234685508506,
|
| 1078 |
+
"learning_rate": 8.328866808433378e-05,
|
| 1079 |
+
"loss": 1.0312,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.29,
|
| 1084 |
+
"grad_norm": 0.4516779428626118,
|
| 1085 |
+
"learning_rate": 8.305867525736474e-05,
|
| 1086 |
+
"loss": 1.0547,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.29,
|
| 1091 |
+
"grad_norm": 0.4444842072606281,
|
| 1092 |
+
"learning_rate": 8.282743291381481e-05,
|
| 1093 |
+
"loss": 1.0703,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.3,
|
| 1098 |
+
"grad_norm": 0.44891341810235713,
|
| 1099 |
+
"learning_rate": 8.259494979393563e-05,
|
| 1100 |
+
"loss": 1.0469,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.3,
|
| 1105 |
+
"grad_norm": 0.4403106392279916,
|
| 1106 |
+
"learning_rate": 8.236123468487648e-05,
|
| 1107 |
+
"loss": 1.0703,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.3,
|
| 1112 |
+
"grad_norm": 0.4558686783543436,
|
| 1113 |
+
"learning_rate": 8.212629642035199e-05,
|
| 1114 |
+
"loss": 1.0547,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3,
|
| 1119 |
+
"grad_norm": 0.47853095524964395,
|
| 1120 |
+
"learning_rate": 8.189014388030833e-05,
|
| 1121 |
+
"loss": 1.0859,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.3,
|
| 1126 |
+
"grad_norm": 0.454113313074197,
|
| 1127 |
+
"learning_rate": 8.165278599058761e-05,
|
| 1128 |
+
"loss": 1.0547,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.31,
|
| 1133 |
+
"grad_norm": 0.4406670018539545,
|
| 1134 |
+
"learning_rate": 8.141423172259038e-05,
|
| 1135 |
+
"loss": 1.0859,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.31,
|
| 1140 |
+
"grad_norm": 0.434252392773616,
|
| 1141 |
+
"learning_rate": 8.117449009293668e-05,
|
| 1142 |
+
"loss": 1.0547,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.31,
|
| 1147 |
+
"grad_norm": 0.44488081257640494,
|
| 1148 |
+
"learning_rate": 8.093357016312517e-05,
|
| 1149 |
+
"loss": 1.0703,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.31,
|
| 1154 |
+
"grad_norm": 0.4291046723882578,
|
| 1155 |
+
"learning_rate": 8.069148103919064e-05,
|
| 1156 |
+
"loss": 1.0703,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.31,
|
| 1161 |
+
"grad_norm": 0.4701461632642551,
|
| 1162 |
+
"learning_rate": 8.044823187135984e-05,
|
| 1163 |
+
"loss": 1.0703,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.31,
|
| 1168 |
+
"grad_norm": 0.41504338561910276,
|
| 1169 |
+
"learning_rate": 8.020383185370559e-05,
|
| 1170 |
+
"loss": 1.0469,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.32,
|
| 1175 |
+
"grad_norm": 0.43178723119245843,
|
| 1176 |
+
"learning_rate": 7.995829022379936e-05,
|
| 1177 |
+
"loss": 1.0703,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.32,
|
| 1182 |
+
"grad_norm": 0.4204377336860703,
|
| 1183 |
+
"learning_rate": 7.9711616262362e-05,
|
| 1184 |
+
"loss": 1.0547,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.32,
|
| 1189 |
+
"grad_norm": 0.4407346163963636,
|
| 1190 |
+
"learning_rate": 7.94638192929131e-05,
|
| 1191 |
+
"loss": 1.0703,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.32,
|
| 1196 |
+
"grad_norm": 0.4264303388977427,
|
| 1197 |
+
"learning_rate": 7.921490868141843e-05,
|
| 1198 |
+
"loss": 1.0391,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.32,
|
| 1203 |
+
"grad_norm": 0.40640791387915454,
|
| 1204 |
+
"learning_rate": 7.896489383593606e-05,
|
| 1205 |
+
"loss": 1.0,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.33,
|
| 1210 |
+
"grad_norm": 0.43144011890160755,
|
| 1211 |
+
"learning_rate": 7.871378420626072e-05,
|
| 1212 |
+
"loss": 1.0547,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.33,
|
| 1217 |
+
"grad_norm": 0.4744375892527014,
|
| 1218 |
+
"learning_rate": 7.84615892835666e-05,
|
| 1219 |
+
"loss": 1.0391,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.33,
|
| 1224 |
+
"grad_norm": 0.4414917687031027,
|
| 1225 |
+
"learning_rate": 7.820831860004867e-05,
|
| 1226 |
+
"loss": 1.0391,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.33,
|
| 1231 |
+
"grad_norm": 0.43753081136596556,
|
| 1232 |
+
"learning_rate": 7.795398172856233e-05,
|
| 1233 |
+
"loss": 1.0391,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.33,
|
| 1238 |
+
"grad_norm": 0.44688090549658416,
|
| 1239 |
+
"learning_rate": 7.769858828226164e-05,
|
| 1240 |
+
"loss": 1.0859,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.34,
|
| 1245 |
+
"grad_norm": 0.4324472242080182,
|
| 1246 |
+
"learning_rate": 7.744214791423596e-05,
|
| 1247 |
+
"loss": 1.0781,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.34,
|
| 1252 |
+
"grad_norm": 0.39471909710720243,
|
| 1253 |
+
"learning_rate": 7.718467031714506e-05,
|
| 1254 |
+
"loss": 1.0938,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.34,
|
| 1259 |
+
"grad_norm": 0.42273379977293096,
|
| 1260 |
+
"learning_rate": 7.692616522285278e-05,
|
| 1261 |
+
"loss": 1.0703,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.34,
|
| 1266 |
+
"grad_norm": 0.41049110470779143,
|
| 1267 |
+
"learning_rate": 7.666664240205922e-05,
|
| 1268 |
+
"loss": 1.0469,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.34,
|
| 1273 |
+
"grad_norm": 0.4309053261577172,
|
| 1274 |
+
"learning_rate": 7.640611166393141e-05,
|
| 1275 |
+
"loss": 1.0547,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.35,
|
| 1280 |
+
"grad_norm": 0.4297343270635459,
|
| 1281 |
+
"learning_rate": 7.614458285573261e-05,
|
| 1282 |
+
"loss": 1.0547,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.35,
|
| 1287 |
+
"grad_norm": 0.42742054343292596,
|
| 1288 |
+
"learning_rate": 7.588206586245002e-05,
|
| 1289 |
+
"loss": 1.0469,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.35,
|
| 1294 |
+
"grad_norm": 0.4332643732697325,
|
| 1295 |
+
"learning_rate": 7.56185706064212e-05,
|
| 1296 |
+
"loss": 1.0391,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.35,
|
| 1301 |
+
"grad_norm": 0.42811233809608473,
|
| 1302 |
+
"learning_rate": 7.535410704695906e-05,
|
| 1303 |
+
"loss": 1.0469,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.35,
|
| 1308 |
+
"grad_norm": 0.4489861675889494,
|
| 1309 |
+
"learning_rate": 7.508868517997544e-05,
|
| 1310 |
+
"loss": 1.0312,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.35,
|
| 1315 |
+
"grad_norm": 0.4205028088463761,
|
| 1316 |
+
"learning_rate": 7.482231503760325e-05,
|
| 1317 |
+
"loss": 1.0469,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.36,
|
| 1322 |
+
"grad_norm": 0.41000506415552723,
|
| 1323 |
+
"learning_rate": 7.455500668781726e-05,
|
| 1324 |
+
"loss": 1.0547,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.36,
|
| 1329 |
+
"grad_norm": 0.41183736439865304,
|
| 1330 |
+
"learning_rate": 7.428677023405366e-05,
|
| 1331 |
+
"loss": 1.0547,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.36,
|
| 1336 |
+
"grad_norm": 0.4246427305638071,
|
| 1337 |
+
"learning_rate": 7.40176158148281e-05,
|
| 1338 |
+
"loss": 1.0625,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.36,
|
| 1343 |
+
"grad_norm": 0.43275232447123674,
|
| 1344 |
+
"learning_rate": 7.374755360335253e-05,
|
| 1345 |
+
"loss": 1.0469,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.36,
|
| 1350 |
+
"grad_norm": 0.42692084681273973,
|
| 1351 |
+
"learning_rate": 7.347659380715061e-05,
|
| 1352 |
+
"loss": 1.0234,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.37,
|
| 1357 |
+
"grad_norm": 0.4311244552583607,
|
| 1358 |
+
"learning_rate": 7.320474666767201e-05,
|
| 1359 |
+
"loss": 1.0234,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.37,
|
| 1364 |
+
"grad_norm": 0.42719595530993326,
|
| 1365 |
+
"learning_rate": 7.293202245990526e-05,
|
| 1366 |
+
"loss": 1.0469,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.37,
|
| 1371 |
+
"grad_norm": 0.4174615425446307,
|
| 1372 |
+
"learning_rate": 7.265843149198931e-05,
|
| 1373 |
+
"loss": 1.0547,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.37,
|
| 1378 |
+
"grad_norm": 0.42222785480422026,
|
| 1379 |
+
"learning_rate": 7.238398410482408e-05,
|
| 1380 |
+
"loss": 1.0547,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.37,
|
| 1385 |
+
"grad_norm": 0.4157306068460529,
|
| 1386 |
+
"learning_rate": 7.210869067167942e-05,
|
| 1387 |
+
"loss": 1.0234,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.38,
|
| 1392 |
+
"grad_norm": 0.4241319467586246,
|
| 1393 |
+
"learning_rate": 7.18325615978032e-05,
|
| 1394 |
+
"loss": 1.0625,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.38,
|
| 1399 |
+
"grad_norm": 0.4087921332041852,
|
| 1400 |
+
"learning_rate": 7.155560732002791e-05,
|
| 1401 |
+
"loss": 1.0391,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.38,
|
| 1406 |
+
"grad_norm": 0.426858061802629,
|
| 1407 |
+
"learning_rate": 7.127783830637625e-05,
|
| 1408 |
+
"loss": 1.0469,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.38,
|
| 1413 |
+
"grad_norm": 0.41722790561085193,
|
| 1414 |
+
"learning_rate": 7.099926505566537e-05,
|
| 1415 |
+
"loss": 1.0469,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.38,
|
| 1420 |
+
"grad_norm": 0.4199601470491497,
|
| 1421 |
+
"learning_rate": 7.071989809711019e-05,
|
| 1422 |
+
"loss": 1.0547,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.39,
|
| 1427 |
+
"grad_norm": 0.44231292212761336,
|
| 1428 |
+
"learning_rate": 7.043974798992532e-05,
|
| 1429 |
+
"loss": 1.0547,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.39,
|
| 1434 |
+
"grad_norm": 0.40964479400554343,
|
| 1435 |
+
"learning_rate": 7.015882532292598e-05,
|
| 1436 |
+
"loss": 1.0547,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.39,
|
| 1441 |
+
"grad_norm": 0.41103344664490243,
|
| 1442 |
+
"learning_rate": 6.98771407141278e-05,
|
| 1443 |
+
"loss": 1.0391,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.39,
|
| 1448 |
+
"grad_norm": 0.418536368662017,
|
| 1449 |
+
"learning_rate": 6.959470481034547e-05,
|
| 1450 |
+
"loss": 1.0391,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.39,
|
| 1455 |
+
"grad_norm": 0.43983351138714233,
|
| 1456 |
+
"learning_rate": 6.931152828679033e-05,
|
| 1457 |
+
"loss": 1.0312,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.39,
|
| 1462 |
+
"grad_norm": 0.4167726489287608,
|
| 1463 |
+
"learning_rate": 6.902762184666687e-05,
|
| 1464 |
+
"loss": 1.0234,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.4,
|
| 1469 |
+
"grad_norm": 0.42759288997893236,
|
| 1470 |
+
"learning_rate": 6.874299622076816e-05,
|
| 1471 |
+
"loss": 1.0625,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.4,
|
| 1476 |
+
"grad_norm": 0.4163882383830232,
|
| 1477 |
+
"learning_rate": 6.845766216707037e-05,
|
| 1478 |
+
"loss": 1.0469,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.4,
|
| 1483 |
+
"grad_norm": 0.40983190994051244,
|
| 1484 |
+
"learning_rate": 6.817163047032598e-05,
|
| 1485 |
+
"loss": 1.0234,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.4,
|
| 1490 |
+
"grad_norm": 0.40059171202862986,
|
| 1491 |
+
"learning_rate": 6.78849119416563e-05,
|
| 1492 |
+
"loss": 1.0156,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.4,
|
| 1497 |
+
"grad_norm": 0.4187064398891471,
|
| 1498 |
+
"learning_rate": 6.759751741814271e-05,
|
| 1499 |
+
"loss": 1.0469,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.41,
|
| 1504 |
+
"grad_norm": 0.42319499896716717,
|
| 1505 |
+
"learning_rate": 6.730945776241722e-05,
|
| 1506 |
+
"loss": 1.0234,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.41,
|
| 1511 |
+
"grad_norm": 0.43680930005688956,
|
| 1512 |
+
"learning_rate": 6.702074386225175e-05,
|
| 1513 |
+
"loss": 1.0469,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.41,
|
| 1518 |
+
"grad_norm": 0.4108033837354488,
|
| 1519 |
+
"learning_rate": 6.67313866301466e-05,
|
| 1520 |
+
"loss": 1.0469,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.41,
|
| 1525 |
+
"grad_norm": 0.40903728151823127,
|
| 1526 |
+
"learning_rate": 6.644139700291817e-05,
|
| 1527 |
+
"loss": 1.0469,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.41,
|
| 1532 |
+
"grad_norm": 0.40715077992299514,
|
| 1533 |
+
"learning_rate": 6.615078594128531e-05,
|
| 1534 |
+
"loss": 1.0703,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.42,
|
| 1539 |
+
"grad_norm": 0.41322957469383936,
|
| 1540 |
+
"learning_rate": 6.585956442945532e-05,
|
| 1541 |
+
"loss": 1.0234,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.42,
|
| 1546 |
+
"grad_norm": 0.421602554588443,
|
| 1547 |
+
"learning_rate": 6.556774347470855e-05,
|
| 1548 |
+
"loss": 1.0625,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.42,
|
| 1553 |
+
"grad_norm": 0.4246703826676253,
|
| 1554 |
+
"learning_rate": 6.52753341069825e-05,
|
| 1555 |
+
"loss": 1.0391,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.42,
|
| 1560 |
+
"grad_norm": 0.4277032038662427,
|
| 1561 |
+
"learning_rate": 6.498234737845488e-05,
|
| 1562 |
+
"loss": 1.0234,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.42,
|
| 1567 |
+
"grad_norm": 0.40733604211970925,
|
| 1568 |
+
"learning_rate": 6.468879436312584e-05,
|
| 1569 |
+
"loss": 1.0547,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.43,
|
| 1574 |
+
"grad_norm": 0.41272813606786746,
|
| 1575 |
+
"learning_rate": 6.439468615639946e-05,
|
| 1576 |
+
"loss": 1.0625,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.43,
|
| 1581 |
+
"grad_norm": 0.40178981821143017,
|
| 1582 |
+
"learning_rate": 6.410003387466433e-05,
|
| 1583 |
+
"loss": 1.0234,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.43,
|
| 1588 |
+
"grad_norm": 0.4153854554817549,
|
| 1589 |
+
"learning_rate": 6.380484865487347e-05,
|
| 1590 |
+
"loss": 1.0391,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.43,
|
| 1595 |
+
"grad_norm": 0.40755934293498974,
|
| 1596 |
+
"learning_rate": 6.35091416541232e-05,
|
| 1597 |
+
"loss": 1.0391,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.43,
|
| 1602 |
+
"grad_norm": 0.41967206872870166,
|
| 1603 |
+
"learning_rate": 6.321292404923167e-05,
|
| 1604 |
+
"loss": 1.0703,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.43,
|
| 1609 |
+
"grad_norm": 0.4017640092647761,
|
| 1610 |
+
"learning_rate": 6.29162070363163e-05,
|
| 1611 |
+
"loss": 1.0625,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.44,
|
| 1616 |
+
"grad_norm": 0.39890051372690344,
|
| 1617 |
+
"learning_rate": 6.261900183037052e-05,
|
| 1618 |
+
"loss": 1.0312,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.44,
|
| 1623 |
+
"grad_norm": 0.4036725539891162,
|
| 1624 |
+
"learning_rate": 6.232131966484006e-05,
|
| 1625 |
+
"loss": 1.0312,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.44,
|
| 1630 |
+
"grad_norm": 0.4122985901559554,
|
| 1631 |
+
"learning_rate": 6.202317179119817e-05,
|
| 1632 |
+
"loss": 1.0156,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.44,
|
| 1637 |
+
"grad_norm": 0.4113133842869648,
|
| 1638 |
+
"learning_rate": 6.172456947852049e-05,
|
| 1639 |
+
"loss": 1.0469,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.44,
|
| 1644 |
+
"grad_norm": 0.4028322239410973,
|
| 1645 |
+
"learning_rate": 6.142552401305906e-05,
|
| 1646 |
+
"loss": 1.0469,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.45,
|
| 1651 |
+
"grad_norm": 0.4077613734483574,
|
| 1652 |
+
"learning_rate": 6.112604669781572e-05,
|
| 1653 |
+
"loss": 1.0391,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.45,
|
| 1658 |
+
"grad_norm": 0.40208253242419867,
|
| 1659 |
+
"learning_rate": 6.0826148852114936e-05,
|
| 1660 |
+
"loss": 1.0469,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.45,
|
| 1665 |
+
"grad_norm": 0.39795754759528085,
|
| 1666 |
+
"learning_rate": 6.052584181117589e-05,
|
| 1667 |
+
"loss": 1.0469,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.45,
|
| 1672 |
+
"grad_norm": 0.40763706027293223,
|
| 1673 |
+
"learning_rate": 6.022513692568412e-05,
|
| 1674 |
+
"loss": 1.0625,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.45,
|
| 1679 |
+
"grad_norm": 0.4296039465981587,
|
| 1680 |
+
"learning_rate": 5.9924045561362474e-05,
|
| 1681 |
+
"loss": 1.0391,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.46,
|
| 1686 |
+
"grad_norm": 0.4070047169709585,
|
| 1687 |
+
"learning_rate": 5.96225790985415e-05,
|
| 1688 |
+
"loss": 1.0547,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.46,
|
| 1693 |
+
"grad_norm": 0.41013474576772757,
|
| 1694 |
+
"learning_rate": 5.9320748931729344e-05,
|
| 1695 |
+
"loss": 1.0156,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.46,
|
| 1700 |
+
"grad_norm": 0.40322499716017,
|
| 1701 |
+
"learning_rate": 5.9018566469180994e-05,
|
| 1702 |
+
"loss": 1.0391,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.46,
|
| 1707 |
+
"grad_norm": 0.3898763992841581,
|
| 1708 |
+
"learning_rate": 5.87160431324672e-05,
|
| 1709 |
+
"loss": 1.0156,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.46,
|
| 1714 |
+
"grad_norm": 0.42982455700255084,
|
| 1715 |
+
"learning_rate": 5.841319035604267e-05,
|
| 1716 |
+
"loss": 1.0625,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.46,
|
| 1721 |
+
"grad_norm": 0.4040478163311833,
|
| 1722 |
+
"learning_rate": 5.8110019586813946e-05,
|
| 1723 |
+
"loss": 0.9961,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.47,
|
| 1728 |
+
"grad_norm": 0.40273222517295776,
|
| 1729 |
+
"learning_rate": 5.780654228370669e-05,
|
| 1730 |
+
"loss": 1.0234,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.47,
|
| 1735 |
+
"grad_norm": 0.40974932826857524,
|
| 1736 |
+
"learning_rate": 5.7502769917232635e-05,
|
| 1737 |
+
"loss": 1.0156,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.47,
|
| 1742 |
+
"grad_norm": 0.39928761514091116,
|
| 1743 |
+
"learning_rate": 5.7198713969056026e-05,
|
| 1744 |
+
"loss": 1.0234,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.47,
|
| 1749 |
+
"grad_norm": 0.41874763062357806,
|
| 1750 |
+
"learning_rate": 5.689438593155956e-05,
|
| 1751 |
+
"loss": 1.0312,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.47,
|
| 1756 |
+
"grad_norm": 0.4493892592268143,
|
| 1757 |
+
"learning_rate": 5.658979730741014e-05,
|
| 1758 |
+
"loss": 1.0547,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.48,
|
| 1763 |
+
"grad_norm": 0.40018316116952474,
|
| 1764 |
+
"learning_rate": 5.6284959609124e-05,
|
| 1765 |
+
"loss": 1.0469,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.48,
|
| 1770 |
+
"grad_norm": 0.43858332707717207,
|
| 1771 |
+
"learning_rate": 5.597988435863166e-05,
|
| 1772 |
+
"loss": 1.0312,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.48,
|
| 1777 |
+
"grad_norm": 0.40836711063525477,
|
| 1778 |
+
"learning_rate": 5.567458308684232e-05,
|
| 1779 |
+
"loss": 1.0547,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.48,
|
| 1784 |
+
"grad_norm": 0.42292844222040155,
|
| 1785 |
+
"learning_rate": 5.536906733320816e-05,
|
| 1786 |
+
"loss": 1.0156,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.48,
|
| 1791 |
+
"grad_norm": 0.41490508684177924,
|
| 1792 |
+
"learning_rate": 5.506334864528808e-05,
|
| 1793 |
+
"loss": 1.0234,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.49,
|
| 1798 |
+
"grad_norm": 0.4058447957006835,
|
| 1799 |
+
"learning_rate": 5.475743857831127e-05,
|
| 1800 |
+
"loss": 1.0156,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.49,
|
| 1805 |
+
"grad_norm": 0.4254621460881678,
|
| 1806 |
+
"learning_rate": 5.445134869474049e-05,
|
| 1807 |
+
"loss": 1.0391,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.49,
|
| 1812 |
+
"grad_norm": 0.4075861687227603,
|
| 1813 |
+
"learning_rate": 5.414509056383498e-05,
|
| 1814 |
+
"loss": 1.0078,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.49,
|
| 1819 |
+
"grad_norm": 0.40610391261853535,
|
| 1820 |
+
"learning_rate": 5.3838675761213244e-05,
|
| 1821 |
+
"loss": 1.0547,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.49,
|
| 1826 |
+
"grad_norm": 0.38922815015134116,
|
| 1827 |
+
"learning_rate": 5.3532115868415464e-05,
|
| 1828 |
+
"loss": 1.0078,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.5,
|
| 1833 |
+
"grad_norm": 0.4046852521792458,
|
| 1834 |
+
"learning_rate": 5.3225422472465824e-05,
|
| 1835 |
+
"loss": 1.0078,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.5,
|
| 1840 |
+
"grad_norm": 0.40728479784786964,
|
| 1841 |
+
"learning_rate": 5.29186071654345e-05,
|
| 1842 |
+
"loss": 0.9648,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.5,
|
| 1847 |
+
"grad_norm": 0.41255158343952975,
|
| 1848 |
+
"learning_rate": 5.261168154399952e-05,
|
| 1849 |
+
"loss": 1.0234,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.5,
|
| 1854 |
+
"grad_norm": 0.4028183441362248,
|
| 1855 |
+
"learning_rate": 5.23046572090085e-05,
|
| 1856 |
+
"loss": 1.0078,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.5,
|
| 1861 |
+
"grad_norm": 0.40792031816309837,
|
| 1862 |
+
"learning_rate": 5.199754576504006e-05,
|
| 1863 |
+
"loss": 1.0078,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.5,
|
| 1868 |
+
"grad_norm": 0.4089443562798811,
|
| 1869 |
+
"learning_rate": 5.169035881996533e-05,
|
| 1870 |
+
"loss": 1.0312,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.51,
|
| 1875 |
+
"grad_norm": 0.40684122314346166,
|
| 1876 |
+
"learning_rate": 5.138310798450912e-05,
|
| 1877 |
+
"loss": 1.0312,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.51,
|
| 1882 |
+
"grad_norm": 0.40867014012821695,
|
| 1883 |
+
"learning_rate": 5.1075804871811115e-05,
|
| 1884 |
+
"loss": 1.0312,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.51,
|
| 1889 |
+
"grad_norm": 0.40061062002695064,
|
| 1890 |
+
"learning_rate": 5.076846109698693e-05,
|
| 1891 |
+
"loss": 1.0547,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.51,
|
| 1896 |
+
"grad_norm": 0.423175226061232,
|
| 1897 |
+
"learning_rate": 5.046108827668903e-05,
|
| 1898 |
+
"loss": 1.0469,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.51,
|
| 1903 |
+
"grad_norm": 0.3898202650786047,
|
| 1904 |
+
"learning_rate": 5.01536980286678e-05,
|
| 1905 |
+
"loss": 1.0156,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.52,
|
| 1910 |
+
"grad_norm": 0.411610879755615,
|
| 1911 |
+
"learning_rate": 4.9846301971332234e-05,
|
| 1912 |
+
"loss": 0.9883,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.52,
|
| 1917 |
+
"grad_norm": 0.39055415860483883,
|
| 1918 |
+
"learning_rate": 4.9538911723310976e-05,
|
| 1919 |
+
"loss": 1.0156,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.52,
|
| 1924 |
+
"grad_norm": 0.4259500716874186,
|
| 1925 |
+
"learning_rate": 4.92315389030131e-05,
|
| 1926 |
+
"loss": 1.0391,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.52,
|
| 1931 |
+
"grad_norm": 0.39261415846035824,
|
| 1932 |
+
"learning_rate": 4.892419512818889e-05,
|
| 1933 |
+
"loss": 1.0312,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.52,
|
| 1938 |
+
"grad_norm": 0.4217477527558212,
|
| 1939 |
+
"learning_rate": 4.86168920154909e-05,
|
| 1940 |
+
"loss": 0.9922,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.53,
|
| 1945 |
+
"grad_norm": 0.38700415086180145,
|
| 1946 |
+
"learning_rate": 4.830964118003468e-05,
|
| 1947 |
+
"loss": 1.0,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.53,
|
| 1952 |
+
"grad_norm": 0.40332274074495494,
|
| 1953 |
+
"learning_rate": 4.800245423495997e-05,
|
| 1954 |
+
"loss": 1.0,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.53,
|
| 1959 |
+
"grad_norm": 0.41396865993704085,
|
| 1960 |
+
"learning_rate": 4.769534279099152e-05,
|
| 1961 |
+
"loss": 1.0078,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.53,
|
| 1966 |
+
"grad_norm": 0.4041936351639291,
|
| 1967 |
+
"learning_rate": 4.7388318456000496e-05,
|
| 1968 |
+
"loss": 1.0078,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.53,
|
| 1973 |
+
"grad_norm": 0.4270421784351172,
|
| 1974 |
+
"learning_rate": 4.708139283456551e-05,
|
| 1975 |
+
"loss": 1.0625,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.54,
|
| 1980 |
+
"grad_norm": 0.4028939120443396,
|
| 1981 |
+
"learning_rate": 4.6774577527534195e-05,
|
| 1982 |
+
"loss": 1.0234,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.54,
|
| 1987 |
+
"grad_norm": 0.40455125854222046,
|
| 1988 |
+
"learning_rate": 4.646788413158455e-05,
|
| 1989 |
+
"loss": 1.0469,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.54,
|
| 1994 |
+
"grad_norm": 0.4058895633541385,
|
| 1995 |
+
"learning_rate": 4.616132423878679e-05,
|
| 1996 |
+
"loss": 1.0391,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.54,
|
| 2001 |
+
"grad_norm": 0.3942526283657809,
|
| 2002 |
+
"learning_rate": 4.585490943616504e-05,
|
| 2003 |
+
"loss": 1.0156,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.54,
|
| 2008 |
+
"grad_norm": 0.40351277549494935,
|
| 2009 |
+
"learning_rate": 4.554865130525953e-05,
|
| 2010 |
+
"loss": 1.0156,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.54,
|
| 2015 |
+
"grad_norm": 0.39184809982008023,
|
| 2016 |
+
"learning_rate": 4.524256142168874e-05,
|
| 2017 |
+
"loss": 1.0156,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.55,
|
| 2022 |
+
"grad_norm": 0.4006543568884177,
|
| 2023 |
+
"learning_rate": 4.4936651354711946e-05,
|
| 2024 |
+
"loss": 0.9727,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.55,
|
| 2029 |
+
"grad_norm": 0.4256220682218964,
|
| 2030 |
+
"learning_rate": 4.463093266679185e-05,
|
| 2031 |
+
"loss": 1.0156,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.55,
|
| 2036 |
+
"grad_norm": 0.3959597237885138,
|
| 2037 |
+
"learning_rate": 4.4325416913157704e-05,
|
| 2038 |
+
"loss": 1.0078,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.55,
|
| 2043 |
+
"grad_norm": 0.4191614983510994,
|
| 2044 |
+
"learning_rate": 4.402011564136836e-05,
|
| 2045 |
+
"loss": 1.0,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.55,
|
| 2050 |
+
"grad_norm": 0.41102487050201564,
|
| 2051 |
+
"learning_rate": 4.371504039087602e-05,
|
| 2052 |
+
"loss": 1.0156,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.56,
|
| 2057 |
+
"grad_norm": 0.43350039494098586,
|
| 2058 |
+
"learning_rate": 4.341020269258987e-05,
|
| 2059 |
+
"loss": 1.0078,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.56,
|
| 2064 |
+
"grad_norm": 0.3956163702456906,
|
| 2065 |
+
"learning_rate": 4.310561406844045e-05,
|
| 2066 |
+
"loss": 1.0078,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.56,
|
| 2071 |
+
"grad_norm": 0.40529243964979217,
|
| 2072 |
+
"learning_rate": 4.2801286030943985e-05,
|
| 2073 |
+
"loss": 1.0,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.56,
|
| 2078 |
+
"grad_norm": 0.4184379424977412,
|
| 2079 |
+
"learning_rate": 4.249723008276737e-05,
|
| 2080 |
+
"loss": 1.0078,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.56,
|
| 2085 |
+
"grad_norm": 0.3971028781090587,
|
| 2086 |
+
"learning_rate": 4.219345771629333e-05,
|
| 2087 |
+
"loss": 1.0156,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.57,
|
| 2092 |
+
"grad_norm": 0.4124935318732211,
|
| 2093 |
+
"learning_rate": 4.188998041318608e-05,
|
| 2094 |
+
"loss": 1.0078,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.57,
|
| 2099 |
+
"grad_norm": 0.38790648111231085,
|
| 2100 |
+
"learning_rate": 4.1586809643957345e-05,
|
| 2101 |
+
"loss": 1.0,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.57,
|
| 2106 |
+
"grad_norm": 0.40687278861829684,
|
| 2107 |
+
"learning_rate": 4.128395686753282e-05,
|
| 2108 |
+
"loss": 1.0312,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.57,
|
| 2113 |
+
"grad_norm": 0.3842187210077263,
|
| 2114 |
+
"learning_rate": 4.098143353081902e-05,
|
| 2115 |
+
"loss": 1.0078,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.57,
|
| 2120 |
+
"grad_norm": 0.4023673478113215,
|
| 2121 |
+
"learning_rate": 4.067925106827068e-05,
|
| 2122 |
+
"loss": 1.0156,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.57,
|
| 2127 |
+
"grad_norm": 0.40540929917797186,
|
| 2128 |
+
"learning_rate": 4.0377420901458506e-05,
|
| 2129 |
+
"loss": 1.0469,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.58,
|
| 2134 |
+
"grad_norm": 0.3923349737804049,
|
| 2135 |
+
"learning_rate": 4.0075954438637545e-05,
|
| 2136 |
+
"loss": 1.0,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.58,
|
| 2141 |
+
"grad_norm": 0.41558812455430966,
|
| 2142 |
+
"learning_rate": 3.977486307431589e-05,
|
| 2143 |
+
"loss": 1.0078,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.58,
|
| 2148 |
+
"grad_norm": 0.40891549560712703,
|
| 2149 |
+
"learning_rate": 3.947415818882414e-05,
|
| 2150 |
+
"loss": 1.0391,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.58,
|
| 2155 |
+
"grad_norm": 0.38609997258343076,
|
| 2156 |
+
"learning_rate": 3.9173851147885075e-05,
|
| 2157 |
+
"loss": 1.0312,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.58,
|
| 2162 |
+
"grad_norm": 0.3906811392128105,
|
| 2163 |
+
"learning_rate": 3.887395330218429e-05,
|
| 2164 |
+
"loss": 1.0156,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.59,
|
| 2169 |
+
"grad_norm": 0.4108545484386376,
|
| 2170 |
+
"learning_rate": 3.857447598694094e-05,
|
| 2171 |
+
"loss": 0.9922,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.59,
|
| 2176 |
+
"grad_norm": 0.40531422168101394,
|
| 2177 |
+
"learning_rate": 3.827543052147952e-05,
|
| 2178 |
+
"loss": 1.0078,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.59,
|
| 2183 |
+
"grad_norm": 0.3991587404518294,
|
| 2184 |
+
"learning_rate": 3.797682820880184e-05,
|
| 2185 |
+
"loss": 0.9961,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.59,
|
| 2190 |
+
"grad_norm": 0.41113645678509786,
|
| 2191 |
+
"learning_rate": 3.7678680335159954e-05,
|
| 2192 |
+
"loss": 1.0156,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.59,
|
| 2197 |
+
"grad_norm": 0.4038074947234651,
|
| 2198 |
+
"learning_rate": 3.7380998169629476e-05,
|
| 2199 |
+
"loss": 1.0312,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.6,
|
| 2204 |
+
"grad_norm": 0.3853125109344581,
|
| 2205 |
+
"learning_rate": 3.708379296368372e-05,
|
| 2206 |
+
"loss": 1.0234,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.6,
|
| 2211 |
+
"grad_norm": 0.4104650046809597,
|
| 2212 |
+
"learning_rate": 3.678707595076834e-05,
|
| 2213 |
+
"loss": 0.9922,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.6,
|
| 2218 |
+
"grad_norm": 0.39375524771920445,
|
| 2219 |
+
"learning_rate": 3.649085834587683e-05,
|
| 2220 |
+
"loss": 1.0156,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.6,
|
| 2225 |
+
"grad_norm": 0.40077662746048126,
|
| 2226 |
+
"learning_rate": 3.619515134512656e-05,
|
| 2227 |
+
"loss": 1.0156,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.6,
|
| 2232 |
+
"grad_norm": 0.38214253590604597,
|
| 2233 |
+
"learning_rate": 3.589996612533568e-05,
|
| 2234 |
+
"loss": 1.0156,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.61,
|
| 2239 |
+
"grad_norm": 0.4009148055080218,
|
| 2240 |
+
"learning_rate": 3.560531384360055e-05,
|
| 2241 |
+
"loss": 1.0078,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.61,
|
| 2246 |
+
"grad_norm": 0.41232895347465953,
|
| 2247 |
+
"learning_rate": 3.531120563687419e-05,
|
| 2248 |
+
"loss": 1.0469,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.61,
|
| 2253 |
+
"grad_norm": 0.38911553214208094,
|
| 2254 |
+
"learning_rate": 3.501765262154513e-05,
|
| 2255 |
+
"loss": 1.0078,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.61,
|
| 2260 |
+
"grad_norm": 0.4093791732496366,
|
| 2261 |
+
"learning_rate": 3.472466589301751e-05,
|
| 2262 |
+
"loss": 0.9766,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.61,
|
| 2267 |
+
"grad_norm": 0.3850449300702058,
|
| 2268 |
+
"learning_rate": 3.4432256525291465e-05,
|
| 2269 |
+
"loss": 0.9883,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.61,
|
| 2274 |
+
"grad_norm": 0.3889336160040775,
|
| 2275 |
+
"learning_rate": 3.41404355705447e-05,
|
| 2276 |
+
"loss": 0.9766,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.62,
|
| 2281 |
+
"grad_norm": 0.4084726866306118,
|
| 2282 |
+
"learning_rate": 3.3849214058714704e-05,
|
| 2283 |
+
"loss": 1.0156,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.62,
|
| 2288 |
+
"grad_norm": 0.4014871038120363,
|
| 2289 |
+
"learning_rate": 3.3558602997081866e-05,
|
| 2290 |
+
"loss": 1.0156,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.62,
|
| 2295 |
+
"grad_norm": 0.4266625922630768,
|
| 2296 |
+
"learning_rate": 3.326861336985341e-05,
|
| 2297 |
+
"loss": 1.0391,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.62,
|
| 2302 |
+
"grad_norm": 0.396771175025528,
|
| 2303 |
+
"learning_rate": 3.297925613774828e-05,
|
| 2304 |
+
"loss": 1.0078,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.62,
|
| 2309 |
+
"grad_norm": 0.4417896085826512,
|
| 2310 |
+
"learning_rate": 3.269054223758279e-05,
|
| 2311 |
+
"loss": 0.9922,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.63,
|
| 2316 |
+
"grad_norm": 0.3809941597462593,
|
| 2317 |
+
"learning_rate": 3.240248258185731e-05,
|
| 2318 |
+
"loss": 0.9961,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.63,
|
| 2323 |
+
"grad_norm": 0.4074336906480307,
|
| 2324 |
+
"learning_rate": 3.2115088058343725e-05,
|
| 2325 |
+
"loss": 0.9922,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.63,
|
| 2330 |
+
"grad_norm": 0.39553570295641505,
|
| 2331 |
+
"learning_rate": 3.1828369529674046e-05,
|
| 2332 |
+
"loss": 1.0,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.63,
|
| 2337 |
+
"grad_norm": 0.397983999068491,
|
| 2338 |
+
"learning_rate": 3.1542337832929644e-05,
|
| 2339 |
+
"loss": 1.0078,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.63,
|
| 2344 |
+
"grad_norm": 0.41099820792481956,
|
| 2345 |
+
"learning_rate": 3.125700377923186e-05,
|
| 2346 |
+
"loss": 1.0469,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.64,
|
| 2351 |
+
"grad_norm": 0.40386749243880216,
|
| 2352 |
+
"learning_rate": 3.0972378153333145e-05,
|
| 2353 |
+
"loss": 0.9961,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.64,
|
| 2358 |
+
"grad_norm": 0.41080474099987024,
|
| 2359 |
+
"learning_rate": 3.068847171320969e-05,
|
| 2360 |
+
"loss": 1.0156,
|
| 2361 |
+
"step": 336
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.64,
|
| 2365 |
+
"grad_norm": 0.403700576708479,
|
| 2366 |
+
"learning_rate": 3.0405295189654537e-05,
|
| 2367 |
+
"loss": 1.0234,
|
| 2368 |
+
"step": 337
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.64,
|
| 2372 |
+
"grad_norm": 0.40482152116129083,
|
| 2373 |
+
"learning_rate": 3.0122859285872214e-05,
|
| 2374 |
+
"loss": 1.0156,
|
| 2375 |
+
"step": 338
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.64,
|
| 2379 |
+
"grad_norm": 0.40683717747057807,
|
| 2380 |
+
"learning_rate": 2.9841174677074035e-05,
|
| 2381 |
+
"loss": 0.9805,
|
| 2382 |
+
"step": 339
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.65,
|
| 2386 |
+
"grad_norm": 0.4153367260281328,
|
| 2387 |
+
"learning_rate": 2.9560252010074706e-05,
|
| 2388 |
+
"loss": 1.0078,
|
| 2389 |
+
"step": 340
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.65,
|
| 2393 |
+
"grad_norm": 0.3911854931588867,
|
| 2394 |
+
"learning_rate": 2.9280101902889824e-05,
|
| 2395 |
+
"loss": 1.0312,
|
| 2396 |
+
"step": 341
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.65,
|
| 2400 |
+
"grad_norm": 0.4042030431024755,
|
| 2401 |
+
"learning_rate": 2.900073494433464e-05,
|
| 2402 |
+
"loss": 1.0156,
|
| 2403 |
+
"step": 342
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.65,
|
| 2407 |
+
"grad_norm": 0.40059455864229415,
|
| 2408 |
+
"learning_rate": 2.8722161693623772e-05,
|
| 2409 |
+
"loss": 0.9922,
|
| 2410 |
+
"step": 343
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.65,
|
| 2414 |
+
"grad_norm": 0.4074896896435664,
|
| 2415 |
+
"learning_rate": 2.8444392679972103e-05,
|
| 2416 |
+
"loss": 0.9883,
|
| 2417 |
+
"step": 344
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.65,
|
| 2421 |
+
"grad_norm": 0.4095882276226098,
|
| 2422 |
+
"learning_rate": 2.8167438402196805e-05,
|
| 2423 |
+
"loss": 1.0312,
|
| 2424 |
+
"step": 345
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.66,
|
| 2428 |
+
"grad_norm": 0.4055972430711286,
|
| 2429 |
+
"learning_rate": 2.7891309328320592e-05,
|
| 2430 |
+
"loss": 1.0078,
|
| 2431 |
+
"step": 346
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.66,
|
| 2435 |
+
"grad_norm": 0.4147093983828081,
|
| 2436 |
+
"learning_rate": 2.761601589517595e-05,
|
| 2437 |
+
"loss": 0.9727,
|
| 2438 |
+
"step": 347
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.66,
|
| 2442 |
+
"grad_norm": 0.3824364918889605,
|
| 2443 |
+
"learning_rate": 2.7341568508010705e-05,
|
| 2444 |
+
"loss": 1.0234,
|
| 2445 |
+
"step": 348
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.66,
|
| 2449 |
+
"grad_norm": 0.4173989668789549,
|
| 2450 |
+
"learning_rate": 2.706797754009476e-05,
|
| 2451 |
+
"loss": 0.9961,
|
| 2452 |
+
"step": 349
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.66,
|
| 2456 |
+
"grad_norm": 0.41599241388744446,
|
| 2457 |
+
"learning_rate": 2.6795253332327995e-05,
|
| 2458 |
+
"loss": 0.9844,
|
| 2459 |
+
"step": 350
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.67,
|
| 2463 |
+
"grad_norm": 0.40510951524103034,
|
| 2464 |
+
"learning_rate": 2.6523406192849386e-05,
|
| 2465 |
+
"loss": 0.9688,
|
| 2466 |
+
"step": 351
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.67,
|
| 2470 |
+
"grad_norm": 0.38849419233186266,
|
| 2471 |
+
"learning_rate": 2.62524463966475e-05,
|
| 2472 |
+
"loss": 1.0312,
|
| 2473 |
+
"step": 352
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.67,
|
| 2477 |
+
"grad_norm": 0.38718946711482044,
|
| 2478 |
+
"learning_rate": 2.5982384185171906e-05,
|
| 2479 |
+
"loss": 1.0078,
|
| 2480 |
+
"step": 353
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.67,
|
| 2484 |
+
"grad_norm": 0.3842929434765999,
|
| 2485 |
+
"learning_rate": 2.5713229765946357e-05,
|
| 2486 |
+
"loss": 1.0156,
|
| 2487 |
+
"step": 354
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.67,
|
| 2491 |
+
"grad_norm": 0.39359245264071546,
|
| 2492 |
+
"learning_rate": 2.544499331218274e-05,
|
| 2493 |
+
"loss": 0.9883,
|
| 2494 |
+
"step": 355
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.68,
|
| 2498 |
+
"grad_norm": 0.4033582052703098,
|
| 2499 |
+
"learning_rate": 2.5177684962396765e-05,
|
| 2500 |
+
"loss": 1.0,
|
| 2501 |
+
"step": 356
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.68,
|
| 2505 |
+
"grad_norm": 0.38879954929363575,
|
| 2506 |
+
"learning_rate": 2.4911314820024568e-05,
|
| 2507 |
+
"loss": 1.0078,
|
| 2508 |
+
"step": 357
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.68,
|
| 2512 |
+
"grad_norm": 0.40327329986367616,
|
| 2513 |
+
"learning_rate": 2.4645892953040962e-05,
|
| 2514 |
+
"loss": 1.0078,
|
| 2515 |
+
"step": 358
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.68,
|
| 2519 |
+
"grad_norm": 0.3920586735187762,
|
| 2520 |
+
"learning_rate": 2.438142939357882e-05,
|
| 2521 |
+
"loss": 1.0,
|
| 2522 |
+
"step": 359
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.68,
|
| 2526 |
+
"grad_norm": 0.4143087212185901,
|
| 2527 |
+
"learning_rate": 2.4117934137550003e-05,
|
| 2528 |
+
"loss": 0.9961,
|
| 2529 |
+
"step": 360
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.69,
|
| 2533 |
+
"grad_norm": 0.3935944385117418,
|
| 2534 |
+
"learning_rate": 2.38554171442674e-05,
|
| 2535 |
+
"loss": 1.0156,
|
| 2536 |
+
"step": 361
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.69,
|
| 2540 |
+
"grad_norm": 0.4077637452431266,
|
| 2541 |
+
"learning_rate": 2.3593888336068597e-05,
|
| 2542 |
+
"loss": 0.9883,
|
| 2543 |
+
"step": 362
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.69,
|
| 2547 |
+
"grad_norm": 0.4025782626367008,
|
| 2548 |
+
"learning_rate": 2.3333357597940793e-05,
|
| 2549 |
+
"loss": 1.0078,
|
| 2550 |
+
"step": 363
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.69,
|
| 2554 |
+
"grad_norm": 0.4036874759716257,
|
| 2555 |
+
"learning_rate": 2.3073834777147236e-05,
|
| 2556 |
+
"loss": 0.9922,
|
| 2557 |
+
"step": 364
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.69,
|
| 2561 |
+
"grad_norm": 0.4001732077591455,
|
| 2562 |
+
"learning_rate": 2.281532968285494e-05,
|
| 2563 |
+
"loss": 1.0156,
|
| 2564 |
+
"step": 365
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.69,
|
| 2568 |
+
"grad_norm": 0.38090979037495276,
|
| 2569 |
+
"learning_rate": 2.2557852085764053e-05,
|
| 2570 |
+
"loss": 0.9766,
|
| 2571 |
+
"step": 366
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.7,
|
| 2575 |
+
"grad_norm": 0.40328341409897206,
|
| 2576 |
+
"learning_rate": 2.230141171773836e-05,
|
| 2577 |
+
"loss": 0.9922,
|
| 2578 |
+
"step": 367
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.7,
|
| 2582 |
+
"grad_norm": 0.3838644049185376,
|
| 2583 |
+
"learning_rate": 2.204601827143769e-05,
|
| 2584 |
+
"loss": 0.9844,
|
| 2585 |
+
"step": 368
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.7,
|
| 2589 |
+
"grad_norm": 0.38931148821481226,
|
| 2590 |
+
"learning_rate": 2.179168139995134e-05,
|
| 2591 |
+
"loss": 1.0156,
|
| 2592 |
+
"step": 369
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.7,
|
| 2596 |
+
"grad_norm": 0.4024461082037364,
|
| 2597 |
+
"learning_rate": 2.1538410716433417e-05,
|
| 2598 |
+
"loss": 0.9805,
|
| 2599 |
+
"step": 370
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.7,
|
| 2603 |
+
"grad_norm": 0.3736565961055131,
|
| 2604 |
+
"learning_rate": 2.1286215793739302e-05,
|
| 2605 |
+
"loss": 1.0078,
|
| 2606 |
+
"step": 371
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.71,
|
| 2610 |
+
"grad_norm": 0.3833954847678005,
|
| 2611 |
+
"learning_rate": 2.103510616406396e-05,
|
| 2612 |
+
"loss": 1.0156,
|
| 2613 |
+
"step": 372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.71,
|
| 2617 |
+
"grad_norm": 0.38010761506947877,
|
| 2618 |
+
"learning_rate": 2.0785091318581577e-05,
|
| 2619 |
+
"loss": 0.9883,
|
| 2620 |
+
"step": 373
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.71,
|
| 2624 |
+
"grad_norm": 0.3883359267276046,
|
| 2625 |
+
"learning_rate": 2.053618070708691e-05,
|
| 2626 |
+
"loss": 1.0234,
|
| 2627 |
+
"step": 374
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.71,
|
| 2631 |
+
"grad_norm": 0.38727784403682314,
|
| 2632 |
+
"learning_rate": 2.0288383737638006e-05,
|
| 2633 |
+
"loss": 1.0,
|
| 2634 |
+
"step": 375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.71,
|
| 2638 |
+
"grad_norm": 0.37785442157781823,
|
| 2639 |
+
"learning_rate": 2.0041709776200664e-05,
|
| 2640 |
+
"loss": 0.9766,
|
| 2641 |
+
"step": 376
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.72,
|
| 2645 |
+
"grad_norm": 0.374719617466221,
|
| 2646 |
+
"learning_rate": 1.9796168146294412e-05,
|
| 2647 |
+
"loss": 0.9727,
|
| 2648 |
+
"step": 377
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.72,
|
| 2652 |
+
"grad_norm": 0.3978681831649405,
|
| 2653 |
+
"learning_rate": 1.9551768128640175e-05,
|
| 2654 |
+
"loss": 1.0156,
|
| 2655 |
+
"step": 378
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.72,
|
| 2659 |
+
"grad_norm": 0.40863119356002636,
|
| 2660 |
+
"learning_rate": 1.9308518960809353e-05,
|
| 2661 |
+
"loss": 0.9805,
|
| 2662 |
+
"step": 379
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.72,
|
| 2666 |
+
"grad_norm": 0.37974978552322725,
|
| 2667 |
+
"learning_rate": 1.9066429836874844e-05,
|
| 2668 |
+
"loss": 1.0078,
|
| 2669 |
+
"step": 380
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.72,
|
| 2673 |
+
"grad_norm": 0.38613047300957787,
|
| 2674 |
+
"learning_rate": 1.8825509907063327e-05,
|
| 2675 |
+
"loss": 0.9688,
|
| 2676 |
+
"step": 381
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.72,
|
| 2680 |
+
"grad_norm": 0.39858125559813595,
|
| 2681 |
+
"learning_rate": 1.8585768277409636e-05,
|
| 2682 |
+
"loss": 1.0078,
|
| 2683 |
+
"step": 382
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.73,
|
| 2687 |
+
"grad_norm": 0.39902011519219927,
|
| 2688 |
+
"learning_rate": 1.83472140094124e-05,
|
| 2689 |
+
"loss": 0.9609,
|
| 2690 |
+
"step": 383
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.73,
|
| 2694 |
+
"grad_norm": 0.39852324308132375,
|
| 2695 |
+
"learning_rate": 1.810985611969167e-05,
|
| 2696 |
+
"loss": 0.9766,
|
| 2697 |
+
"step": 384
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.73,
|
| 2701 |
+
"grad_norm": 0.39740793737557956,
|
| 2702 |
+
"learning_rate": 1.7873703579648034e-05,
|
| 2703 |
+
"loss": 0.9961,
|
| 2704 |
+
"step": 385
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.73,
|
| 2708 |
+
"grad_norm": 0.38900589785267126,
|
| 2709 |
+
"learning_rate": 1.763876531512354e-05,
|
| 2710 |
+
"loss": 0.9688,
|
| 2711 |
+
"step": 386
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.73,
|
| 2715 |
+
"grad_norm": 0.386397499552252,
|
| 2716 |
+
"learning_rate": 1.7405050206064373e-05,
|
| 2717 |
+
"loss": 1.0078,
|
| 2718 |
+
"step": 387
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.74,
|
| 2722 |
+
"grad_norm": 0.39337570995784904,
|
| 2723 |
+
"learning_rate": 1.7172567086185205e-05,
|
| 2724 |
+
"loss": 0.9727,
|
| 2725 |
+
"step": 388
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.74,
|
| 2729 |
+
"grad_norm": 0.39083779363840615,
|
| 2730 |
+
"learning_rate": 1.694132474263526e-05,
|
| 2731 |
+
"loss": 0.9961,
|
| 2732 |
+
"step": 389
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.74,
|
| 2736 |
+
"grad_norm": 0.38939147028830934,
|
| 2737 |
+
"learning_rate": 1.671133191566624e-05,
|
| 2738 |
+
"loss": 0.9844,
|
| 2739 |
+
"step": 390
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.74,
|
| 2743 |
+
"grad_norm": 0.44238601157646656,
|
| 2744 |
+
"learning_rate": 1.6482597298301916e-05,
|
| 2745 |
+
"loss": 0.9805,
|
| 2746 |
+
"step": 391
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.74,
|
| 2750 |
+
"grad_norm": 0.39265218999260465,
|
| 2751 |
+
"learning_rate": 1.625512953600966e-05,
|
| 2752 |
+
"loss": 1.0,
|
| 2753 |
+
"step": 392
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.75,
|
| 2757 |
+
"grad_norm": 0.3835027930578862,
|
| 2758 |
+
"learning_rate": 1.6028937226373536e-05,
|
| 2759 |
+
"loss": 0.9766,
|
| 2760 |
+
"step": 393
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.75,
|
| 2764 |
+
"grad_norm": 0.4052201995250459,
|
| 2765 |
+
"learning_rate": 1.5804028918769485e-05,
|
| 2766 |
+
"loss": 1.0,
|
| 2767 |
+
"step": 394
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.75,
|
| 2771 |
+
"grad_norm": 0.3929827776726385,
|
| 2772 |
+
"learning_rate": 1.5580413114042e-05,
|
| 2773 |
+
"loss": 0.9766,
|
| 2774 |
+
"step": 395
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.75,
|
| 2778 |
+
"grad_norm": 0.37984173524249143,
|
| 2779 |
+
"learning_rate": 1.535809826418304e-05,
|
| 2780 |
+
"loss": 0.9922,
|
| 2781 |
+
"step": 396
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.75,
|
| 2785 |
+
"grad_norm": 0.39211944754121586,
|
| 2786 |
+
"learning_rate": 1.5137092772012368e-05,
|
| 2787 |
+
"loss": 0.9844,
|
| 2788 |
+
"step": 397
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.76,
|
| 2792 |
+
"grad_norm": 0.39835572557937476,
|
| 2793 |
+
"learning_rate": 1.4917404990860112e-05,
|
| 2794 |
+
"loss": 1.0156,
|
| 2795 |
+
"step": 398
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.76,
|
| 2799 |
+
"grad_norm": 0.3685838055250128,
|
| 2800 |
+
"learning_rate": 1.469904322425092e-05,
|
| 2801 |
+
"loss": 1.0078,
|
| 2802 |
+
"step": 399
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.76,
|
| 2806 |
+
"grad_norm": 0.3708790521540525,
|
| 2807 |
+
"learning_rate": 1.4482015725590158e-05,
|
| 2808 |
+
"loss": 0.9727,
|
| 2809 |
+
"step": 400
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.76,
|
| 2813 |
+
"grad_norm": 0.3796896559412745,
|
| 2814 |
+
"learning_rate": 1.4266330697851954e-05,
|
| 2815 |
+
"loss": 0.9961,
|
| 2816 |
+
"step": 401
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.76,
|
| 2820 |
+
"grad_norm": 0.374826650593594,
|
| 2821 |
+
"learning_rate": 1.4051996293269182e-05,
|
| 2822 |
+
"loss": 0.9766,
|
| 2823 |
+
"step": 402
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 0.76,
|
| 2827 |
+
"grad_norm": 0.38661887803441924,
|
| 2828 |
+
"learning_rate": 1.3839020613025266e-05,
|
| 2829 |
+
"loss": 1.0,
|
| 2830 |
+
"step": 403
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 0.77,
|
| 2834 |
+
"grad_norm": 0.3745066620120658,
|
| 2835 |
+
"learning_rate": 1.3627411706948029e-05,
|
| 2836 |
+
"loss": 0.9688,
|
| 2837 |
+
"step": 404
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.77,
|
| 2841 |
+
"grad_norm": 0.3772263032436855,
|
| 2842 |
+
"learning_rate": 1.3417177573205398e-05,
|
| 2843 |
+
"loss": 0.9922,
|
| 2844 |
+
"step": 405
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.77,
|
| 2848 |
+
"grad_norm": 0.37135625308638415,
|
| 2849 |
+
"learning_rate": 1.3208326158003171e-05,
|
| 2850 |
+
"loss": 0.9844,
|
| 2851 |
+
"step": 406
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.77,
|
| 2855 |
+
"grad_norm": 0.39016768277198083,
|
| 2856 |
+
"learning_rate": 1.3000865355284563e-05,
|
| 2857 |
+
"loss": 0.9922,
|
| 2858 |
+
"step": 407
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 0.77,
|
| 2862 |
+
"grad_norm": 0.3927111734870179,
|
| 2863 |
+
"learning_rate": 1.2794803006431982e-05,
|
| 2864 |
+
"loss": 0.9688,
|
| 2865 |
+
"step": 408
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 0.78,
|
| 2869 |
+
"grad_norm": 0.37854433770919677,
|
| 2870 |
+
"learning_rate": 1.2590146899970446e-05,
|
| 2871 |
+
"loss": 0.9805,
|
| 2872 |
+
"step": 409
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 0.78,
|
| 2876 |
+
"grad_norm": 0.39232004793616226,
|
| 2877 |
+
"learning_rate": 1.2386904771273444e-05,
|
| 2878 |
+
"loss": 0.9961,
|
| 2879 |
+
"step": 410
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 0.78,
|
| 2883 |
+
"grad_norm": 0.38535521167421993,
|
| 2884 |
+
"learning_rate": 1.218508430227035e-05,
|
| 2885 |
+
"loss": 0.9844,
|
| 2886 |
+
"step": 411
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 0.78,
|
| 2890 |
+
"grad_norm": 0.3686602860581547,
|
| 2891 |
+
"learning_rate": 1.1984693121156226e-05,
|
| 2892 |
+
"loss": 0.9922,
|
| 2893 |
+
"step": 412
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 0.78,
|
| 2897 |
+
"grad_norm": 0.3859440212089631,
|
| 2898 |
+
"learning_rate": 1.1785738802103396e-05,
|
| 2899 |
+
"loss": 1.0156,
|
| 2900 |
+
"step": 413
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 0.79,
|
| 2904 |
+
"grad_norm": 0.3921328346507493,
|
| 2905 |
+
"learning_rate": 1.158822886497521e-05,
|
| 2906 |
+
"loss": 0.9688,
|
| 2907 |
+
"step": 414
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 0.79,
|
| 2911 |
+
"grad_norm": 0.39742562204123394,
|
| 2912 |
+
"learning_rate": 1.1392170775041788e-05,
|
| 2913 |
+
"loss": 1.0078,
|
| 2914 |
+
"step": 415
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 0.79,
|
| 2918 |
+
"grad_norm": 0.3713395354970734,
|
| 2919 |
+
"learning_rate": 1.1197571942697938e-05,
|
| 2920 |
+
"loss": 0.9805,
|
| 2921 |
+
"step": 416
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 0.79,
|
| 2925 |
+
"grad_norm": 0.37345209868445495,
|
| 2926 |
+
"learning_rate": 1.1004439723182942e-05,
|
| 2927 |
+
"loss": 1.0,
|
| 2928 |
+
"step": 417
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 0.79,
|
| 2932 |
+
"grad_norm": 0.3856263873198924,
|
| 2933 |
+
"learning_rate": 1.0812781416302642e-05,
|
| 2934 |
+
"loss": 0.9648,
|
| 2935 |
+
"step": 418
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 0.8,
|
| 2939 |
+
"grad_norm": 0.37612362914326103,
|
| 2940 |
+
"learning_rate": 1.0622604266153485e-05,
|
| 2941 |
+
"loss": 1.0156,
|
| 2942 |
+
"step": 419
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 0.8,
|
| 2946 |
+
"grad_norm": 0.3735721290488117,
|
| 2947 |
+
"learning_rate": 1.0433915460848764e-05,
|
| 2948 |
+
"loss": 0.9531,
|
| 2949 |
+
"step": 420
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.8,
|
| 2953 |
+
"grad_norm": 0.3831137038951988,
|
| 2954 |
+
"learning_rate": 1.0246722132246856e-05,
|
| 2955 |
+
"loss": 0.9727,
|
| 2956 |
+
"step": 421
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.8,
|
| 2960 |
+
"grad_norm": 0.38425446590883783,
|
| 2961 |
+
"learning_rate": 1.0061031355681766e-05,
|
| 2962 |
+
"loss": 0.9805,
|
| 2963 |
+
"step": 422
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 0.8,
|
| 2967 |
+
"grad_norm": 0.37733541326906417,
|
| 2968 |
+
"learning_rate": 9.876850149695555e-06,
|
| 2969 |
+
"loss": 0.9727,
|
| 2970 |
+
"step": 423
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 0.8,
|
| 2974 |
+
"grad_norm": 0.3919247049760062,
|
| 2975 |
+
"learning_rate": 9.694185475773216e-06,
|
| 2976 |
+
"loss": 0.9844,
|
| 2977 |
+
"step": 424
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 0.81,
|
| 2981 |
+
"grad_norm": 0.37412167877987657,
|
| 2982 |
+
"learning_rate": 9.513044238079427e-06,
|
| 2983 |
+
"loss": 0.9844,
|
| 2984 |
+
"step": 425
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.81,
|
| 2988 |
+
"grad_norm": 0.3960239887267585,
|
| 2989 |
+
"learning_rate": 9.333433283197702e-06,
|
| 2990 |
+
"loss": 1.0078,
|
| 2991 |
+
"step": 426
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 0.81,
|
| 2995 |
+
"grad_norm": 0.36022823771296714,
|
| 2996 |
+
"learning_rate": 9.15535939987151e-06,
|
| 2997 |
+
"loss": 0.9648,
|
| 2998 |
+
"step": 427
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 0.81,
|
| 3002 |
+
"grad_norm": 0.3789422853471504,
|
| 3003 |
+
"learning_rate": 8.978829318747745e-06,
|
| 3004 |
+
"loss": 0.9844,
|
| 3005 |
+
"step": 428
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.81,
|
| 3009 |
+
"grad_norm": 0.39075327374116037,
|
| 3010 |
+
"learning_rate": 8.803849712122292e-06,
|
| 3011 |
+
"loss": 1.0156,
|
| 3012 |
+
"step": 429
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 0.82,
|
| 3016 |
+
"grad_norm": 0.389242893802255,
|
| 3017 |
+
"learning_rate": 8.63042719368789e-06,
|
| 3018 |
+
"loss": 0.9766,
|
| 3019 |
+
"step": 430
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 0.82,
|
| 3023 |
+
"grad_norm": 0.3779626313074645,
|
| 3024 |
+
"learning_rate": 8.458568318284088e-06,
|
| 3025 |
+
"loss": 0.9883,
|
| 3026 |
+
"step": 431
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.82,
|
| 3030 |
+
"grad_norm": 0.39319540149781285,
|
| 3031 |
+
"learning_rate": 8.288279581649528e-06,
|
| 3032 |
+
"loss": 1.0,
|
| 3033 |
+
"step": 432
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 0.82,
|
| 3037 |
+
"grad_norm": 0.3759206398973123,
|
| 3038 |
+
"learning_rate": 8.11956742017641e-06,
|
| 3039 |
+
"loss": 0.9766,
|
| 3040 |
+
"step": 433
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 0.82,
|
| 3044 |
+
"grad_norm": 0.3938599895612702,
|
| 3045 |
+
"learning_rate": 7.952438210667268e-06,
|
| 3046 |
+
"loss": 1.0156,
|
| 3047 |
+
"step": 434
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 0.83,
|
| 3051 |
+
"grad_norm": 0.3821358600474751,
|
| 3052 |
+
"learning_rate": 7.786898270093846e-06,
|
| 3053 |
+
"loss": 0.9766,
|
| 3054 |
+
"step": 435
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 0.83,
|
| 3058 |
+
"grad_norm": 0.3811416337365797,
|
| 3059 |
+
"learning_rate": 7.6229538553584556e-06,
|
| 3060 |
+
"loss": 0.9844,
|
| 3061 |
+
"step": 436
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 0.83,
|
| 3065 |
+
"grad_norm": 0.384284050269022,
|
| 3066 |
+
"learning_rate": 7.460611163057346e-06,
|
| 3067 |
+
"loss": 0.9727,
|
| 3068 |
+
"step": 437
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 0.83,
|
| 3072 |
+
"grad_norm": 0.3868115258369787,
|
| 3073 |
+
"learning_rate": 7.299876329246652e-06,
|
| 3074 |
+
"loss": 0.9805,
|
| 3075 |
+
"step": 438
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 0.83,
|
| 3079 |
+
"grad_norm": 0.37631545582941645,
|
| 3080 |
+
"learning_rate": 7.140755429210316e-06,
|
| 3081 |
+
"loss": 0.9766,
|
| 3082 |
+
"step": 439
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 0.83,
|
| 3086 |
+
"grad_norm": 0.3763933121794425,
|
| 3087 |
+
"learning_rate": 6.983254477230588e-06,
|
| 3088 |
+
"loss": 0.9805,
|
| 3089 |
+
"step": 440
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 0.84,
|
| 3093 |
+
"grad_norm": 0.38966862555598764,
|
| 3094 |
+
"learning_rate": 6.827379426360614e-06,
|
| 3095 |
+
"loss": 0.9414,
|
| 3096 |
+
"step": 441
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 0.84,
|
| 3100 |
+
"grad_norm": 0.38924826237998583,
|
| 3101 |
+
"learning_rate": 6.673136168199467e-06,
|
| 3102 |
+
"loss": 0.9766,
|
| 3103 |
+
"step": 442
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 0.84,
|
| 3107 |
+
"grad_norm": 0.3716162541474658,
|
| 3108 |
+
"learning_rate": 6.52053053266945e-06,
|
| 3109 |
+
"loss": 1.0078,
|
| 3110 |
+
"step": 443
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 0.84,
|
| 3114 |
+
"grad_norm": 0.40192334917868294,
|
| 3115 |
+
"learning_rate": 6.369568287795791e-06,
|
| 3116 |
+
"loss": 1.0,
|
| 3117 |
+
"step": 444
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 0.84,
|
| 3121 |
+
"grad_norm": 0.3827921806873429,
|
| 3122 |
+
"learning_rate": 6.22025513948854e-06,
|
| 3123 |
+
"loss": 0.9609,
|
| 3124 |
+
"step": 445
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 0.85,
|
| 3128 |
+
"grad_norm": 0.3651988094584562,
|
| 3129 |
+
"learning_rate": 6.0725967313269736e-06,
|
| 3130 |
+
"loss": 1.0234,
|
| 3131 |
+
"step": 446
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 0.85,
|
| 3135 |
+
"grad_norm": 0.3854817154179708,
|
| 3136 |
+
"learning_rate": 5.926598644346259e-06,
|
| 3137 |
+
"loss": 0.9883,
|
| 3138 |
+
"step": 447
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 0.85,
|
| 3142 |
+
"grad_norm": 0.4041053789118015,
|
| 3143 |
+
"learning_rate": 5.782266396826536e-06,
|
| 3144 |
+
"loss": 0.9922,
|
| 3145 |
+
"step": 448
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 0.85,
|
| 3149 |
+
"grad_norm": 0.3840835793609324,
|
| 3150 |
+
"learning_rate": 5.639605444084273e-06,
|
| 3151 |
+
"loss": 0.9922,
|
| 3152 |
+
"step": 449
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 0.85,
|
| 3156 |
+
"grad_norm": 0.3827506231880665,
|
| 3157 |
+
"learning_rate": 5.498621178266167e-06,
|
| 3158 |
+
"loss": 0.9844,
|
| 3159 |
+
"step": 450
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 0.86,
|
| 3163 |
+
"grad_norm": 0.37488009002085854,
|
| 3164 |
+
"learning_rate": 5.3593189281452625e-06,
|
| 3165 |
+
"loss": 0.9883,
|
| 3166 |
+
"step": 451
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 0.86,
|
| 3170 |
+
"grad_norm": 0.3644346732423304,
|
| 3171 |
+
"learning_rate": 5.221703958919572e-06,
|
| 3172 |
+
"loss": 1.0,
|
| 3173 |
+
"step": 452
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 0.86,
|
| 3177 |
+
"grad_norm": 0.3648839469610167,
|
| 3178 |
+
"learning_rate": 5.085781472013051e-06,
|
| 3179 |
+
"loss": 0.9844,
|
| 3180 |
+
"step": 453
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 0.86,
|
| 3184 |
+
"grad_norm": 0.3888452684975849,
|
| 3185 |
+
"learning_rate": 4.951556604879048e-06,
|
| 3186 |
+
"loss": 0.9961,
|
| 3187 |
+
"step": 454
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 0.86,
|
| 3191 |
+
"grad_norm": 0.38081986253747263,
|
| 3192 |
+
"learning_rate": 4.819034430806046e-06,
|
| 3193 |
+
"loss": 1.0234,
|
| 3194 |
+
"step": 455
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 0.87,
|
| 3198 |
+
"grad_norm": 0.37504903165101505,
|
| 3199 |
+
"learning_rate": 4.688219958725981e-06,
|
| 3200 |
+
"loss": 0.9922,
|
| 3201 |
+
"step": 456
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 0.87,
|
| 3205 |
+
"grad_norm": 0.3896425547477861,
|
| 3206 |
+
"learning_rate": 4.559118133024853e-06,
|
| 3207 |
+
"loss": 0.9688,
|
| 3208 |
+
"step": 457
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 0.87,
|
| 3212 |
+
"grad_norm": 0.3794758055441137,
|
| 3213 |
+
"learning_rate": 4.431733833355933e-06,
|
| 3214 |
+
"loss": 0.9766,
|
| 3215 |
+
"step": 458
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.87,
|
| 3219 |
+
"grad_norm": 0.39706131136751927,
|
| 3220 |
+
"learning_rate": 4.3060718744552256e-06,
|
| 3221 |
+
"loss": 1.0,
|
| 3222 |
+
"step": 459
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 0.87,
|
| 3226 |
+
"grad_norm": 0.3697319148486722,
|
| 3227 |
+
"learning_rate": 4.1821370059595575e-06,
|
| 3228 |
+
"loss": 0.9961,
|
| 3229 |
+
"step": 460
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.87,
|
| 3233 |
+
"grad_norm": 0.3732079712646108,
|
| 3234 |
+
"learning_rate": 4.05993391222701e-06,
|
| 3235 |
+
"loss": 0.9922,
|
| 3236 |
+
"step": 461
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.88,
|
| 3240 |
+
"grad_norm": 0.38872894699778315,
|
| 3241 |
+
"learning_rate": 3.939467212159925e-06,
|
| 3242 |
+
"loss": 0.957,
|
| 3243 |
+
"step": 462
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 0.88,
|
| 3247 |
+
"grad_norm": 0.39026050723200223,
|
| 3248 |
+
"learning_rate": 3.820741459030253e-06,
|
| 3249 |
+
"loss": 1.0,
|
| 3250 |
+
"step": 463
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 0.88,
|
| 3254 |
+
"grad_norm": 0.3816637074881011,
|
| 3255 |
+
"learning_rate": 3.70376114030751e-06,
|
| 3256 |
+
"loss": 0.9727,
|
| 3257 |
+
"step": 464
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 0.88,
|
| 3261 |
+
"grad_norm": 0.381226241519682,
|
| 3262 |
+
"learning_rate": 3.5885306774891215e-06,
|
| 3263 |
+
"loss": 0.957,
|
| 3264 |
+
"step": 465
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 0.88,
|
| 3268 |
+
"grad_norm": 0.3815235626105606,
|
| 3269 |
+
"learning_rate": 3.475054425933344e-06,
|
| 3270 |
+
"loss": 1.0078,
|
| 3271 |
+
"step": 466
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.89,
|
| 3275 |
+
"grad_norm": 0.37253784076771357,
|
| 3276 |
+
"learning_rate": 3.3633366746946004e-06,
|
| 3277 |
+
"loss": 0.9844,
|
| 3278 |
+
"step": 467
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.89,
|
| 3282 |
+
"grad_norm": 0.3919508192472245,
|
| 3283 |
+
"learning_rate": 3.2533816463614253e-06,
|
| 3284 |
+
"loss": 0.9805,
|
| 3285 |
+
"step": 468
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 0.89,
|
| 3289 |
+
"grad_norm": 0.3589524968140092,
|
| 3290 |
+
"learning_rate": 3.145193496896809e-06,
|
| 3291 |
+
"loss": 0.9805,
|
| 3292 |
+
"step": 469
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 0.89,
|
| 3296 |
+
"grad_norm": 0.37438948854975374,
|
| 3297 |
+
"learning_rate": 3.0387763154811454e-06,
|
| 3298 |
+
"loss": 0.9766,
|
| 3299 |
+
"step": 470
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 0.89,
|
| 3303 |
+
"grad_norm": 0.37638045292642797,
|
| 3304 |
+
"learning_rate": 2.934134124357646e-06,
|
| 3305 |
+
"loss": 0.9766,
|
| 3306 |
+
"step": 471
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 0.9,
|
| 3310 |
+
"grad_norm": 0.37548669011906294,
|
| 3311 |
+
"learning_rate": 2.83127087868037e-06,
|
| 3312 |
+
"loss": 0.9961,
|
| 3313 |
+
"step": 472
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 0.9,
|
| 3317 |
+
"grad_norm": 0.37099994562581057,
|
| 3318 |
+
"learning_rate": 2.7301904663646516e-06,
|
| 3319 |
+
"loss": 0.9805,
|
| 3320 |
+
"step": 473
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 0.9,
|
| 3324 |
+
"grad_norm": 0.3955783574675612,
|
| 3325 |
+
"learning_rate": 2.630896707940228e-06,
|
| 3326 |
+
"loss": 1.0,
|
| 3327 |
+
"step": 474
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 0.9,
|
| 3331 |
+
"grad_norm": 0.3781205817722125,
|
| 3332 |
+
"learning_rate": 2.5333933564067492e-06,
|
| 3333 |
+
"loss": 0.9648,
|
| 3334 |
+
"step": 475
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 0.9,
|
| 3338 |
+
"grad_norm": 0.3753919414015063,
|
| 3339 |
+
"learning_rate": 2.4376840970920134e-06,
|
| 3340 |
+
"loss": 0.9766,
|
| 3341 |
+
"step": 476
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 0.91,
|
| 3345 |
+
"grad_norm": 0.37073539113386406,
|
| 3346 |
+
"learning_rate": 2.343772547512613e-06,
|
| 3347 |
+
"loss": 0.9727,
|
| 3348 |
+
"step": 477
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 0.91,
|
| 3352 |
+
"grad_norm": 0.38467962659041166,
|
| 3353 |
+
"learning_rate": 2.2516622572372414e-06,
|
| 3354 |
+
"loss": 0.9961,
|
| 3355 |
+
"step": 478
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 0.91,
|
| 3359 |
+
"grad_norm": 0.37351142314581637,
|
| 3360 |
+
"learning_rate": 2.1613567077524875e-06,
|
| 3361 |
+
"loss": 0.9648,
|
| 3362 |
+
"step": 479
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 0.91,
|
| 3366 |
+
"grad_norm": 0.3827518716422808,
|
| 3367 |
+
"learning_rate": 2.0728593123312935e-06,
|
| 3368 |
+
"loss": 0.957,
|
| 3369 |
+
"step": 480
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 0.91,
|
| 3373 |
+
"grad_norm": 0.38424950524851154,
|
| 3374 |
+
"learning_rate": 1.9861734159038968e-06,
|
| 3375 |
+
"loss": 0.9805,
|
| 3376 |
+
"step": 481
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 0.91,
|
| 3380 |
+
"grad_norm": 0.3738580907918172,
|
| 3381 |
+
"learning_rate": 1.9013022949314563e-06,
|
| 3382 |
+
"loss": 1.0,
|
| 3383 |
+
"step": 482
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 0.92,
|
| 3387 |
+
"grad_norm": 0.35985698703033747,
|
| 3388 |
+
"learning_rate": 1.8182491572821536e-06,
|
| 3389 |
+
"loss": 0.9688,
|
| 3390 |
+
"step": 483
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 0.92,
|
| 3394 |
+
"grad_norm": 0.37376402159660854,
|
| 3395 |
+
"learning_rate": 1.7370171421099978e-06,
|
| 3396 |
+
"loss": 0.9805,
|
| 3397 |
+
"step": 484
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 0.92,
|
| 3401 |
+
"grad_norm": 0.3652435400198038,
|
| 3402 |
+
"learning_rate": 1.6576093197361253e-06,
|
| 3403 |
+
"loss": 1.0,
|
| 3404 |
+
"step": 485
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 0.92,
|
| 3408 |
+
"grad_norm": 0.3740292147578786,
|
| 3409 |
+
"learning_rate": 1.5800286915328033e-06,
|
| 3410 |
+
"loss": 0.9922,
|
| 3411 |
+
"step": 486
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 0.92,
|
| 3415 |
+
"grad_norm": 0.38020345497873537,
|
| 3416 |
+
"learning_rate": 1.5042781898099434e-06,
|
| 3417 |
+
"loss": 0.9883,
|
| 3418 |
+
"step": 487
|
| 3419 |
+
},
|
| 3420 |
+
{
|
| 3421 |
+
"epoch": 0.93,
|
| 3422 |
+
"grad_norm": 0.38405525205639585,
|
| 3423 |
+
"learning_rate": 1.430360677704301e-06,
|
| 3424 |
+
"loss": 0.9844,
|
| 3425 |
+
"step": 488
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 0.93,
|
| 3429 |
+
"grad_norm": 0.37116971953078254,
|
| 3430 |
+
"learning_rate": 1.3582789490712179e-06,
|
| 3431 |
+
"loss": 0.9727,
|
| 3432 |
+
"step": 489
|
| 3433 |
+
},
|
| 3434 |
+
{
|
| 3435 |
+
"epoch": 0.93,
|
| 3436 |
+
"grad_norm": 0.3675736740984735,
|
| 3437 |
+
"learning_rate": 1.2880357283790777e-06,
|
| 3438 |
+
"loss": 0.9961,
|
| 3439 |
+
"step": 490
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 0.93,
|
| 3443 |
+
"grad_norm": 0.3615376408573602,
|
| 3444 |
+
"learning_rate": 1.2196336706062739e-06,
|
| 3445 |
+
"loss": 0.9805,
|
| 3446 |
+
"step": 491
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 0.93,
|
| 3450 |
+
"grad_norm": 0.3749327617084023,
|
| 3451 |
+
"learning_rate": 1.153075361140915e-06,
|
| 3452 |
+
"loss": 1.0156,
|
| 3453 |
+
"step": 492
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 0.94,
|
| 3457 |
+
"grad_norm": 0.36973528586380827,
|
| 3458 |
+
"learning_rate": 1.0883633156830553e-06,
|
| 3459 |
+
"loss": 1.0234,
|
| 3460 |
+
"step": 493
|
| 3461 |
+
},
|
| 3462 |
+
{
|
| 3463 |
+
"epoch": 0.94,
|
| 3464 |
+
"grad_norm": 0.36950719264405446,
|
| 3465 |
+
"learning_rate": 1.0254999801496247e-06,
|
| 3466 |
+
"loss": 0.9883,
|
| 3467 |
+
"step": 494
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 0.94,
|
| 3471 |
+
"grad_norm": 0.3811515872434199,
|
| 3472 |
+
"learning_rate": 9.644877305819976e-07,
|
| 3473 |
+
"loss": 0.9844,
|
| 3474 |
+
"step": 495
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"epoch": 0.94,
|
| 3478 |
+
"grad_norm": 0.37251325878792274,
|
| 3479 |
+
"learning_rate": 9.053288730561716e-07,
|
| 3480 |
+
"loss": 1.0,
|
| 3481 |
+
"step": 496
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 0.94,
|
| 3485 |
+
"grad_norm": 0.3784945023163416,
|
| 3486 |
+
"learning_rate": 8.480256435956124e-07,
|
| 3487 |
+
"loss": 0.9883,
|
| 3488 |
+
"step": 497
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 0.94,
|
| 3492 |
+
"grad_norm": 0.3823913771851788,
|
| 3493 |
+
"learning_rate": 7.925802080867128e-07,
|
| 3494 |
+
"loss": 0.9922,
|
| 3495 |
+
"step": 498
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 0.95,
|
| 3499 |
+
"grad_norm": 0.3723209207003651,
|
| 3500 |
+
"learning_rate": 7.389946621969679e-07,
|
| 3501 |
+
"loss": 0.9766,
|
| 3502 |
+
"step": 499
|
| 3503 |
+
},
|
| 3504 |
+
{
|
| 3505 |
+
"epoch": 0.95,
|
| 3506 |
+
"grad_norm": 0.3734561531299352,
|
| 3507 |
+
"learning_rate": 6.872710312957497e-07,
|
| 3508 |
+
"loss": 0.9883,
|
| 3509 |
+
"step": 500
|
| 3510 |
+
},
|
| 3511 |
+
{
|
| 3512 |
+
"epoch": 0.95,
|
| 3513 |
+
"grad_norm": 0.3718975890363552,
|
| 3514 |
+
"learning_rate": 6.374112703777301e-07,
|
| 3515 |
+
"loss": 0.9727,
|
| 3516 |
+
"step": 501
|
| 3517 |
+
},
|
| 3518 |
+
{
|
| 3519 |
+
"epoch": 0.95,
|
| 3520 |
+
"grad_norm": 0.3853867112825849,
|
| 3521 |
+
"learning_rate": 5.894172639890394e-07,
|
| 3522 |
+
"loss": 0.9727,
|
| 3523 |
+
"step": 502
|
| 3524 |
+
},
|
| 3525 |
+
{
|
| 3526 |
+
"epoch": 0.95,
|
| 3527 |
+
"grad_norm": 0.3666171985176669,
|
| 3528 |
+
"learning_rate": 5.432908261559733e-07,
|
| 3529 |
+
"loss": 0.9727,
|
| 3530 |
+
"step": 503
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"epoch": 0.96,
|
| 3534 |
+
"grad_norm": 0.37512968709593764,
|
| 3535 |
+
"learning_rate": 4.990337003164924e-07,
|
| 3536 |
+
"loss": 0.9688,
|
| 3537 |
+
"step": 504
|
| 3538 |
+
},
|
| 3539 |
+
{
|
| 3540 |
+
"epoch": 0.96,
|
| 3541 |
+
"grad_norm": 0.38232480313500466,
|
| 3542 |
+
"learning_rate": 4.5664755925426403e-07,
|
| 3543 |
+
"loss": 0.9844,
|
| 3544 |
+
"step": 505
|
| 3545 |
+
},
|
| 3546 |
+
{
|
| 3547 |
+
"epoch": 0.96,
|
| 3548 |
+
"grad_norm": 0.3700171570622694,
|
| 3549 |
+
"learning_rate": 4.1613400503550114e-07,
|
| 3550 |
+
"loss": 0.9766,
|
| 3551 |
+
"step": 506
|
| 3552 |
+
},
|
| 3553 |
+
{
|
| 3554 |
+
"epoch": 0.96,
|
| 3555 |
+
"grad_norm": 0.3900755929317903,
|
| 3556 |
+
"learning_rate": 3.7749456894834447e-07,
|
| 3557 |
+
"loss": 0.9609,
|
| 3558 |
+
"step": 507
|
| 3559 |
+
},
|
| 3560 |
+
{
|
| 3561 |
+
"epoch": 0.96,
|
| 3562 |
+
"grad_norm": 0.36995686804328504,
|
| 3563 |
+
"learning_rate": 3.4073071144502533e-07,
|
| 3564 |
+
"loss": 0.9688,
|
| 3565 |
+
"step": 508
|
| 3566 |
+
},
|
| 3567 |
+
{
|
| 3568 |
+
"epoch": 0.97,
|
| 3569 |
+
"grad_norm": 0.36023064413895745,
|
| 3570 |
+
"learning_rate": 3.058438220866544e-07,
|
| 3571 |
+
"loss": 0.9883,
|
| 3572 |
+
"step": 509
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 0.97,
|
| 3576 |
+
"grad_norm": 0.37996338814367037,
|
| 3577 |
+
"learning_rate": 2.72835219490708e-07,
|
| 3578 |
+
"loss": 0.9805,
|
| 3579 |
+
"step": 510
|
| 3580 |
+
},
|
| 3581 |
+
{
|
| 3582 |
+
"epoch": 0.97,
|
| 3583 |
+
"grad_norm": 0.36362699174525226,
|
| 3584 |
+
"learning_rate": 2.4170615128117357e-07,
|
| 3585 |
+
"loss": 0.9453,
|
| 3586 |
+
"step": 511
|
| 3587 |
+
},
|
| 3588 |
+
{
|
| 3589 |
+
"epoch": 0.97,
|
| 3590 |
+
"grad_norm": 0.37920383685543685,
|
| 3591 |
+
"learning_rate": 2.12457794041393e-07,
|
| 3592 |
+
"loss": 1.0156,
|
| 3593 |
+
"step": 512
|
| 3594 |
+
},
|
| 3595 |
+
{
|
| 3596 |
+
"epoch": 0.97,
|
| 3597 |
+
"grad_norm": 0.3802256086316899,
|
| 3598 |
+
"learning_rate": 1.850912532696092e-07,
|
| 3599 |
+
"loss": 0.9883,
|
| 3600 |
+
"step": 513
|
| 3601 |
+
},
|
| 3602 |
+
{
|
| 3603 |
+
"epoch": 0.98,
|
| 3604 |
+
"grad_norm": 0.3840079426171848,
|
| 3605 |
+
"learning_rate": 1.596075633371774e-07,
|
| 3606 |
+
"loss": 1.0,
|
| 3607 |
+
"step": 514
|
| 3608 |
+
},
|
| 3609 |
+
{
|
| 3610 |
+
"epoch": 0.98,
|
| 3611 |
+
"grad_norm": 0.372033357737712,
|
| 3612 |
+
"learning_rate": 1.3600768744944647e-07,
|
| 3613 |
+
"loss": 0.9727,
|
| 3614 |
+
"step": 515
|
| 3615 |
+
},
|
| 3616 |
+
{
|
| 3617 |
+
"epoch": 0.98,
|
| 3618 |
+
"grad_norm": 0.3700966978882948,
|
| 3619 |
+
"learning_rate": 1.1429251760938231e-07,
|
| 3620 |
+
"loss": 0.9453,
|
| 3621 |
+
"step": 516
|
| 3622 |
+
},
|
| 3623 |
+
{
|
| 3624 |
+
"epoch": 0.98,
|
| 3625 |
+
"grad_norm": 0.37138234312324336,
|
| 3626 |
+
"learning_rate": 9.446287458383385e-08,
|
| 3627 |
+
"loss": 0.9531,
|
| 3628 |
+
"step": 517
|
| 3629 |
+
},
|
| 3630 |
+
{
|
| 3631 |
+
"epoch": 0.98,
|
| 3632 |
+
"grad_norm": 0.38319867619202025,
|
| 3633 |
+
"learning_rate": 7.651950787251339e-08,
|
| 3634 |
+
"loss": 0.9883,
|
| 3635 |
+
"step": 518
|
| 3636 |
+
},
|
| 3637 |
+
{
|
| 3638 |
+
"epoch": 0.98,
|
| 3639 |
+
"grad_norm": 0.36834536474781127,
|
| 3640 |
+
"learning_rate": 6.046309567968588e-08,
|
| 3641 |
+
"loss": 0.9805,
|
| 3642 |
+
"step": 519
|
| 3643 |
+
},
|
| 3644 |
+
{
|
| 3645 |
+
"epoch": 0.99,
|
| 3646 |
+
"grad_norm": 0.3838857136930694,
|
| 3647 |
+
"learning_rate": 4.6294244888500645e-08,
|
| 3648 |
+
"loss": 1.0,
|
| 3649 |
+
"step": 520
|
| 3650 |
+
},
|
| 3651 |
+
{
|
| 3652 |
+
"epoch": 0.99,
|
| 3653 |
+
"grad_norm": 0.37142652746946664,
|
| 3654 |
+
"learning_rate": 3.4013491038087375e-08,
|
| 3655 |
+
"loss": 1.0,
|
| 3656 |
+
"step": 521
|
| 3657 |
+
},
|
| 3658 |
+
{
|
| 3659 |
+
"epoch": 0.99,
|
| 3660 |
+
"grad_norm": 0.3764293979963409,
|
| 3661 |
+
"learning_rate": 2.3621298303294625e-08,
|
| 3662 |
+
"loss": 0.9688,
|
| 3663 |
+
"step": 522
|
| 3664 |
+
},
|
| 3665 |
+
{
|
| 3666 |
+
"epoch": 0.99,
|
| 3667 |
+
"grad_norm": 0.3612657340251834,
|
| 3668 |
+
"learning_rate": 1.511805947714273e-08,
|
| 3669 |
+
"loss": 0.9961,
|
| 3670 |
+
"step": 523
|
| 3671 |
+
},
|
| 3672 |
+
{
|
| 3673 |
+
"epoch": 0.99,
|
| 3674 |
+
"grad_norm": 0.3846047566682503,
|
| 3675 |
+
"learning_rate": 8.504095956002323e-09,
|
| 3676 |
+
"loss": 0.9922,
|
| 3677 |
+
"step": 524
|
| 3678 |
+
},
|
| 3679 |
+
{
|
| 3680 |
+
"epoch": 1.0,
|
| 3681 |
+
"grad_norm": 0.37603252090597145,
|
| 3682 |
+
"learning_rate": 3.7796577274096245e-09,
|
| 3683 |
+
"loss": 0.9727,
|
| 3684 |
+
"step": 525
|
| 3685 |
+
},
|
| 3686 |
+
{
|
| 3687 |
+
"epoch": 1.0,
|
| 3688 |
+
"grad_norm": 0.3918810108171524,
|
| 3689 |
+
"learning_rate": 9.449233606573238e-10,
|
| 3690 |
+
"loss": 0.9805,
|
| 3691 |
+
"step": 526
|
| 3692 |
+
},
|
| 3693 |
+
{
|
| 3694 |
+
"epoch": 1.0,
|
| 3695 |
+
"grad_norm": 0.37221487121132474,
|
| 3696 |
+
"learning_rate": 0.0,
|
| 3697 |
+
"loss": 1.0078,
|
| 3698 |
+
"step": 527
|
| 3699 |
+
},
|
| 3700 |
+
{
|
| 3701 |
+
"epoch": 1.0,
|
| 3702 |
+
"step": 527,
|
| 3703 |
+
"total_flos": 2.9568341572059136e+16,
|
| 3704 |
+
"train_loss": 1.0576598078747628,
|
| 3705 |
+
"train_runtime": 6355.9639,
|
| 3706 |
+
"train_samples_per_second": 340.075,
|
| 3707 |
+
"train_steps_per_second": 0.083
|
| 3708 |
+
}
|
| 3709 |
+
],
|
| 3710 |
+
"logging_steps": 1.0,
|
| 3711 |
+
"max_steps": 527,
|
| 3712 |
+
"num_input_tokens_seen": 0,
|
| 3713 |
+
"num_train_epochs": 1,
|
| 3714 |
+
"save_steps": 210,
|
| 3715 |
+
"total_flos": 2.9568341572059136e+16,
|
| 3716 |
+
"train_batch_size": 16,
|
| 3717 |
+
"trial_name": null,
|
| 3718 |
+
"trial_params": null
|
| 3719 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e832039ee7206cc26424f54e091cb93c28d03dd4e03ebcf5bec918cf7ede8a7
|
| 3 |
+
size 6779
|