initial upload
Browse files- .gitattributes +19 -0
- README.md +59 -0
- all_results.json +9 -0
- checkpoint-411/optimizer_0/.metadata +3 -0
- checkpoint-411/optimizer_0/__0_0.distcp +3 -0
- checkpoint-411/optimizer_0/__1_0.distcp +3 -0
- checkpoint-411/optimizer_0/__2_0.distcp +3 -0
- checkpoint-411/optimizer_0/__3_0.distcp +3 -0
- checkpoint-411/optimizer_0/__4_0.distcp +3 -0
- checkpoint-411/optimizer_0/__5_0.distcp +3 -0
- checkpoint-411/optimizer_0/__6_0.distcp +3 -0
- checkpoint-411/optimizer_0/__7_0.distcp +3 -0
- checkpoint-411/pytorch_model_fsdp_0/.metadata +3 -0
- checkpoint-411/pytorch_model_fsdp_0/__0_0.distcp +3 -0
- checkpoint-411/pytorch_model_fsdp_0/__1_0.distcp +3 -0
- checkpoint-411/pytorch_model_fsdp_0/__2_0.distcp +3 -0
- checkpoint-411/pytorch_model_fsdp_0/__3_0.distcp +3 -0
- checkpoint-411/pytorch_model_fsdp_0/__4_0.distcp +3 -0
- checkpoint-411/pytorch_model_fsdp_0/__5_0.distcp +3 -0
- checkpoint-411/pytorch_model_fsdp_0/__6_0.distcp +3 -0
- checkpoint-411/pytorch_model_fsdp_0/__7_0.distcp +3 -0
- checkpoint-411/rng_state_0.pth +3 -0
- checkpoint-411/rng_state_1.pth +3 -0
- checkpoint-411/rng_state_2.pth +3 -0
- checkpoint-411/rng_state_3.pth +3 -0
- checkpoint-411/rng_state_4.pth +3 -0
- checkpoint-411/rng_state_5.pth +3 -0
- checkpoint-411/rng_state_6.pth +3 -0
- checkpoint-411/rng_state_7.pth +3 -0
- checkpoint-411/scheduler.pt +3 -0
- checkpoint-411/trainer_state.json +607 -0
- config.json +36 -0
- generation_config.json +7 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +298 -0
- runs/Jun20_09-56-47_hakone/events.out.tfevents.1750427946.hakone.1502283.0 +3 -0
- runs/Jun20_10-02-28_hakone/events.out.tfevents.1750428275.hakone.1507035.0 +3 -0
- runs/Jun20_13-15-13_hakone/events.out.tfevents.1750439726.hakone.1542090.0 +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2066 -0
- train_results.json +9 -0
- trainer_state.json +616 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,22 @@ saved_model/**/* 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 36 |
+
checkpoint-411/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-411/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
checkpoint-411/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
checkpoint-411/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
checkpoint-411/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
checkpoint-411/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
checkpoint-411/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
checkpoint-411/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
checkpoint-411/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
checkpoint-411/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
checkpoint-411/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
checkpoint-411/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
checkpoint-411/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
checkpoint-411/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
checkpoint-411/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
checkpoint-411/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
checkpoint-411/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
checkpoint-411/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name:
|
| 5 |
+
tags:
|
| 6 |
+
- sft
|
| 7 |
+
- full-finetuning
|
| 8 |
+
tags:
|
| 9 |
+
- generated_from_trainer
|
| 10 |
+
licence: license
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for {'tags': ['sft', 'full-finetuning']}
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B).
|
| 16 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
+
|
| 18 |
+
## Quick start
|
| 19 |
+
|
| 20 |
+
```python
|
| 21 |
+
from transformers import pipeline
|
| 22 |
+
|
| 23 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 24 |
+
generator = pipeline("text-generation", model="None", device="cuda")
|
| 25 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 26 |
+
print(output["generated_text"])
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
## Training procedure
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
This model was trained with SFT.
|
| 35 |
+
|
| 36 |
+
### Framework versions
|
| 37 |
+
|
| 38 |
+
- TRL: 0.13.0
|
| 39 |
+
- Transformers: 4.46.0
|
| 40 |
+
- Pytorch: 2.7.0
|
| 41 |
+
- Datasets: 3.2.0
|
| 42 |
+
- Tokenizers: 0.20.3
|
| 43 |
+
|
| 44 |
+
## Citations
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
Cite TRL as:
|
| 49 |
+
|
| 50 |
+
```bibtex
|
| 51 |
+
@misc{vonwerra2022trl,
|
| 52 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 53 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
| 54 |
+
year = 2020,
|
| 55 |
+
journal = {GitHub repository},
|
| 56 |
+
publisher = {GitHub},
|
| 57 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 58 |
+
}
|
| 59 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9987849331713244,
|
| 3 |
+
"total_flos": 1.267367944707375e+18,
|
| 4 |
+
"train_loss": 0.9162624978671109,
|
| 5 |
+
"train_runtime": 10821.8058,
|
| 6 |
+
"train_samples": 37443,
|
| 7 |
+
"train_samples_per_second": 2.433,
|
| 8 |
+
"train_steps_per_second": 0.038
|
| 9 |
+
}
|
checkpoint-411/optimizer_0/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e993a88d903d728f5e982989e31f5dada2d490c1f8f42926c8a270e181c7c4c4
|
| 3 |
+
size 1130169
|
checkpoint-411/optimizer_0/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ec4fc563e82b113bae6450e6404550061b561c08fcf54bc22514b588e8a20a8
|
| 3 |
+
size 8031179062
|
checkpoint-411/optimizer_0/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:628852775cc42941863445ed3e311c533b6a828e8b1d9988a41fd09efbfc8cb8
|
| 3 |
+
size 8031261002
|
checkpoint-411/optimizer_0/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f028d9064fa730adaef1823613b88a11b8f2f6eaa69707eda064643b1ea1980e
|
| 3 |
+
size 8031247818
|
checkpoint-411/optimizer_0/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:335181f0bb665631a1d0c150d8119f4e5ef6d823eb0dfa3e57f98747f62cf8ab
|
| 3 |
+
size 8031247818
|
checkpoint-411/optimizer_0/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc15f30d5fa0a38369fd7284563a8d84a35bafd74392c281feb88d9ede49e67b
|
| 3 |
+
size 8031247818
|
checkpoint-411/optimizer_0/__5_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a93cca366ea2480a74c1068e8b5e364219b9ca4c7fbe80425a2e4a044208d30
|
| 3 |
+
size 8031251285
|
checkpoint-411/optimizer_0/__6_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dbdc8a7465d0c3ebfcda7e63c0278bbe8829c7d66068de522b77fe49f938234
|
| 3 |
+
size 8031251285
|
checkpoint-411/optimizer_0/__7_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf0bcc588a63e313abb270717a56303fd021577f039cdd856bff2855ee32c59b
|
| 3 |
+
size 8031251285
|
checkpoint-411/pytorch_model_fsdp_0/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d89c518fa0345c51c3a4c440a62b7bc487cdd72e005db1b7ec0437635a0f4849
|
| 3 |
+
size 456668
|
checkpoint-411/pytorch_model_fsdp_0/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eddef7fc71fc493691512bece68ba9fa2e323465f995a598dbd34839d9e7811e
|
| 3 |
+
size 4015589531
|
checkpoint-411/pytorch_model_fsdp_0/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06a0dc5babbdcaf4dd7912fe75d34e2f189027529264ad3e719e48390e7abf7e
|
| 3 |
+
size 4015589531
|
checkpoint-411/pytorch_model_fsdp_0/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89b869d4183676245c041222691563149afbb4360e5266d4fc67c5a2c035cb99
|
| 3 |
+
size 4015589531
|
checkpoint-411/pytorch_model_fsdp_0/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18f35333d61935da3491f55bea9ee9f2504ba5841f68c024ac14e58eaaa4394f
|
| 3 |
+
size 4015589531
|
checkpoint-411/pytorch_model_fsdp_0/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c28d38a64bbfe5c449128c652bd7a8e1d0aa3033c61116f0bf9a72de6c30727
|
| 3 |
+
size 4015589531
|
checkpoint-411/pytorch_model_fsdp_0/__5_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:510b4588754f3037c222fb04935117daf43111bb481f5aad777233cd1cf51a19
|
| 3 |
+
size 4015589531
|
checkpoint-411/pytorch_model_fsdp_0/__6_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4889f54e41219fd1d77f30317e089c046af00d4870d0c96a89a091e9aed88f59
|
| 3 |
+
size 4015589531
|
checkpoint-411/pytorch_model_fsdp_0/__7_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13dd7ed85163d122fb5dd5914776e70f3cb8f8617b62ba509f5f7049d3d9db1a
|
| 3 |
+
size 4015589531
|
checkpoint-411/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8f92cf63e0989759370d24108b469c492c12202403f036015307ce49f12cedc
|
| 3 |
+
size 16389
|
checkpoint-411/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ed40a0a4e9f365d2c6cc004d97e6705894eba46c8be4c160c1455bc3062dee1
|
| 3 |
+
size 16389
|
checkpoint-411/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d688b304d19c260b5cfa471535ed51d7e1d60b3a0d0159dfd1a04b87904a9f42
|
| 3 |
+
size 16389
|
checkpoint-411/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9967425ebcaee80d9b518fa0244d52f739b1b983d87cda71d5fede0c073e9d3b
|
| 3 |
+
size 16389
|
checkpoint-411/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:469900fd39c667ffbd49c3c407c0ba317a1e9f5f9339a99b5d38423b7d0ce6d4
|
| 3 |
+
size 16389
|
checkpoint-411/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:124688471ff2a6e80f2fcefedbf741fb18d08dd539d5bd07a52e81be545142a5
|
| 3 |
+
size 16389
|
checkpoint-411/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e69f1ced9f992a72c948698e5eb06088610788988cdb2fdbdd624e064319d60
|
| 3 |
+
size 16389
|
checkpoint-411/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a376268a55d6ee10c371c06aa952334c4c6a1af9ea2d71b1951a57367a0c6722
|
| 3 |
+
size 16389
|
checkpoint-411/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee1ebcd4e6415547ca6de294ab51235ef5f63e0645387600f6c342b9a2476f6e
|
| 3 |
+
size 1465
|
checkpoint-411/trainer_state.json
ADDED
|
@@ -0,0 +1,607 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9987849331713244,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 411,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012150668286755772,
|
| 13 |
+
"grad_norm": 4.5974345207214355,
|
| 14 |
+
"learning_rate": 4.761904761904762e-06,
|
| 15 |
+
"loss": 1.3953,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.024301336573511544,
|
| 20 |
+
"grad_norm": 2.528956651687622,
|
| 21 |
+
"learning_rate": 9.523809523809525e-06,
|
| 22 |
+
"loss": 1.2041,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03645200486026731,
|
| 27 |
+
"grad_norm": 1.4799861907958984,
|
| 28 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 29 |
+
"loss": 1.1068,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04860267314702309,
|
| 34 |
+
"grad_norm": 1.4184110164642334,
|
| 35 |
+
"learning_rate": 1.904761904761905e-05,
|
| 36 |
+
"loss": 1.0285,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.060753341433778855,
|
| 41 |
+
"grad_norm": 1.0306570529937744,
|
| 42 |
+
"learning_rate": 1.9994809335686152e-05,
|
| 43 |
+
"loss": 1.0168,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07290400972053462,
|
| 48 |
+
"grad_norm": 0.8752269744873047,
|
| 49 |
+
"learning_rate": 1.9973731496914914e-05,
|
| 50 |
+
"loss": 0.9848,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0850546780072904,
|
| 55 |
+
"grad_norm": 0.8289946913719177,
|
| 56 |
+
"learning_rate": 1.9936476229183133e-05,
|
| 57 |
+
"loss": 0.9947,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09720534629404617,
|
| 62 |
+
"grad_norm": 0.8398821353912354,
|
| 63 |
+
"learning_rate": 1.9883103960671305e-05,
|
| 64 |
+
"loss": 0.9783,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10935601458080195,
|
| 69 |
+
"grad_norm": 0.8018831610679626,
|
| 70 |
+
"learning_rate": 1.9813701261394136e-05,
|
| 71 |
+
"loss": 0.9788,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.12150668286755771,
|
| 76 |
+
"grad_norm": 0.8563551306724548,
|
| 77 |
+
"learning_rate": 1.9728380702783644e-05,
|
| 78 |
+
"loss": 0.9635,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1336573511543135,
|
| 83 |
+
"grad_norm": 0.746189296245575,
|
| 84 |
+
"learning_rate": 1.962728067509791e-05,
|
| 85 |
+
"loss": 0.9706,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.14580801944106925,
|
| 90 |
+
"grad_norm": 0.8066502809524536,
|
| 91 |
+
"learning_rate": 1.9510565162951538e-05,
|
| 92 |
+
"loss": 0.9456,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.15795868772782504,
|
| 97 |
+
"grad_norm": 0.7983813285827637,
|
| 98 |
+
"learning_rate": 1.9378423479332045e-05,
|
| 99 |
+
"loss": 0.9386,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1701093560145808,
|
| 104 |
+
"grad_norm": 0.7811228632926941,
|
| 105 |
+
"learning_rate": 1.923106995853349e-05,
|
| 106 |
+
"loss": 0.9432,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1822600243013366,
|
| 111 |
+
"grad_norm": 0.7911136746406555,
|
| 112 |
+
"learning_rate": 1.9068743608505454e-05,
|
| 113 |
+
"loss": 0.9538,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.19441069258809235,
|
| 118 |
+
"grad_norm": 0.7658519744873047,
|
| 119 |
+
"learning_rate": 1.8891707723181294e-05,
|
| 120 |
+
"loss": 0.9526,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2065613608748481,
|
| 125 |
+
"grad_norm": 0.8204901814460754,
|
| 126 |
+
"learning_rate": 1.8700249455414394e-05,
|
| 127 |
+
"loss": 0.937,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2187120291616039,
|
| 132 |
+
"grad_norm": 0.760960042476654,
|
| 133 |
+
"learning_rate": 1.8494679351215212e-05,
|
| 134 |
+
"loss": 0.9267,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.23086269744835966,
|
| 139 |
+
"grad_norm": 0.804595947265625,
|
| 140 |
+
"learning_rate": 1.82753308460445e-05,
|
| 141 |
+
"loss": 0.9276,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.24301336573511542,
|
| 146 |
+
"grad_norm": 2.3202602863311768,
|
| 147 |
+
"learning_rate": 1.804255972397977e-05,
|
| 148 |
+
"loss": 0.923,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2551640340218712,
|
| 153 |
+
"grad_norm": 0.7664303779602051,
|
| 154 |
+
"learning_rate": 1.7796743540632226e-05,
|
| 155 |
+
"loss": 0.9085,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.267314702308627,
|
| 160 |
+
"grad_norm": 0.8157963752746582,
|
| 161 |
+
"learning_rate": 1.753828101075017e-05,
|
| 162 |
+
"loss": 0.9501,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.27946537059538273,
|
| 167 |
+
"grad_norm": 0.8094449639320374,
|
| 168 |
+
"learning_rate": 1.7267591361502233e-05,
|
| 169 |
+
"loss": 0.9271,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2916160388821385,
|
| 174 |
+
"grad_norm": 0.9288702011108398,
|
| 175 |
+
"learning_rate": 1.6985113652489374e-05,
|
| 176 |
+
"loss": 0.9571,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3037667071688943,
|
| 181 |
+
"grad_norm": 0.84999018907547,
|
| 182 |
+
"learning_rate": 1.6691306063588583e-05,
|
| 183 |
+
"loss": 0.9042,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3159173754556501,
|
| 188 |
+
"grad_norm": 0.8100440502166748,
|
| 189 |
+
"learning_rate": 1.638664515178348e-05,
|
| 190 |
+
"loss": 0.9104,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.32806804374240583,
|
| 195 |
+
"grad_norm": 0.7512496113777161,
|
| 196 |
+
"learning_rate": 1.6071625078187113e-05,
|
| 197 |
+
"loss": 0.9129,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3402187120291616,
|
| 202 |
+
"grad_norm": 0.7866060733795166,
|
| 203 |
+
"learning_rate": 1.574675680651084e-05,
|
| 204 |
+
"loss": 0.9113,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.35236938031591736,
|
| 209 |
+
"grad_norm": 0.7891241908073425,
|
| 210 |
+
"learning_rate": 1.5412567274279316e-05,
|
| 211 |
+
"loss": 0.9286,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3645200486026732,
|
| 216 |
+
"grad_norm": 0.7657147645950317,
|
| 217 |
+
"learning_rate": 1.5069598538135905e-05,
|
| 218 |
+
"loss": 0.9302,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.37667071688942894,
|
| 223 |
+
"grad_norm": 0.7555293440818787,
|
| 224 |
+
"learning_rate": 1.471840689462482e-05,
|
| 225 |
+
"loss": 0.914,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3888213851761847,
|
| 230 |
+
"grad_norm": 0.7541491389274597,
|
| 231 |
+
"learning_rate": 1.4359561977876102e-05,
|
| 232 |
+
"loss": 0.9241,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.40097205346294046,
|
| 237 |
+
"grad_norm": 0.7439760565757751,
|
| 238 |
+
"learning_rate": 1.3993645835656955e-05,
|
| 239 |
+
"loss": 0.8976,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4131227217496962,
|
| 244 |
+
"grad_norm": 0.7437750697135925,
|
| 245 |
+
"learning_rate": 1.362125198528817e-05,
|
| 246 |
+
"loss": 0.9033,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.425273390036452,
|
| 251 |
+
"grad_norm": 0.7202824354171753,
|
| 252 |
+
"learning_rate": 1.3242984450956829e-05,
|
| 253 |
+
"loss": 0.9024,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4374240583232078,
|
| 258 |
+
"grad_norm": 0.7379337549209595,
|
| 259 |
+
"learning_rate": 1.2859456783986892e-05,
|
| 260 |
+
"loss": 0.8918,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.44957472660996356,
|
| 265 |
+
"grad_norm": 0.7616682648658752,
|
| 266 |
+
"learning_rate": 1.2471291067656696e-05,
|
| 267 |
+
"loss": 0.9167,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4617253948967193,
|
| 272 |
+
"grad_norm": 0.7680121660232544,
|
| 273 |
+
"learning_rate": 1.2079116908177592e-05,
|
| 274 |
+
"loss": 0.8958,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4738760631834751,
|
| 279 |
+
"grad_norm": 0.7707135081291199,
|
| 280 |
+
"learning_rate": 1.1683570413470384e-05,
|
| 281 |
+
"loss": 0.9227,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.48602673147023084,
|
| 286 |
+
"grad_norm": 0.7425935864448547,
|
| 287 |
+
"learning_rate": 1.1285293161395948e-05,
|
| 288 |
+
"loss": 0.8913,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.49817739975698666,
|
| 293 |
+
"grad_norm": 0.7188636660575867,
|
| 294 |
+
"learning_rate": 1.0884931159113585e-05,
|
| 295 |
+
"loss": 0.8897,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5103280680437424,
|
| 300 |
+
"grad_norm": 0.7420693039894104,
|
| 301 |
+
"learning_rate": 1.0483133795255072e-05,
|
| 302 |
+
"loss": 0.9006,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5224787363304981,
|
| 307 |
+
"grad_norm": 0.6850030422210693,
|
| 308 |
+
"learning_rate": 1.0080552786613899e-05,
|
| 309 |
+
"loss": 0.8779,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.534629404617254,
|
| 314 |
+
"grad_norm": 0.6989702582359314,
|
| 315 |
+
"learning_rate": 9.677841121058274e-06,
|
| 316 |
+
"loss": 0.8798,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5467800729040098,
|
| 321 |
+
"grad_norm": 0.7223166823387146,
|
| 322 |
+
"learning_rate": 9.275651998382377e-06,
|
| 323 |
+
"loss": 0.8698,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5589307411907655,
|
| 328 |
+
"grad_norm": 0.6972896456718445,
|
| 329 |
+
"learning_rate": 8.874637770813947e-06,
|
| 330 |
+
"loss": 0.8872,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5710814094775213,
|
| 335 |
+
"grad_norm": 0.7595990300178528,
|
| 336 |
+
"learning_rate": 8.475448884896546e-06,
|
| 337 |
+
"loss": 0.8884,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.583232077764277,
|
| 342 |
+
"grad_norm": 0.7290850281715393,
|
| 343 |
+
"learning_rate": 8.078732826462917e-06,
|
| 344 |
+
"loss": 0.9027,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5953827460510328,
|
| 349 |
+
"grad_norm": 0.7032327055931091,
|
| 350 |
+
"learning_rate": 7.685133070410571e-06,
|
| 351 |
+
"loss": 0.8746,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6075334143377886,
|
| 356 |
+
"grad_norm": 0.7111395001411438,
|
| 357 |
+
"learning_rate": 7.2952880369831635e-06,
|
| 358 |
+
"loss": 0.8936,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6196840826245443,
|
| 363 |
+
"grad_norm": 0.7329614162445068,
|
| 364 |
+
"learning_rate": 6.909830056250527e-06,
|
| 365 |
+
"loss": 0.902,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6318347509113001,
|
| 370 |
+
"grad_norm": 0.7125659584999084,
|
| 371 |
+
"learning_rate": 6.529384342466971e-06,
|
| 372 |
+
"loss": 0.8933,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6439854191980559,
|
| 377 |
+
"grad_norm": 0.7025656700134277,
|
| 378 |
+
"learning_rate": 6.154567979971493e-06,
|
| 379 |
+
"loss": 0.8746,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6561360874848117,
|
| 384 |
+
"grad_norm": 0.7765396237373352,
|
| 385 |
+
"learning_rate": 5.785988922274711e-06,
|
| 386 |
+
"loss": 0.8776,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6682867557715675,
|
| 391 |
+
"grad_norm": 0.7155898213386536,
|
| 392 |
+
"learning_rate": 5.424245005956048e-06,
|
| 393 |
+
"loss": 0.8769,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6804374240583232,
|
| 398 |
+
"grad_norm": 0.6775897145271301,
|
| 399 |
+
"learning_rate": 5.069922980970626e-06,
|
| 400 |
+
"loss": 0.8598,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.692588092345079,
|
| 405 |
+
"grad_norm": 0.6870752573013306,
|
| 406 |
+
"learning_rate": 4.7235975589386715e-06,
|
| 407 |
+
"loss": 0.8896,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7047387606318347,
|
| 412 |
+
"grad_norm": 0.8218388557434082,
|
| 413 |
+
"learning_rate": 4.385830480961192e-06,
|
| 414 |
+
"loss": 0.8667,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7168894289185905,
|
| 419 |
+
"grad_norm": 0.7360238432884216,
|
| 420 |
+
"learning_rate": 4.057169606473828e-06,
|
| 421 |
+
"loss": 0.8857,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7290400972053463,
|
| 426 |
+
"grad_norm": 0.7152702212333679,
|
| 427 |
+
"learning_rate": 3.738148024616863e-06,
|
| 428 |
+
"loss": 0.8634,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.741190765492102,
|
| 433 |
+
"grad_norm": 0.670099675655365,
|
| 434 |
+
"learning_rate": 3.4292831895626944e-06,
|
| 435 |
+
"loss": 0.8742,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7533414337788579,
|
| 440 |
+
"grad_norm": 0.6950808763504028,
|
| 441 |
+
"learning_rate": 3.131076081203247e-06,
|
| 442 |
+
"loss": 0.8554,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.7654921020656136,
|
| 447 |
+
"grad_norm": 0.6677831411361694,
|
| 448 |
+
"learning_rate": 2.8440103925587904e-06,
|
| 449 |
+
"loss": 0.8527,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7776427703523694,
|
| 454 |
+
"grad_norm": 0.7251385450363159,
|
| 455 |
+
"learning_rate": 2.5685517452260566e-06,
|
| 456 |
+
"loss": 0.8745,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7897934386391251,
|
| 461 |
+
"grad_norm": 0.6926601529121399,
|
| 462 |
+
"learning_rate": 2.3051469341383403e-06,
|
| 463 |
+
"loss": 0.8918,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8019441069258809,
|
| 468 |
+
"grad_norm": 0.7035492062568665,
|
| 469 |
+
"learning_rate": 2.0542232028624585e-06,
|
| 470 |
+
"loss": 0.8701,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8140947752126367,
|
| 475 |
+
"grad_norm": 0.6695080399513245,
|
| 476 |
+
"learning_rate": 1.8161875506081294e-06,
|
| 477 |
+
"loss": 0.875,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8262454434993924,
|
| 482 |
+
"grad_norm": 0.6605943441390991,
|
| 483 |
+
"learning_rate": 1.5914260720737796e-06,
|
| 484 |
+
"loss": 0.8567,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8383961117861483,
|
| 489 |
+
"grad_norm": 0.6579225659370422,
|
| 490 |
+
"learning_rate": 1.3803033311995072e-06,
|
| 491 |
+
"loss": 0.8646,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.850546780072904,
|
| 496 |
+
"grad_norm": 0.663512110710144,
|
| 497 |
+
"learning_rate": 1.1831617698430609e-06,
|
| 498 |
+
"loss": 0.8685,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8626974483596598,
|
| 503 |
+
"grad_norm": 0.6766116619110107,
|
| 504 |
+
"learning_rate": 1.0003211523378798e-06,
|
| 505 |
+
"loss": 0.8794,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8748481166464156,
|
| 510 |
+
"grad_norm": 0.6653870344161987,
|
| 511 |
+
"learning_rate": 8.320780468341761e-07,
|
| 512 |
+
"loss": 0.8728,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8869987849331713,
|
| 517 |
+
"grad_norm": 0.6814940571784973,
|
| 518 |
+
"learning_rate": 6.787053442643233e-07,
|
| 519 |
+
"loss": 0.8616,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8991494532199271,
|
| 524 |
+
"grad_norm": 0.6656913757324219,
|
| 525 |
+
"learning_rate": 5.404518157127481e-07,
|
| 526 |
+
"loss": 0.8737,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9113001215066828,
|
| 531 |
+
"grad_norm": 0.6845870018005371,
|
| 532 |
+
"learning_rate": 4.1754170890833777e-07,
|
| 533 |
+
"loss": 0.8772,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9234507897934386,
|
| 538 |
+
"grad_norm": 0.6904654502868652,
|
| 539 |
+
"learning_rate": 3.101743844937943e-07,
|
| 540 |
+
"loss": 0.8678,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.9356014580801945,
|
| 545 |
+
"grad_norm": 0.6672822833061218,
|
| 546 |
+
"learning_rate": 2.1852399266194312e-07,
|
| 547 |
+
"loss": 0.8726,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9477521263669502,
|
| 552 |
+
"grad_norm": 0.6618822813034058,
|
| 553 |
+
"learning_rate": 1.4273919068349184e-07,
|
| 554 |
+
"loss": 0.8508,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.959902794653706,
|
| 559 |
+
"grad_norm": 0.6553758382797241,
|
| 560 |
+
"learning_rate": 8.29429017843797e-08,
|
| 561 |
+
"loss": 0.8737,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.9720534629404617,
|
| 566 |
+
"grad_norm": 0.6471725106239319,
|
| 567 |
+
"learning_rate": 3.923211576387087e-08,
|
| 568 |
+
"loss": 0.8588,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9842041312272175,
|
| 573 |
+
"grad_norm": 0.6723016500473022,
|
| 574 |
+
"learning_rate": 1.1677731676733584e-08,
|
| 575 |
+
"loss": 0.881,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9963547995139733,
|
| 580 |
+
"grad_norm": 0.640786349773407,
|
| 581 |
+
"learning_rate": 3.244428347204398e-10,
|
| 582 |
+
"loss": 0.8539,
|
| 583 |
+
"step": 410
|
| 584 |
+
}
|
| 585 |
+
],
|
| 586 |
+
"logging_steps": 5,
|
| 587 |
+
"max_steps": 411,
|
| 588 |
+
"num_input_tokens_seen": 0,
|
| 589 |
+
"num_train_epochs": 1,
|
| 590 |
+
"save_steps": 500,
|
| 591 |
+
"stateful_callbacks": {
|
| 592 |
+
"TrainerControl": {
|
| 593 |
+
"args": {
|
| 594 |
+
"should_epoch_stop": false,
|
| 595 |
+
"should_evaluate": false,
|
| 596 |
+
"should_log": false,
|
| 597 |
+
"should_save": true,
|
| 598 |
+
"should_training_stop": true
|
| 599 |
+
},
|
| 600 |
+
"attributes": {}
|
| 601 |
+
}
|
| 602 |
+
},
|
| 603 |
+
"total_flos": 1.267367944707375e+18,
|
| 604 |
+
"train_batch_size": 4,
|
| 605 |
+
"trial_name": null,
|
| 606 |
+
"trial_params": null
|
| 607 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128001,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 14336,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": {
|
| 24 |
+
"factor": 8.0,
|
| 25 |
+
"high_freq_factor": 4.0,
|
| 26 |
+
"low_freq_factor": 1.0,
|
| 27 |
+
"original_max_position_embeddings": 8192,
|
| 28 |
+
"rope_type": "llama3"
|
| 29 |
+
},
|
| 30 |
+
"rope_theta": 500000.0,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.46.0",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 128256
|
| 36 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"eos_token_id": 128001,
|
| 5 |
+
"transformers_version": "4.46.0",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ff22c11945e826fdca79bb81974b16e84faf0222d14d7da2f22fb151aaf537f
|
| 3 |
+
size 4886466168
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:644ae099672f64f43785d6ef3dae0baeb8202fa492d11ece7a0bb78559b34884
|
| 3 |
+
size 4832007448
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f49f215d49a4bea68f2a054ffafe3a0de1806f386c5ce6929c41c6353a4220c
|
| 3 |
+
size 4999813112
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c74a66b432805bc5cccf1db60cb03dfe5f3d4622f113be012f3ac55fbb89e1
|
| 3 |
+
size 4999813128
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df7ff2716122581c0cb72d16e26c1cb7679847cd85ff8063047f22d7e13001b7
|
| 3 |
+
size 4832007496
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f0a3a54d6b45afd15e8285bd4d3fc9087a37489b315584cdcbc7419f5af74b6
|
| 3 |
+
size 4999813120
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:686e3da87effdb4044633a0c5e05128881c43b67aead10b6ba0f3d2478ca213f
|
| 3 |
+
size 2571158184
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 32121044992
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00007-of-00007.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00007-of-00007.safetensors"
|
| 297 |
+
}
|
| 298 |
+
}
|
runs/Jun20_09-56-47_hakone/events.out.tfevents.1750427946.hakone.1502283.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8520c32c2d095937e1835b528046b294279652b18c15999d22d754e46d82f9a6
|
| 3 |
+
size 6457
|
runs/Jun20_10-02-28_hakone/events.out.tfevents.1750428275.hakone.1507035.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d856e4956c2de3d85c7b8d63b8a540ab3f85e2ca701e3d0a18e7994f00043d4
|
| 3 |
+
size 6457
|
runs/Jun20_13-15-13_hakone/events.out.tfevents.1750439726.hakone.1542090.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:340b562a1ba27e38d67a3b1787b4b5ae824fcaec2981502e8c8091032d7152c0
|
| 3 |
+
size 24013
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end▁of▁sentence|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end▁of▁sentence|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
|
| 3 |
+
size 17209530
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2066 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"128000": {
|
| 7 |
+
"content": "<|begin▁of▁sentence|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"128001": {
|
| 15 |
+
"content": "<|end▁of▁sentence|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"128002": {
|
| 23 |
+
"content": "<|reserved_special_token_0|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"128003": {
|
| 31 |
+
"content": "<|reserved_special_token_1|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"128004": {
|
| 39 |
+
"content": "<|finetune_right_pad_id|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"128005": {
|
| 47 |
+
"content": "<|reserved_special_token_2|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"128006": {
|
| 55 |
+
"content": "<|start_header_id|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"128007": {
|
| 63 |
+
"content": "<|end_header_id|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"128008": {
|
| 71 |
+
"content": "<|eom_id|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"128009": {
|
| 79 |
+
"content": "<|eot_id|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"128010": {
|
| 87 |
+
"content": "<|python_tag|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"128011": {
|
| 95 |
+
"content": "<|User|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"128012": {
|
| 103 |
+
"content": "<|Assistant|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"128013": {
|
| 111 |
+
"content": "<think>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"128014": {
|
| 119 |
+
"content": "</think>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"128015": {
|
| 127 |
+
"content": "<|▁pad▁|>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"128016": {
|
| 135 |
+
"content": "<|reserved_special_token_8|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": true
|
| 141 |
+
},
|
| 142 |
+
"128017": {
|
| 143 |
+
"content": "<|reserved_special_token_9|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
"128018": {
|
| 151 |
+
"content": "<|reserved_special_token_10|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": true
|
| 157 |
+
},
|
| 158 |
+
"128019": {
|
| 159 |
+
"content": "<|reserved_special_token_11|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": true
|
| 165 |
+
},
|
| 166 |
+
"128020": {
|
| 167 |
+
"content": "<|reserved_special_token_12|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": true
|
| 173 |
+
},
|
| 174 |
+
"128021": {
|
| 175 |
+
"content": "<|reserved_special_token_13|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
},
|
| 182 |
+
"128022": {
|
| 183 |
+
"content": "<|reserved_special_token_14|>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": true
|
| 189 |
+
},
|
| 190 |
+
"128023": {
|
| 191 |
+
"content": "<|reserved_special_token_15|>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": true
|
| 197 |
+
},
|
| 198 |
+
"128024": {
|
| 199 |
+
"content": "<|reserved_special_token_16|>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": true
|
| 205 |
+
},
|
| 206 |
+
"128025": {
|
| 207 |
+
"content": "<|reserved_special_token_17|>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": true
|
| 213 |
+
},
|
| 214 |
+
"128026": {
|
| 215 |
+
"content": "<|reserved_special_token_18|>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"128027": {
|
| 223 |
+
"content": "<|reserved_special_token_19|>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"128028": {
|
| 231 |
+
"content": "<|reserved_special_token_20|>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"128029": {
|
| 239 |
+
"content": "<|reserved_special_token_21|>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"128030": {
|
| 247 |
+
"content": "<|reserved_special_token_22|>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"128031": {
|
| 255 |
+
"content": "<|reserved_special_token_23|>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"128032": {
|
| 263 |
+
"content": "<|reserved_special_token_24|>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"128033": {
|
| 271 |
+
"content": "<|reserved_special_token_25|>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"128034": {
|
| 279 |
+
"content": "<|reserved_special_token_26|>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"128035": {
|
| 287 |
+
"content": "<|reserved_special_token_27|>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"128036": {
|
| 295 |
+
"content": "<|reserved_special_token_28|>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"128037": {
|
| 303 |
+
"content": "<|reserved_special_token_29|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
"128038": {
|
| 311 |
+
"content": "<|reserved_special_token_30|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": true
|
| 317 |
+
},
|
| 318 |
+
"128039": {
|
| 319 |
+
"content": "<|reserved_special_token_31|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
"128040": {
|
| 327 |
+
"content": "<|reserved_special_token_32|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": true
|
| 333 |
+
},
|
| 334 |
+
"128041": {
|
| 335 |
+
"content": "<|reserved_special_token_33|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": true
|
| 341 |
+
},
|
| 342 |
+
"128042": {
|
| 343 |
+
"content": "<|reserved_special_token_34|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": true
|
| 349 |
+
},
|
| 350 |
+
"128043": {
|
| 351 |
+
"content": "<|reserved_special_token_35|>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": true
|
| 357 |
+
},
|
| 358 |
+
"128044": {
|
| 359 |
+
"content": "<|reserved_special_token_36|>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
"128045": {
|
| 367 |
+
"content": "<|reserved_special_token_37|>",
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"normalized": false,
|
| 370 |
+
"rstrip": false,
|
| 371 |
+
"single_word": false,
|
| 372 |
+
"special": true
|
| 373 |
+
},
|
| 374 |
+
"128046": {
|
| 375 |
+
"content": "<|reserved_special_token_38|>",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
"128047": {
|
| 383 |
+
"content": "<|reserved_special_token_39|>",
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"normalized": false,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"special": true
|
| 389 |
+
},
|
| 390 |
+
"128048": {
|
| 391 |
+
"content": "<|reserved_special_token_40|>",
|
| 392 |
+
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
"128049": {
|
| 399 |
+
"content": "<|reserved_special_token_41|>",
|
| 400 |
+
"lstrip": false,
|
| 401 |
+
"normalized": false,
|
| 402 |
+
"rstrip": false,
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"special": true
|
| 405 |
+
},
|
| 406 |
+
"128050": {
|
| 407 |
+
"content": "<|reserved_special_token_42|>",
|
| 408 |
+
"lstrip": false,
|
| 409 |
+
"normalized": false,
|
| 410 |
+
"rstrip": false,
|
| 411 |
+
"single_word": false,
|
| 412 |
+
"special": true
|
| 413 |
+
},
|
| 414 |
+
"128051": {
|
| 415 |
+
"content": "<|reserved_special_token_43|>",
|
| 416 |
+
"lstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"rstrip": false,
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"special": true
|
| 421 |
+
},
|
| 422 |
+
"128052": {
|
| 423 |
+
"content": "<|reserved_special_token_44|>",
|
| 424 |
+
"lstrip": false,
|
| 425 |
+
"normalized": false,
|
| 426 |
+
"rstrip": false,
|
| 427 |
+
"single_word": false,
|
| 428 |
+
"special": true
|
| 429 |
+
},
|
| 430 |
+
"128053": {
|
| 431 |
+
"content": "<|reserved_special_token_45|>",
|
| 432 |
+
"lstrip": false,
|
| 433 |
+
"normalized": false,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"single_word": false,
|
| 436 |
+
"special": true
|
| 437 |
+
},
|
| 438 |
+
"128054": {
|
| 439 |
+
"content": "<|reserved_special_token_46|>",
|
| 440 |
+
"lstrip": false,
|
| 441 |
+
"normalized": false,
|
| 442 |
+
"rstrip": false,
|
| 443 |
+
"single_word": false,
|
| 444 |
+
"special": true
|
| 445 |
+
},
|
| 446 |
+
"128055": {
|
| 447 |
+
"content": "<|reserved_special_token_47|>",
|
| 448 |
+
"lstrip": false,
|
| 449 |
+
"normalized": false,
|
| 450 |
+
"rstrip": false,
|
| 451 |
+
"single_word": false,
|
| 452 |
+
"special": true
|
| 453 |
+
},
|
| 454 |
+
"128056": {
|
| 455 |
+
"content": "<|reserved_special_token_48|>",
|
| 456 |
+
"lstrip": false,
|
| 457 |
+
"normalized": false,
|
| 458 |
+
"rstrip": false,
|
| 459 |
+
"single_word": false,
|
| 460 |
+
"special": true
|
| 461 |
+
},
|
| 462 |
+
"128057": {
|
| 463 |
+
"content": "<|reserved_special_token_49|>",
|
| 464 |
+
"lstrip": false,
|
| 465 |
+
"normalized": false,
|
| 466 |
+
"rstrip": false,
|
| 467 |
+
"single_word": false,
|
| 468 |
+
"special": true
|
| 469 |
+
},
|
| 470 |
+
"128058": {
|
| 471 |
+
"content": "<|reserved_special_token_50|>",
|
| 472 |
+
"lstrip": false,
|
| 473 |
+
"normalized": false,
|
| 474 |
+
"rstrip": false,
|
| 475 |
+
"single_word": false,
|
| 476 |
+
"special": true
|
| 477 |
+
},
|
| 478 |
+
"128059": {
|
| 479 |
+
"content": "<|reserved_special_token_51|>",
|
| 480 |
+
"lstrip": false,
|
| 481 |
+
"normalized": false,
|
| 482 |
+
"rstrip": false,
|
| 483 |
+
"single_word": false,
|
| 484 |
+
"special": true
|
| 485 |
+
},
|
| 486 |
+
"128060": {
|
| 487 |
+
"content": "<|reserved_special_token_52|>",
|
| 488 |
+
"lstrip": false,
|
| 489 |
+
"normalized": false,
|
| 490 |
+
"rstrip": false,
|
| 491 |
+
"single_word": false,
|
| 492 |
+
"special": true
|
| 493 |
+
},
|
| 494 |
+
"128061": {
|
| 495 |
+
"content": "<|reserved_special_token_53|>",
|
| 496 |
+
"lstrip": false,
|
| 497 |
+
"normalized": false,
|
| 498 |
+
"rstrip": false,
|
| 499 |
+
"single_word": false,
|
| 500 |
+
"special": true
|
| 501 |
+
},
|
| 502 |
+
"128062": {
|
| 503 |
+
"content": "<|reserved_special_token_54|>",
|
| 504 |
+
"lstrip": false,
|
| 505 |
+
"normalized": false,
|
| 506 |
+
"rstrip": false,
|
| 507 |
+
"single_word": false,
|
| 508 |
+
"special": true
|
| 509 |
+
},
|
| 510 |
+
"128063": {
|
| 511 |
+
"content": "<|reserved_special_token_55|>",
|
| 512 |
+
"lstrip": false,
|
| 513 |
+
"normalized": false,
|
| 514 |
+
"rstrip": false,
|
| 515 |
+
"single_word": false,
|
| 516 |
+
"special": true
|
| 517 |
+
},
|
| 518 |
+
"128064": {
|
| 519 |
+
"content": "<|reserved_special_token_56|>",
|
| 520 |
+
"lstrip": false,
|
| 521 |
+
"normalized": false,
|
| 522 |
+
"rstrip": false,
|
| 523 |
+
"single_word": false,
|
| 524 |
+
"special": true
|
| 525 |
+
},
|
| 526 |
+
"128065": {
|
| 527 |
+
"content": "<|reserved_special_token_57|>",
|
| 528 |
+
"lstrip": false,
|
| 529 |
+
"normalized": false,
|
| 530 |
+
"rstrip": false,
|
| 531 |
+
"single_word": false,
|
| 532 |
+
"special": true
|
| 533 |
+
},
|
| 534 |
+
"128066": {
|
| 535 |
+
"content": "<|reserved_special_token_58|>",
|
| 536 |
+
"lstrip": false,
|
| 537 |
+
"normalized": false,
|
| 538 |
+
"rstrip": false,
|
| 539 |
+
"single_word": false,
|
| 540 |
+
"special": true
|
| 541 |
+
},
|
| 542 |
+
"128067": {
|
| 543 |
+
"content": "<|reserved_special_token_59|>",
|
| 544 |
+
"lstrip": false,
|
| 545 |
+
"normalized": false,
|
| 546 |
+
"rstrip": false,
|
| 547 |
+
"single_word": false,
|
| 548 |
+
"special": true
|
| 549 |
+
},
|
| 550 |
+
"128068": {
|
| 551 |
+
"content": "<|reserved_special_token_60|>",
|
| 552 |
+
"lstrip": false,
|
| 553 |
+
"normalized": false,
|
| 554 |
+
"rstrip": false,
|
| 555 |
+
"single_word": false,
|
| 556 |
+
"special": true
|
| 557 |
+
},
|
| 558 |
+
"128069": {
|
| 559 |
+
"content": "<|reserved_special_token_61|>",
|
| 560 |
+
"lstrip": false,
|
| 561 |
+
"normalized": false,
|
| 562 |
+
"rstrip": false,
|
| 563 |
+
"single_word": false,
|
| 564 |
+
"special": true
|
| 565 |
+
},
|
| 566 |
+
"128070": {
|
| 567 |
+
"content": "<|reserved_special_token_62|>",
|
| 568 |
+
"lstrip": false,
|
| 569 |
+
"normalized": false,
|
| 570 |
+
"rstrip": false,
|
| 571 |
+
"single_word": false,
|
| 572 |
+
"special": true
|
| 573 |
+
},
|
| 574 |
+
"128071": {
|
| 575 |
+
"content": "<|reserved_special_token_63|>",
|
| 576 |
+
"lstrip": false,
|
| 577 |
+
"normalized": false,
|
| 578 |
+
"rstrip": false,
|
| 579 |
+
"single_word": false,
|
| 580 |
+
"special": true
|
| 581 |
+
},
|
| 582 |
+
"128072": {
|
| 583 |
+
"content": "<|reserved_special_token_64|>",
|
| 584 |
+
"lstrip": false,
|
| 585 |
+
"normalized": false,
|
| 586 |
+
"rstrip": false,
|
| 587 |
+
"single_word": false,
|
| 588 |
+
"special": true
|
| 589 |
+
},
|
| 590 |
+
"128073": {
|
| 591 |
+
"content": "<|reserved_special_token_65|>",
|
| 592 |
+
"lstrip": false,
|
| 593 |
+
"normalized": false,
|
| 594 |
+
"rstrip": false,
|
| 595 |
+
"single_word": false,
|
| 596 |
+
"special": true
|
| 597 |
+
},
|
| 598 |
+
"128074": {
|
| 599 |
+
"content": "<|reserved_special_token_66|>",
|
| 600 |
+
"lstrip": false,
|
| 601 |
+
"normalized": false,
|
| 602 |
+
"rstrip": false,
|
| 603 |
+
"single_word": false,
|
| 604 |
+
"special": true
|
| 605 |
+
},
|
| 606 |
+
"128075": {
|
| 607 |
+
"content": "<|reserved_special_token_67|>",
|
| 608 |
+
"lstrip": false,
|
| 609 |
+
"normalized": false,
|
| 610 |
+
"rstrip": false,
|
| 611 |
+
"single_word": false,
|
| 612 |
+
"special": true
|
| 613 |
+
},
|
| 614 |
+
"128076": {
|
| 615 |
+
"content": "<|reserved_special_token_68|>",
|
| 616 |
+
"lstrip": false,
|
| 617 |
+
"normalized": false,
|
| 618 |
+
"rstrip": false,
|
| 619 |
+
"single_word": false,
|
| 620 |
+
"special": true
|
| 621 |
+
},
|
| 622 |
+
"128077": {
|
| 623 |
+
"content": "<|reserved_special_token_69|>",
|
| 624 |
+
"lstrip": false,
|
| 625 |
+
"normalized": false,
|
| 626 |
+
"rstrip": false,
|
| 627 |
+
"single_word": false,
|
| 628 |
+
"special": true
|
| 629 |
+
},
|
| 630 |
+
"128078": {
|
| 631 |
+
"content": "<|reserved_special_token_70|>",
|
| 632 |
+
"lstrip": false,
|
| 633 |
+
"normalized": false,
|
| 634 |
+
"rstrip": false,
|
| 635 |
+
"single_word": false,
|
| 636 |
+
"special": true
|
| 637 |
+
},
|
| 638 |
+
"128079": {
|
| 639 |
+
"content": "<|reserved_special_token_71|>",
|
| 640 |
+
"lstrip": false,
|
| 641 |
+
"normalized": false,
|
| 642 |
+
"rstrip": false,
|
| 643 |
+
"single_word": false,
|
| 644 |
+
"special": true
|
| 645 |
+
},
|
| 646 |
+
"128080": {
|
| 647 |
+
"content": "<|reserved_special_token_72|>",
|
| 648 |
+
"lstrip": false,
|
| 649 |
+
"normalized": false,
|
| 650 |
+
"rstrip": false,
|
| 651 |
+
"single_word": false,
|
| 652 |
+
"special": true
|
| 653 |
+
},
|
| 654 |
+
"128081": {
|
| 655 |
+
"content": "<|reserved_special_token_73|>",
|
| 656 |
+
"lstrip": false,
|
| 657 |
+
"normalized": false,
|
| 658 |
+
"rstrip": false,
|
| 659 |
+
"single_word": false,
|
| 660 |
+
"special": true
|
| 661 |
+
},
|
| 662 |
+
"128082": {
|
| 663 |
+
"content": "<|reserved_special_token_74|>",
|
| 664 |
+
"lstrip": false,
|
| 665 |
+
"normalized": false,
|
| 666 |
+
"rstrip": false,
|
| 667 |
+
"single_word": false,
|
| 668 |
+
"special": true
|
| 669 |
+
},
|
| 670 |
+
"128083": {
|
| 671 |
+
"content": "<|reserved_special_token_75|>",
|
| 672 |
+
"lstrip": false,
|
| 673 |
+
"normalized": false,
|
| 674 |
+
"rstrip": false,
|
| 675 |
+
"single_word": false,
|
| 676 |
+
"special": true
|
| 677 |
+
},
|
| 678 |
+
"128084": {
|
| 679 |
+
"content": "<|reserved_special_token_76|>",
|
| 680 |
+
"lstrip": false,
|
| 681 |
+
"normalized": false,
|
| 682 |
+
"rstrip": false,
|
| 683 |
+
"single_word": false,
|
| 684 |
+
"special": true
|
| 685 |
+
},
|
| 686 |
+
"128085": {
|
| 687 |
+
"content": "<|reserved_special_token_77|>",
|
| 688 |
+
"lstrip": false,
|
| 689 |
+
"normalized": false,
|
| 690 |
+
"rstrip": false,
|
| 691 |
+
"single_word": false,
|
| 692 |
+
"special": true
|
| 693 |
+
},
|
| 694 |
+
"128086": {
|
| 695 |
+
"content": "<|reserved_special_token_78|>",
|
| 696 |
+
"lstrip": false,
|
| 697 |
+
"normalized": false,
|
| 698 |
+
"rstrip": false,
|
| 699 |
+
"single_word": false,
|
| 700 |
+
"special": true
|
| 701 |
+
},
|
| 702 |
+
"128087": {
|
| 703 |
+
"content": "<|reserved_special_token_79|>",
|
| 704 |
+
"lstrip": false,
|
| 705 |
+
"normalized": false,
|
| 706 |
+
"rstrip": false,
|
| 707 |
+
"single_word": false,
|
| 708 |
+
"special": true
|
| 709 |
+
},
|
| 710 |
+
"128088": {
|
| 711 |
+
"content": "<|reserved_special_token_80|>",
|
| 712 |
+
"lstrip": false,
|
| 713 |
+
"normalized": false,
|
| 714 |
+
"rstrip": false,
|
| 715 |
+
"single_word": false,
|
| 716 |
+
"special": true
|
| 717 |
+
},
|
| 718 |
+
"128089": {
|
| 719 |
+
"content": "<|reserved_special_token_81|>",
|
| 720 |
+
"lstrip": false,
|
| 721 |
+
"normalized": false,
|
| 722 |
+
"rstrip": false,
|
| 723 |
+
"single_word": false,
|
| 724 |
+
"special": true
|
| 725 |
+
},
|
| 726 |
+
"128090": {
|
| 727 |
+
"content": "<|reserved_special_token_82|>",
|
| 728 |
+
"lstrip": false,
|
| 729 |
+
"normalized": false,
|
| 730 |
+
"rstrip": false,
|
| 731 |
+
"single_word": false,
|
| 732 |
+
"special": true
|
| 733 |
+
},
|
| 734 |
+
"128091": {
|
| 735 |
+
"content": "<|reserved_special_token_83|>",
|
| 736 |
+
"lstrip": false,
|
| 737 |
+
"normalized": false,
|
| 738 |
+
"rstrip": false,
|
| 739 |
+
"single_word": false,
|
| 740 |
+
"special": true
|
| 741 |
+
},
|
| 742 |
+
"128092": {
|
| 743 |
+
"content": "<|reserved_special_token_84|>",
|
| 744 |
+
"lstrip": false,
|
| 745 |
+
"normalized": false,
|
| 746 |
+
"rstrip": false,
|
| 747 |
+
"single_word": false,
|
| 748 |
+
"special": true
|
| 749 |
+
},
|
| 750 |
+
"128093": {
|
| 751 |
+
"content": "<|reserved_special_token_85|>",
|
| 752 |
+
"lstrip": false,
|
| 753 |
+
"normalized": false,
|
| 754 |
+
"rstrip": false,
|
| 755 |
+
"single_word": false,
|
| 756 |
+
"special": true
|
| 757 |
+
},
|
| 758 |
+
"128094": {
|
| 759 |
+
"content": "<|reserved_special_token_86|>",
|
| 760 |
+
"lstrip": false,
|
| 761 |
+
"normalized": false,
|
| 762 |
+
"rstrip": false,
|
| 763 |
+
"single_word": false,
|
| 764 |
+
"special": true
|
| 765 |
+
},
|
| 766 |
+
"128095": {
|
| 767 |
+
"content": "<|reserved_special_token_87|>",
|
| 768 |
+
"lstrip": false,
|
| 769 |
+
"normalized": false,
|
| 770 |
+
"rstrip": false,
|
| 771 |
+
"single_word": false,
|
| 772 |
+
"special": true
|
| 773 |
+
},
|
| 774 |
+
"128096": {
|
| 775 |
+
"content": "<|reserved_special_token_88|>",
|
| 776 |
+
"lstrip": false,
|
| 777 |
+
"normalized": false,
|
| 778 |
+
"rstrip": false,
|
| 779 |
+
"single_word": false,
|
| 780 |
+
"special": true
|
| 781 |
+
},
|
| 782 |
+
"128097": {
|
| 783 |
+
"content": "<|reserved_special_token_89|>",
|
| 784 |
+
"lstrip": false,
|
| 785 |
+
"normalized": false,
|
| 786 |
+
"rstrip": false,
|
| 787 |
+
"single_word": false,
|
| 788 |
+
"special": true
|
| 789 |
+
},
|
| 790 |
+
"128098": {
|
| 791 |
+
"content": "<|reserved_special_token_90|>",
|
| 792 |
+
"lstrip": false,
|
| 793 |
+
"normalized": false,
|
| 794 |
+
"rstrip": false,
|
| 795 |
+
"single_word": false,
|
| 796 |
+
"special": true
|
| 797 |
+
},
|
| 798 |
+
"128099": {
|
| 799 |
+
"content": "<|reserved_special_token_91|>",
|
| 800 |
+
"lstrip": false,
|
| 801 |
+
"normalized": false,
|
| 802 |
+
"rstrip": false,
|
| 803 |
+
"single_word": false,
|
| 804 |
+
"special": true
|
| 805 |
+
},
|
| 806 |
+
"128100": {
|
| 807 |
+
"content": "<|reserved_special_token_92|>",
|
| 808 |
+
"lstrip": false,
|
| 809 |
+
"normalized": false,
|
| 810 |
+
"rstrip": false,
|
| 811 |
+
"single_word": false,
|
| 812 |
+
"special": true
|
| 813 |
+
},
|
| 814 |
+
"128101": {
|
| 815 |
+
"content": "<|reserved_special_token_93|>",
|
| 816 |
+
"lstrip": false,
|
| 817 |
+
"normalized": false,
|
| 818 |
+
"rstrip": false,
|
| 819 |
+
"single_word": false,
|
| 820 |
+
"special": true
|
| 821 |
+
},
|
| 822 |
+
"128102": {
|
| 823 |
+
"content": "<|reserved_special_token_94|>",
|
| 824 |
+
"lstrip": false,
|
| 825 |
+
"normalized": false,
|
| 826 |
+
"rstrip": false,
|
| 827 |
+
"single_word": false,
|
| 828 |
+
"special": true
|
| 829 |
+
},
|
| 830 |
+
"128103": {
|
| 831 |
+
"content": "<|reserved_special_token_95|>",
|
| 832 |
+
"lstrip": false,
|
| 833 |
+
"normalized": false,
|
| 834 |
+
"rstrip": false,
|
| 835 |
+
"single_word": false,
|
| 836 |
+
"special": true
|
| 837 |
+
},
|
| 838 |
+
"128104": {
|
| 839 |
+
"content": "<|reserved_special_token_96|>",
|
| 840 |
+
"lstrip": false,
|
| 841 |
+
"normalized": false,
|
| 842 |
+
"rstrip": false,
|
| 843 |
+
"single_word": false,
|
| 844 |
+
"special": true
|
| 845 |
+
},
|
| 846 |
+
"128105": {
|
| 847 |
+
"content": "<|reserved_special_token_97|>",
|
| 848 |
+
"lstrip": false,
|
| 849 |
+
"normalized": false,
|
| 850 |
+
"rstrip": false,
|
| 851 |
+
"single_word": false,
|
| 852 |
+
"special": true
|
| 853 |
+
},
|
| 854 |
+
"128106": {
|
| 855 |
+
"content": "<|reserved_special_token_98|>",
|
| 856 |
+
"lstrip": false,
|
| 857 |
+
"normalized": false,
|
| 858 |
+
"rstrip": false,
|
| 859 |
+
"single_word": false,
|
| 860 |
+
"special": true
|
| 861 |
+
},
|
| 862 |
+
"128107": {
|
| 863 |
+
"content": "<|reserved_special_token_99|>",
|
| 864 |
+
"lstrip": false,
|
| 865 |
+
"normalized": false,
|
| 866 |
+
"rstrip": false,
|
| 867 |
+
"single_word": false,
|
| 868 |
+
"special": true
|
| 869 |
+
},
|
| 870 |
+
"128108": {
|
| 871 |
+
"content": "<|reserved_special_token_100|>",
|
| 872 |
+
"lstrip": false,
|
| 873 |
+
"normalized": false,
|
| 874 |
+
"rstrip": false,
|
| 875 |
+
"single_word": false,
|
| 876 |
+
"special": true
|
| 877 |
+
},
|
| 878 |
+
"128109": {
|
| 879 |
+
"content": "<|reserved_special_token_101|>",
|
| 880 |
+
"lstrip": false,
|
| 881 |
+
"normalized": false,
|
| 882 |
+
"rstrip": false,
|
| 883 |
+
"single_word": false,
|
| 884 |
+
"special": true
|
| 885 |
+
},
|
| 886 |
+
"128110": {
|
| 887 |
+
"content": "<|reserved_special_token_102|>",
|
| 888 |
+
"lstrip": false,
|
| 889 |
+
"normalized": false,
|
| 890 |
+
"rstrip": false,
|
| 891 |
+
"single_word": false,
|
| 892 |
+
"special": true
|
| 893 |
+
},
|
| 894 |
+
"128111": {
|
| 895 |
+
"content": "<|reserved_special_token_103|>",
|
| 896 |
+
"lstrip": false,
|
| 897 |
+
"normalized": false,
|
| 898 |
+
"rstrip": false,
|
| 899 |
+
"single_word": false,
|
| 900 |
+
"special": true
|
| 901 |
+
},
|
| 902 |
+
"128112": {
|
| 903 |
+
"content": "<|reserved_special_token_104|>",
|
| 904 |
+
"lstrip": false,
|
| 905 |
+
"normalized": false,
|
| 906 |
+
"rstrip": false,
|
| 907 |
+
"single_word": false,
|
| 908 |
+
"special": true
|
| 909 |
+
},
|
| 910 |
+
"128113": {
|
| 911 |
+
"content": "<|reserved_special_token_105|>",
|
| 912 |
+
"lstrip": false,
|
| 913 |
+
"normalized": false,
|
| 914 |
+
"rstrip": false,
|
| 915 |
+
"single_word": false,
|
| 916 |
+
"special": true
|
| 917 |
+
},
|
| 918 |
+
"128114": {
|
| 919 |
+
"content": "<|reserved_special_token_106|>",
|
| 920 |
+
"lstrip": false,
|
| 921 |
+
"normalized": false,
|
| 922 |
+
"rstrip": false,
|
| 923 |
+
"single_word": false,
|
| 924 |
+
"special": true
|
| 925 |
+
},
|
| 926 |
+
"128115": {
|
| 927 |
+
"content": "<|reserved_special_token_107|>",
|
| 928 |
+
"lstrip": false,
|
| 929 |
+
"normalized": false,
|
| 930 |
+
"rstrip": false,
|
| 931 |
+
"single_word": false,
|
| 932 |
+
"special": true
|
| 933 |
+
},
|
| 934 |
+
"128116": {
|
| 935 |
+
"content": "<|reserved_special_token_108|>",
|
| 936 |
+
"lstrip": false,
|
| 937 |
+
"normalized": false,
|
| 938 |
+
"rstrip": false,
|
| 939 |
+
"single_word": false,
|
| 940 |
+
"special": true
|
| 941 |
+
},
|
| 942 |
+
"128117": {
|
| 943 |
+
"content": "<|reserved_special_token_109|>",
|
| 944 |
+
"lstrip": false,
|
| 945 |
+
"normalized": false,
|
| 946 |
+
"rstrip": false,
|
| 947 |
+
"single_word": false,
|
| 948 |
+
"special": true
|
| 949 |
+
},
|
| 950 |
+
"128118": {
|
| 951 |
+
"content": "<|reserved_special_token_110|>",
|
| 952 |
+
"lstrip": false,
|
| 953 |
+
"normalized": false,
|
| 954 |
+
"rstrip": false,
|
| 955 |
+
"single_word": false,
|
| 956 |
+
"special": true
|
| 957 |
+
},
|
| 958 |
+
"128119": {
|
| 959 |
+
"content": "<|reserved_special_token_111|>",
|
| 960 |
+
"lstrip": false,
|
| 961 |
+
"normalized": false,
|
| 962 |
+
"rstrip": false,
|
| 963 |
+
"single_word": false,
|
| 964 |
+
"special": true
|
| 965 |
+
},
|
| 966 |
+
"128120": {
|
| 967 |
+
"content": "<|reserved_special_token_112|>",
|
| 968 |
+
"lstrip": false,
|
| 969 |
+
"normalized": false,
|
| 970 |
+
"rstrip": false,
|
| 971 |
+
"single_word": false,
|
| 972 |
+
"special": true
|
| 973 |
+
},
|
| 974 |
+
"128121": {
|
| 975 |
+
"content": "<|reserved_special_token_113|>",
|
| 976 |
+
"lstrip": false,
|
| 977 |
+
"normalized": false,
|
| 978 |
+
"rstrip": false,
|
| 979 |
+
"single_word": false,
|
| 980 |
+
"special": true
|
| 981 |
+
},
|
| 982 |
+
"128122": {
|
| 983 |
+
"content": "<|reserved_special_token_114|>",
|
| 984 |
+
"lstrip": false,
|
| 985 |
+
"normalized": false,
|
| 986 |
+
"rstrip": false,
|
| 987 |
+
"single_word": false,
|
| 988 |
+
"special": true
|
| 989 |
+
},
|
| 990 |
+
"128123": {
|
| 991 |
+
"content": "<|reserved_special_token_115|>",
|
| 992 |
+
"lstrip": false,
|
| 993 |
+
"normalized": false,
|
| 994 |
+
"rstrip": false,
|
| 995 |
+
"single_word": false,
|
| 996 |
+
"special": true
|
| 997 |
+
},
|
| 998 |
+
"128124": {
|
| 999 |
+
"content": "<|reserved_special_token_116|>",
|
| 1000 |
+
"lstrip": false,
|
| 1001 |
+
"normalized": false,
|
| 1002 |
+
"rstrip": false,
|
| 1003 |
+
"single_word": false,
|
| 1004 |
+
"special": true
|
| 1005 |
+
},
|
| 1006 |
+
"128125": {
|
| 1007 |
+
"content": "<|reserved_special_token_117|>",
|
| 1008 |
+
"lstrip": false,
|
| 1009 |
+
"normalized": false,
|
| 1010 |
+
"rstrip": false,
|
| 1011 |
+
"single_word": false,
|
| 1012 |
+
"special": true
|
| 1013 |
+
},
|
| 1014 |
+
"128126": {
|
| 1015 |
+
"content": "<|reserved_special_token_118|>",
|
| 1016 |
+
"lstrip": false,
|
| 1017 |
+
"normalized": false,
|
| 1018 |
+
"rstrip": false,
|
| 1019 |
+
"single_word": false,
|
| 1020 |
+
"special": true
|
| 1021 |
+
},
|
| 1022 |
+
"128127": {
|
| 1023 |
+
"content": "<|reserved_special_token_119|>",
|
| 1024 |
+
"lstrip": false,
|
| 1025 |
+
"normalized": false,
|
| 1026 |
+
"rstrip": false,
|
| 1027 |
+
"single_word": false,
|
| 1028 |
+
"special": true
|
| 1029 |
+
},
|
| 1030 |
+
"128128": {
|
| 1031 |
+
"content": "<|reserved_special_token_120|>",
|
| 1032 |
+
"lstrip": false,
|
| 1033 |
+
"normalized": false,
|
| 1034 |
+
"rstrip": false,
|
| 1035 |
+
"single_word": false,
|
| 1036 |
+
"special": true
|
| 1037 |
+
},
|
| 1038 |
+
"128129": {
|
| 1039 |
+
"content": "<|reserved_special_token_121|>",
|
| 1040 |
+
"lstrip": false,
|
| 1041 |
+
"normalized": false,
|
| 1042 |
+
"rstrip": false,
|
| 1043 |
+
"single_word": false,
|
| 1044 |
+
"special": true
|
| 1045 |
+
},
|
| 1046 |
+
"128130": {
|
| 1047 |
+
"content": "<|reserved_special_token_122|>",
|
| 1048 |
+
"lstrip": false,
|
| 1049 |
+
"normalized": false,
|
| 1050 |
+
"rstrip": false,
|
| 1051 |
+
"single_word": false,
|
| 1052 |
+
"special": true
|
| 1053 |
+
},
|
| 1054 |
+
"128131": {
|
| 1055 |
+
"content": "<|reserved_special_token_123|>",
|
| 1056 |
+
"lstrip": false,
|
| 1057 |
+
"normalized": false,
|
| 1058 |
+
"rstrip": false,
|
| 1059 |
+
"single_word": false,
|
| 1060 |
+
"special": true
|
| 1061 |
+
},
|
| 1062 |
+
"128132": {
|
| 1063 |
+
"content": "<|reserved_special_token_124|>",
|
| 1064 |
+
"lstrip": false,
|
| 1065 |
+
"normalized": false,
|
| 1066 |
+
"rstrip": false,
|
| 1067 |
+
"single_word": false,
|
| 1068 |
+
"special": true
|
| 1069 |
+
},
|
| 1070 |
+
"128133": {
|
| 1071 |
+
"content": "<|reserved_special_token_125|>",
|
| 1072 |
+
"lstrip": false,
|
| 1073 |
+
"normalized": false,
|
| 1074 |
+
"rstrip": false,
|
| 1075 |
+
"single_word": false,
|
| 1076 |
+
"special": true
|
| 1077 |
+
},
|
| 1078 |
+
"128134": {
|
| 1079 |
+
"content": "<|reserved_special_token_126|>",
|
| 1080 |
+
"lstrip": false,
|
| 1081 |
+
"normalized": false,
|
| 1082 |
+
"rstrip": false,
|
| 1083 |
+
"single_word": false,
|
| 1084 |
+
"special": true
|
| 1085 |
+
},
|
| 1086 |
+
"128135": {
|
| 1087 |
+
"content": "<|reserved_special_token_127|>",
|
| 1088 |
+
"lstrip": false,
|
| 1089 |
+
"normalized": false,
|
| 1090 |
+
"rstrip": false,
|
| 1091 |
+
"single_word": false,
|
| 1092 |
+
"special": true
|
| 1093 |
+
},
|
| 1094 |
+
"128136": {
|
| 1095 |
+
"content": "<|reserved_special_token_128|>",
|
| 1096 |
+
"lstrip": false,
|
| 1097 |
+
"normalized": false,
|
| 1098 |
+
"rstrip": false,
|
| 1099 |
+
"single_word": false,
|
| 1100 |
+
"special": true
|
| 1101 |
+
},
|
| 1102 |
+
"128137": {
|
| 1103 |
+
"content": "<|reserved_special_token_129|>",
|
| 1104 |
+
"lstrip": false,
|
| 1105 |
+
"normalized": false,
|
| 1106 |
+
"rstrip": false,
|
| 1107 |
+
"single_word": false,
|
| 1108 |
+
"special": true
|
| 1109 |
+
},
|
| 1110 |
+
"128138": {
|
| 1111 |
+
"content": "<|reserved_special_token_130|>",
|
| 1112 |
+
"lstrip": false,
|
| 1113 |
+
"normalized": false,
|
| 1114 |
+
"rstrip": false,
|
| 1115 |
+
"single_word": false,
|
| 1116 |
+
"special": true
|
| 1117 |
+
},
|
| 1118 |
+
"128139": {
|
| 1119 |
+
"content": "<|reserved_special_token_131|>",
|
| 1120 |
+
"lstrip": false,
|
| 1121 |
+
"normalized": false,
|
| 1122 |
+
"rstrip": false,
|
| 1123 |
+
"single_word": false,
|
| 1124 |
+
"special": true
|
| 1125 |
+
},
|
| 1126 |
+
"128140": {
|
| 1127 |
+
"content": "<|reserved_special_token_132|>",
|
| 1128 |
+
"lstrip": false,
|
| 1129 |
+
"normalized": false,
|
| 1130 |
+
"rstrip": false,
|
| 1131 |
+
"single_word": false,
|
| 1132 |
+
"special": true
|
| 1133 |
+
},
|
| 1134 |
+
"128141": {
|
| 1135 |
+
"content": "<|reserved_special_token_133|>",
|
| 1136 |
+
"lstrip": false,
|
| 1137 |
+
"normalized": false,
|
| 1138 |
+
"rstrip": false,
|
| 1139 |
+
"single_word": false,
|
| 1140 |
+
"special": true
|
| 1141 |
+
},
|
| 1142 |
+
"128142": {
|
| 1143 |
+
"content": "<|reserved_special_token_134|>",
|
| 1144 |
+
"lstrip": false,
|
| 1145 |
+
"normalized": false,
|
| 1146 |
+
"rstrip": false,
|
| 1147 |
+
"single_word": false,
|
| 1148 |
+
"special": true
|
| 1149 |
+
},
|
| 1150 |
+
"128143": {
|
| 1151 |
+
"content": "<|reserved_special_token_135|>",
|
| 1152 |
+
"lstrip": false,
|
| 1153 |
+
"normalized": false,
|
| 1154 |
+
"rstrip": false,
|
| 1155 |
+
"single_word": false,
|
| 1156 |
+
"special": true
|
| 1157 |
+
},
|
| 1158 |
+
"128144": {
|
| 1159 |
+
"content": "<|reserved_special_token_136|>",
|
| 1160 |
+
"lstrip": false,
|
| 1161 |
+
"normalized": false,
|
| 1162 |
+
"rstrip": false,
|
| 1163 |
+
"single_word": false,
|
| 1164 |
+
"special": true
|
| 1165 |
+
},
|
| 1166 |
+
"128145": {
|
| 1167 |
+
"content": "<|reserved_special_token_137|>",
|
| 1168 |
+
"lstrip": false,
|
| 1169 |
+
"normalized": false,
|
| 1170 |
+
"rstrip": false,
|
| 1171 |
+
"single_word": false,
|
| 1172 |
+
"special": true
|
| 1173 |
+
},
|
| 1174 |
+
"128146": {
|
| 1175 |
+
"content": "<|reserved_special_token_138|>",
|
| 1176 |
+
"lstrip": false,
|
| 1177 |
+
"normalized": false,
|
| 1178 |
+
"rstrip": false,
|
| 1179 |
+
"single_word": false,
|
| 1180 |
+
"special": true
|
| 1181 |
+
},
|
| 1182 |
+
"128147": {
|
| 1183 |
+
"content": "<|reserved_special_token_139|>",
|
| 1184 |
+
"lstrip": false,
|
| 1185 |
+
"normalized": false,
|
| 1186 |
+
"rstrip": false,
|
| 1187 |
+
"single_word": false,
|
| 1188 |
+
"special": true
|
| 1189 |
+
},
|
| 1190 |
+
"128148": {
|
| 1191 |
+
"content": "<|reserved_special_token_140|>",
|
| 1192 |
+
"lstrip": false,
|
| 1193 |
+
"normalized": false,
|
| 1194 |
+
"rstrip": false,
|
| 1195 |
+
"single_word": false,
|
| 1196 |
+
"special": true
|
| 1197 |
+
},
|
| 1198 |
+
"128149": {
|
| 1199 |
+
"content": "<|reserved_special_token_141|>",
|
| 1200 |
+
"lstrip": false,
|
| 1201 |
+
"normalized": false,
|
| 1202 |
+
"rstrip": false,
|
| 1203 |
+
"single_word": false,
|
| 1204 |
+
"special": true
|
| 1205 |
+
},
|
| 1206 |
+
"128150": {
|
| 1207 |
+
"content": "<|reserved_special_token_142|>",
|
| 1208 |
+
"lstrip": false,
|
| 1209 |
+
"normalized": false,
|
| 1210 |
+
"rstrip": false,
|
| 1211 |
+
"single_word": false,
|
| 1212 |
+
"special": true
|
| 1213 |
+
},
|
| 1214 |
+
"128151": {
|
| 1215 |
+
"content": "<|reserved_special_token_143|>",
|
| 1216 |
+
"lstrip": false,
|
| 1217 |
+
"normalized": false,
|
| 1218 |
+
"rstrip": false,
|
| 1219 |
+
"single_word": false,
|
| 1220 |
+
"special": true
|
| 1221 |
+
},
|
| 1222 |
+
"128152": {
|
| 1223 |
+
"content": "<|reserved_special_token_144|>",
|
| 1224 |
+
"lstrip": false,
|
| 1225 |
+
"normalized": false,
|
| 1226 |
+
"rstrip": false,
|
| 1227 |
+
"single_word": false,
|
| 1228 |
+
"special": true
|
| 1229 |
+
},
|
| 1230 |
+
"128153": {
|
| 1231 |
+
"content": "<|reserved_special_token_145|>",
|
| 1232 |
+
"lstrip": false,
|
| 1233 |
+
"normalized": false,
|
| 1234 |
+
"rstrip": false,
|
| 1235 |
+
"single_word": false,
|
| 1236 |
+
"special": true
|
| 1237 |
+
},
|
| 1238 |
+
"128154": {
|
| 1239 |
+
"content": "<|reserved_special_token_146|>",
|
| 1240 |
+
"lstrip": false,
|
| 1241 |
+
"normalized": false,
|
| 1242 |
+
"rstrip": false,
|
| 1243 |
+
"single_word": false,
|
| 1244 |
+
"special": true
|
| 1245 |
+
},
|
| 1246 |
+
"128155": {
|
| 1247 |
+
"content": "<|reserved_special_token_147|>",
|
| 1248 |
+
"lstrip": false,
|
| 1249 |
+
"normalized": false,
|
| 1250 |
+
"rstrip": false,
|
| 1251 |
+
"single_word": false,
|
| 1252 |
+
"special": true
|
| 1253 |
+
},
|
| 1254 |
+
"128156": {
|
| 1255 |
+
"content": "<|reserved_special_token_148|>",
|
| 1256 |
+
"lstrip": false,
|
| 1257 |
+
"normalized": false,
|
| 1258 |
+
"rstrip": false,
|
| 1259 |
+
"single_word": false,
|
| 1260 |
+
"special": true
|
| 1261 |
+
},
|
| 1262 |
+
"128157": {
|
| 1263 |
+
"content": "<|reserved_special_token_149|>",
|
| 1264 |
+
"lstrip": false,
|
| 1265 |
+
"normalized": false,
|
| 1266 |
+
"rstrip": false,
|
| 1267 |
+
"single_word": false,
|
| 1268 |
+
"special": true
|
| 1269 |
+
},
|
| 1270 |
+
"128158": {
|
| 1271 |
+
"content": "<|reserved_special_token_150|>",
|
| 1272 |
+
"lstrip": false,
|
| 1273 |
+
"normalized": false,
|
| 1274 |
+
"rstrip": false,
|
| 1275 |
+
"single_word": false,
|
| 1276 |
+
"special": true
|
| 1277 |
+
},
|
| 1278 |
+
"128159": {
|
| 1279 |
+
"content": "<|reserved_special_token_151|>",
|
| 1280 |
+
"lstrip": false,
|
| 1281 |
+
"normalized": false,
|
| 1282 |
+
"rstrip": false,
|
| 1283 |
+
"single_word": false,
|
| 1284 |
+
"special": true
|
| 1285 |
+
},
|
| 1286 |
+
"128160": {
|
| 1287 |
+
"content": "<|reserved_special_token_152|>",
|
| 1288 |
+
"lstrip": false,
|
| 1289 |
+
"normalized": false,
|
| 1290 |
+
"rstrip": false,
|
| 1291 |
+
"single_word": false,
|
| 1292 |
+
"special": true
|
| 1293 |
+
},
|
| 1294 |
+
"128161": {
|
| 1295 |
+
"content": "<|reserved_special_token_153|>",
|
| 1296 |
+
"lstrip": false,
|
| 1297 |
+
"normalized": false,
|
| 1298 |
+
"rstrip": false,
|
| 1299 |
+
"single_word": false,
|
| 1300 |
+
"special": true
|
| 1301 |
+
},
|
| 1302 |
+
"128162": {
|
| 1303 |
+
"content": "<|reserved_special_token_154|>",
|
| 1304 |
+
"lstrip": false,
|
| 1305 |
+
"normalized": false,
|
| 1306 |
+
"rstrip": false,
|
| 1307 |
+
"single_word": false,
|
| 1308 |
+
"special": true
|
| 1309 |
+
},
|
| 1310 |
+
"128163": {
|
| 1311 |
+
"content": "<|reserved_special_token_155|>",
|
| 1312 |
+
"lstrip": false,
|
| 1313 |
+
"normalized": false,
|
| 1314 |
+
"rstrip": false,
|
| 1315 |
+
"single_word": false,
|
| 1316 |
+
"special": true
|
| 1317 |
+
},
|
| 1318 |
+
"128164": {
|
| 1319 |
+
"content": "<|reserved_special_token_156|>",
|
| 1320 |
+
"lstrip": false,
|
| 1321 |
+
"normalized": false,
|
| 1322 |
+
"rstrip": false,
|
| 1323 |
+
"single_word": false,
|
| 1324 |
+
"special": true
|
| 1325 |
+
},
|
| 1326 |
+
"128165": {
|
| 1327 |
+
"content": "<|reserved_special_token_157|>",
|
| 1328 |
+
"lstrip": false,
|
| 1329 |
+
"normalized": false,
|
| 1330 |
+
"rstrip": false,
|
| 1331 |
+
"single_word": false,
|
| 1332 |
+
"special": true
|
| 1333 |
+
},
|
| 1334 |
+
"128166": {
|
| 1335 |
+
"content": "<|reserved_special_token_158|>",
|
| 1336 |
+
"lstrip": false,
|
| 1337 |
+
"normalized": false,
|
| 1338 |
+
"rstrip": false,
|
| 1339 |
+
"single_word": false,
|
| 1340 |
+
"special": true
|
| 1341 |
+
},
|
| 1342 |
+
"128167": {
|
| 1343 |
+
"content": "<|reserved_special_token_159|>",
|
| 1344 |
+
"lstrip": false,
|
| 1345 |
+
"normalized": false,
|
| 1346 |
+
"rstrip": false,
|
| 1347 |
+
"single_word": false,
|
| 1348 |
+
"special": true
|
| 1349 |
+
},
|
| 1350 |
+
"128168": {
|
| 1351 |
+
"content": "<|reserved_special_token_160|>",
|
| 1352 |
+
"lstrip": false,
|
| 1353 |
+
"normalized": false,
|
| 1354 |
+
"rstrip": false,
|
| 1355 |
+
"single_word": false,
|
| 1356 |
+
"special": true
|
| 1357 |
+
},
|
| 1358 |
+
"128169": {
|
| 1359 |
+
"content": "<|reserved_special_token_161|>",
|
| 1360 |
+
"lstrip": false,
|
| 1361 |
+
"normalized": false,
|
| 1362 |
+
"rstrip": false,
|
| 1363 |
+
"single_word": false,
|
| 1364 |
+
"special": true
|
| 1365 |
+
},
|
| 1366 |
+
"128170": {
|
| 1367 |
+
"content": "<|reserved_special_token_162|>",
|
| 1368 |
+
"lstrip": false,
|
| 1369 |
+
"normalized": false,
|
| 1370 |
+
"rstrip": false,
|
| 1371 |
+
"single_word": false,
|
| 1372 |
+
"special": true
|
| 1373 |
+
},
|
| 1374 |
+
"128171": {
|
| 1375 |
+
"content": "<|reserved_special_token_163|>",
|
| 1376 |
+
"lstrip": false,
|
| 1377 |
+
"normalized": false,
|
| 1378 |
+
"rstrip": false,
|
| 1379 |
+
"single_word": false,
|
| 1380 |
+
"special": true
|
| 1381 |
+
},
|
| 1382 |
+
"128172": {
|
| 1383 |
+
"content": "<|reserved_special_token_164|>",
|
| 1384 |
+
"lstrip": false,
|
| 1385 |
+
"normalized": false,
|
| 1386 |
+
"rstrip": false,
|
| 1387 |
+
"single_word": false,
|
| 1388 |
+
"special": true
|
| 1389 |
+
},
|
| 1390 |
+
"128173": {
|
| 1391 |
+
"content": "<|reserved_special_token_165|>",
|
| 1392 |
+
"lstrip": false,
|
| 1393 |
+
"normalized": false,
|
| 1394 |
+
"rstrip": false,
|
| 1395 |
+
"single_word": false,
|
| 1396 |
+
"special": true
|
| 1397 |
+
},
|
| 1398 |
+
"128174": {
|
| 1399 |
+
"content": "<|reserved_special_token_166|>",
|
| 1400 |
+
"lstrip": false,
|
| 1401 |
+
"normalized": false,
|
| 1402 |
+
"rstrip": false,
|
| 1403 |
+
"single_word": false,
|
| 1404 |
+
"special": true
|
| 1405 |
+
},
|
| 1406 |
+
"128175": {
|
| 1407 |
+
"content": "<|reserved_special_token_167|>",
|
| 1408 |
+
"lstrip": false,
|
| 1409 |
+
"normalized": false,
|
| 1410 |
+
"rstrip": false,
|
| 1411 |
+
"single_word": false,
|
| 1412 |
+
"special": true
|
| 1413 |
+
},
|
| 1414 |
+
"128176": {
|
| 1415 |
+
"content": "<|reserved_special_token_168|>",
|
| 1416 |
+
"lstrip": false,
|
| 1417 |
+
"normalized": false,
|
| 1418 |
+
"rstrip": false,
|
| 1419 |
+
"single_word": false,
|
| 1420 |
+
"special": true
|
| 1421 |
+
},
|
| 1422 |
+
"128177": {
|
| 1423 |
+
"content": "<|reserved_special_token_169|>",
|
| 1424 |
+
"lstrip": false,
|
| 1425 |
+
"normalized": false,
|
| 1426 |
+
"rstrip": false,
|
| 1427 |
+
"single_word": false,
|
| 1428 |
+
"special": true
|
| 1429 |
+
},
|
| 1430 |
+
"128178": {
|
| 1431 |
+
"content": "<|reserved_special_token_170|>",
|
| 1432 |
+
"lstrip": false,
|
| 1433 |
+
"normalized": false,
|
| 1434 |
+
"rstrip": false,
|
| 1435 |
+
"single_word": false,
|
| 1436 |
+
"special": true
|
| 1437 |
+
},
|
| 1438 |
+
"128179": {
|
| 1439 |
+
"content": "<|reserved_special_token_171|>",
|
| 1440 |
+
"lstrip": false,
|
| 1441 |
+
"normalized": false,
|
| 1442 |
+
"rstrip": false,
|
| 1443 |
+
"single_word": false,
|
| 1444 |
+
"special": true
|
| 1445 |
+
},
|
| 1446 |
+
"128180": {
|
| 1447 |
+
"content": "<|reserved_special_token_172|>",
|
| 1448 |
+
"lstrip": false,
|
| 1449 |
+
"normalized": false,
|
| 1450 |
+
"rstrip": false,
|
| 1451 |
+
"single_word": false,
|
| 1452 |
+
"special": true
|
| 1453 |
+
},
|
| 1454 |
+
"128181": {
|
| 1455 |
+
"content": "<|reserved_special_token_173|>",
|
| 1456 |
+
"lstrip": false,
|
| 1457 |
+
"normalized": false,
|
| 1458 |
+
"rstrip": false,
|
| 1459 |
+
"single_word": false,
|
| 1460 |
+
"special": true
|
| 1461 |
+
},
|
| 1462 |
+
"128182": {
|
| 1463 |
+
"content": "<|reserved_special_token_174|>",
|
| 1464 |
+
"lstrip": false,
|
| 1465 |
+
"normalized": false,
|
| 1466 |
+
"rstrip": false,
|
| 1467 |
+
"single_word": false,
|
| 1468 |
+
"special": true
|
| 1469 |
+
},
|
| 1470 |
+
"128183": {
|
| 1471 |
+
"content": "<|reserved_special_token_175|>",
|
| 1472 |
+
"lstrip": false,
|
| 1473 |
+
"normalized": false,
|
| 1474 |
+
"rstrip": false,
|
| 1475 |
+
"single_word": false,
|
| 1476 |
+
"special": true
|
| 1477 |
+
},
|
| 1478 |
+
"128184": {
|
| 1479 |
+
"content": "<|reserved_special_token_176|>",
|
| 1480 |
+
"lstrip": false,
|
| 1481 |
+
"normalized": false,
|
| 1482 |
+
"rstrip": false,
|
| 1483 |
+
"single_word": false,
|
| 1484 |
+
"special": true
|
| 1485 |
+
},
|
| 1486 |
+
"128185": {
|
| 1487 |
+
"content": "<|reserved_special_token_177|>",
|
| 1488 |
+
"lstrip": false,
|
| 1489 |
+
"normalized": false,
|
| 1490 |
+
"rstrip": false,
|
| 1491 |
+
"single_word": false,
|
| 1492 |
+
"special": true
|
| 1493 |
+
},
|
| 1494 |
+
"128186": {
|
| 1495 |
+
"content": "<|reserved_special_token_178|>",
|
| 1496 |
+
"lstrip": false,
|
| 1497 |
+
"normalized": false,
|
| 1498 |
+
"rstrip": false,
|
| 1499 |
+
"single_word": false,
|
| 1500 |
+
"special": true
|
| 1501 |
+
},
|
| 1502 |
+
"128187": {
|
| 1503 |
+
"content": "<|reserved_special_token_179|>",
|
| 1504 |
+
"lstrip": false,
|
| 1505 |
+
"normalized": false,
|
| 1506 |
+
"rstrip": false,
|
| 1507 |
+
"single_word": false,
|
| 1508 |
+
"special": true
|
| 1509 |
+
},
|
| 1510 |
+
"128188": {
|
| 1511 |
+
"content": "<|reserved_special_token_180|>",
|
| 1512 |
+
"lstrip": false,
|
| 1513 |
+
"normalized": false,
|
| 1514 |
+
"rstrip": false,
|
| 1515 |
+
"single_word": false,
|
| 1516 |
+
"special": true
|
| 1517 |
+
},
|
| 1518 |
+
"128189": {
|
| 1519 |
+
"content": "<|reserved_special_token_181|>",
|
| 1520 |
+
"lstrip": false,
|
| 1521 |
+
"normalized": false,
|
| 1522 |
+
"rstrip": false,
|
| 1523 |
+
"single_word": false,
|
| 1524 |
+
"special": true
|
| 1525 |
+
},
|
| 1526 |
+
"128190": {
|
| 1527 |
+
"content": "<|reserved_special_token_182|>",
|
| 1528 |
+
"lstrip": false,
|
| 1529 |
+
"normalized": false,
|
| 1530 |
+
"rstrip": false,
|
| 1531 |
+
"single_word": false,
|
| 1532 |
+
"special": true
|
| 1533 |
+
},
|
| 1534 |
+
"128191": {
|
| 1535 |
+
"content": "<|reserved_special_token_183|>",
|
| 1536 |
+
"lstrip": false,
|
| 1537 |
+
"normalized": false,
|
| 1538 |
+
"rstrip": false,
|
| 1539 |
+
"single_word": false,
|
| 1540 |
+
"special": true
|
| 1541 |
+
},
|
| 1542 |
+
"128192": {
|
| 1543 |
+
"content": "<|reserved_special_token_184|>",
|
| 1544 |
+
"lstrip": false,
|
| 1545 |
+
"normalized": false,
|
| 1546 |
+
"rstrip": false,
|
| 1547 |
+
"single_word": false,
|
| 1548 |
+
"special": true
|
| 1549 |
+
},
|
| 1550 |
+
"128193": {
|
| 1551 |
+
"content": "<|reserved_special_token_185|>",
|
| 1552 |
+
"lstrip": false,
|
| 1553 |
+
"normalized": false,
|
| 1554 |
+
"rstrip": false,
|
| 1555 |
+
"single_word": false,
|
| 1556 |
+
"special": true
|
| 1557 |
+
},
|
| 1558 |
+
"128194": {
|
| 1559 |
+
"content": "<|reserved_special_token_186|>",
|
| 1560 |
+
"lstrip": false,
|
| 1561 |
+
"normalized": false,
|
| 1562 |
+
"rstrip": false,
|
| 1563 |
+
"single_word": false,
|
| 1564 |
+
"special": true
|
| 1565 |
+
},
|
| 1566 |
+
"128195": {
|
| 1567 |
+
"content": "<|reserved_special_token_187|>",
|
| 1568 |
+
"lstrip": false,
|
| 1569 |
+
"normalized": false,
|
| 1570 |
+
"rstrip": false,
|
| 1571 |
+
"single_word": false,
|
| 1572 |
+
"special": true
|
| 1573 |
+
},
|
| 1574 |
+
"128196": {
|
| 1575 |
+
"content": "<|reserved_special_token_188|>",
|
| 1576 |
+
"lstrip": false,
|
| 1577 |
+
"normalized": false,
|
| 1578 |
+
"rstrip": false,
|
| 1579 |
+
"single_word": false,
|
| 1580 |
+
"special": true
|
| 1581 |
+
},
|
| 1582 |
+
"128197": {
|
| 1583 |
+
"content": "<|reserved_special_token_189|>",
|
| 1584 |
+
"lstrip": false,
|
| 1585 |
+
"normalized": false,
|
| 1586 |
+
"rstrip": false,
|
| 1587 |
+
"single_word": false,
|
| 1588 |
+
"special": true
|
| 1589 |
+
},
|
| 1590 |
+
"128198": {
|
| 1591 |
+
"content": "<|reserved_special_token_190|>",
|
| 1592 |
+
"lstrip": false,
|
| 1593 |
+
"normalized": false,
|
| 1594 |
+
"rstrip": false,
|
| 1595 |
+
"single_word": false,
|
| 1596 |
+
"special": true
|
| 1597 |
+
},
|
| 1598 |
+
"128199": {
|
| 1599 |
+
"content": "<|reserved_special_token_191|>",
|
| 1600 |
+
"lstrip": false,
|
| 1601 |
+
"normalized": false,
|
| 1602 |
+
"rstrip": false,
|
| 1603 |
+
"single_word": false,
|
| 1604 |
+
"special": true
|
| 1605 |
+
},
|
| 1606 |
+
"128200": {
|
| 1607 |
+
"content": "<|reserved_special_token_192|>",
|
| 1608 |
+
"lstrip": false,
|
| 1609 |
+
"normalized": false,
|
| 1610 |
+
"rstrip": false,
|
| 1611 |
+
"single_word": false,
|
| 1612 |
+
"special": true
|
| 1613 |
+
},
|
| 1614 |
+
"128201": {
|
| 1615 |
+
"content": "<|reserved_special_token_193|>",
|
| 1616 |
+
"lstrip": false,
|
| 1617 |
+
"normalized": false,
|
| 1618 |
+
"rstrip": false,
|
| 1619 |
+
"single_word": false,
|
| 1620 |
+
"special": true
|
| 1621 |
+
},
|
| 1622 |
+
"128202": {
|
| 1623 |
+
"content": "<|reserved_special_token_194|>",
|
| 1624 |
+
"lstrip": false,
|
| 1625 |
+
"normalized": false,
|
| 1626 |
+
"rstrip": false,
|
| 1627 |
+
"single_word": false,
|
| 1628 |
+
"special": true
|
| 1629 |
+
},
|
| 1630 |
+
"128203": {
|
| 1631 |
+
"content": "<|reserved_special_token_195|>",
|
| 1632 |
+
"lstrip": false,
|
| 1633 |
+
"normalized": false,
|
| 1634 |
+
"rstrip": false,
|
| 1635 |
+
"single_word": false,
|
| 1636 |
+
"special": true
|
| 1637 |
+
},
|
| 1638 |
+
"128204": {
|
| 1639 |
+
"content": "<|reserved_special_token_196|>",
|
| 1640 |
+
"lstrip": false,
|
| 1641 |
+
"normalized": false,
|
| 1642 |
+
"rstrip": false,
|
| 1643 |
+
"single_word": false,
|
| 1644 |
+
"special": true
|
| 1645 |
+
},
|
| 1646 |
+
"128205": {
|
| 1647 |
+
"content": "<|reserved_special_token_197|>",
|
| 1648 |
+
"lstrip": false,
|
| 1649 |
+
"normalized": false,
|
| 1650 |
+
"rstrip": false,
|
| 1651 |
+
"single_word": false,
|
| 1652 |
+
"special": true
|
| 1653 |
+
},
|
| 1654 |
+
"128206": {
|
| 1655 |
+
"content": "<|reserved_special_token_198|>",
|
| 1656 |
+
"lstrip": false,
|
| 1657 |
+
"normalized": false,
|
| 1658 |
+
"rstrip": false,
|
| 1659 |
+
"single_word": false,
|
| 1660 |
+
"special": true
|
| 1661 |
+
},
|
| 1662 |
+
"128207": {
|
| 1663 |
+
"content": "<|reserved_special_token_199|>",
|
| 1664 |
+
"lstrip": false,
|
| 1665 |
+
"normalized": false,
|
| 1666 |
+
"rstrip": false,
|
| 1667 |
+
"single_word": false,
|
| 1668 |
+
"special": true
|
| 1669 |
+
},
|
| 1670 |
+
"128208": {
|
| 1671 |
+
"content": "<|reserved_special_token_200|>",
|
| 1672 |
+
"lstrip": false,
|
| 1673 |
+
"normalized": false,
|
| 1674 |
+
"rstrip": false,
|
| 1675 |
+
"single_word": false,
|
| 1676 |
+
"special": true
|
| 1677 |
+
},
|
| 1678 |
+
"128209": {
|
| 1679 |
+
"content": "<|reserved_special_token_201|>",
|
| 1680 |
+
"lstrip": false,
|
| 1681 |
+
"normalized": false,
|
| 1682 |
+
"rstrip": false,
|
| 1683 |
+
"single_word": false,
|
| 1684 |
+
"special": true
|
| 1685 |
+
},
|
| 1686 |
+
"128210": {
|
| 1687 |
+
"content": "<|reserved_special_token_202|>",
|
| 1688 |
+
"lstrip": false,
|
| 1689 |
+
"normalized": false,
|
| 1690 |
+
"rstrip": false,
|
| 1691 |
+
"single_word": false,
|
| 1692 |
+
"special": true
|
| 1693 |
+
},
|
| 1694 |
+
"128211": {
|
| 1695 |
+
"content": "<|reserved_special_token_203|>",
|
| 1696 |
+
"lstrip": false,
|
| 1697 |
+
"normalized": false,
|
| 1698 |
+
"rstrip": false,
|
| 1699 |
+
"single_word": false,
|
| 1700 |
+
"special": true
|
| 1701 |
+
},
|
| 1702 |
+
"128212": {
|
| 1703 |
+
"content": "<|reserved_special_token_204|>",
|
| 1704 |
+
"lstrip": false,
|
| 1705 |
+
"normalized": false,
|
| 1706 |
+
"rstrip": false,
|
| 1707 |
+
"single_word": false,
|
| 1708 |
+
"special": true
|
| 1709 |
+
},
|
| 1710 |
+
"128213": {
|
| 1711 |
+
"content": "<|reserved_special_token_205|>",
|
| 1712 |
+
"lstrip": false,
|
| 1713 |
+
"normalized": false,
|
| 1714 |
+
"rstrip": false,
|
| 1715 |
+
"single_word": false,
|
| 1716 |
+
"special": true
|
| 1717 |
+
},
|
| 1718 |
+
"128214": {
|
| 1719 |
+
"content": "<|reserved_special_token_206|>",
|
| 1720 |
+
"lstrip": false,
|
| 1721 |
+
"normalized": false,
|
| 1722 |
+
"rstrip": false,
|
| 1723 |
+
"single_word": false,
|
| 1724 |
+
"special": true
|
| 1725 |
+
},
|
| 1726 |
+
"128215": {
|
| 1727 |
+
"content": "<|reserved_special_token_207|>",
|
| 1728 |
+
"lstrip": false,
|
| 1729 |
+
"normalized": false,
|
| 1730 |
+
"rstrip": false,
|
| 1731 |
+
"single_word": false,
|
| 1732 |
+
"special": true
|
| 1733 |
+
},
|
| 1734 |
+
"128216": {
|
| 1735 |
+
"content": "<|reserved_special_token_208|>",
|
| 1736 |
+
"lstrip": false,
|
| 1737 |
+
"normalized": false,
|
| 1738 |
+
"rstrip": false,
|
| 1739 |
+
"single_word": false,
|
| 1740 |
+
"special": true
|
| 1741 |
+
},
|
| 1742 |
+
"128217": {
|
| 1743 |
+
"content": "<|reserved_special_token_209|>",
|
| 1744 |
+
"lstrip": false,
|
| 1745 |
+
"normalized": false,
|
| 1746 |
+
"rstrip": false,
|
| 1747 |
+
"single_word": false,
|
| 1748 |
+
"special": true
|
| 1749 |
+
},
|
| 1750 |
+
"128218": {
|
| 1751 |
+
"content": "<|reserved_special_token_210|>",
|
| 1752 |
+
"lstrip": false,
|
| 1753 |
+
"normalized": false,
|
| 1754 |
+
"rstrip": false,
|
| 1755 |
+
"single_word": false,
|
| 1756 |
+
"special": true
|
| 1757 |
+
},
|
| 1758 |
+
"128219": {
|
| 1759 |
+
"content": "<|reserved_special_token_211|>",
|
| 1760 |
+
"lstrip": false,
|
| 1761 |
+
"normalized": false,
|
| 1762 |
+
"rstrip": false,
|
| 1763 |
+
"single_word": false,
|
| 1764 |
+
"special": true
|
| 1765 |
+
},
|
| 1766 |
+
"128220": {
|
| 1767 |
+
"content": "<|reserved_special_token_212|>",
|
| 1768 |
+
"lstrip": false,
|
| 1769 |
+
"normalized": false,
|
| 1770 |
+
"rstrip": false,
|
| 1771 |
+
"single_word": false,
|
| 1772 |
+
"special": true
|
| 1773 |
+
},
|
| 1774 |
+
"128221": {
|
| 1775 |
+
"content": "<|reserved_special_token_213|>",
|
| 1776 |
+
"lstrip": false,
|
| 1777 |
+
"normalized": false,
|
| 1778 |
+
"rstrip": false,
|
| 1779 |
+
"single_word": false,
|
| 1780 |
+
"special": true
|
| 1781 |
+
},
|
| 1782 |
+
"128222": {
|
| 1783 |
+
"content": "<|reserved_special_token_214|>",
|
| 1784 |
+
"lstrip": false,
|
| 1785 |
+
"normalized": false,
|
| 1786 |
+
"rstrip": false,
|
| 1787 |
+
"single_word": false,
|
| 1788 |
+
"special": true
|
| 1789 |
+
},
|
| 1790 |
+
"128223": {
|
| 1791 |
+
"content": "<|reserved_special_token_215|>",
|
| 1792 |
+
"lstrip": false,
|
| 1793 |
+
"normalized": false,
|
| 1794 |
+
"rstrip": false,
|
| 1795 |
+
"single_word": false,
|
| 1796 |
+
"special": true
|
| 1797 |
+
},
|
| 1798 |
+
"128224": {
|
| 1799 |
+
"content": "<|reserved_special_token_216|>",
|
| 1800 |
+
"lstrip": false,
|
| 1801 |
+
"normalized": false,
|
| 1802 |
+
"rstrip": false,
|
| 1803 |
+
"single_word": false,
|
| 1804 |
+
"special": true
|
| 1805 |
+
},
|
| 1806 |
+
"128225": {
|
| 1807 |
+
"content": "<|reserved_special_token_217|>",
|
| 1808 |
+
"lstrip": false,
|
| 1809 |
+
"normalized": false,
|
| 1810 |
+
"rstrip": false,
|
| 1811 |
+
"single_word": false,
|
| 1812 |
+
"special": true
|
| 1813 |
+
},
|
| 1814 |
+
"128226": {
|
| 1815 |
+
"content": "<|reserved_special_token_218|>",
|
| 1816 |
+
"lstrip": false,
|
| 1817 |
+
"normalized": false,
|
| 1818 |
+
"rstrip": false,
|
| 1819 |
+
"single_word": false,
|
| 1820 |
+
"special": true
|
| 1821 |
+
},
|
| 1822 |
+
"128227": {
|
| 1823 |
+
"content": "<|reserved_special_token_219|>",
|
| 1824 |
+
"lstrip": false,
|
| 1825 |
+
"normalized": false,
|
| 1826 |
+
"rstrip": false,
|
| 1827 |
+
"single_word": false,
|
| 1828 |
+
"special": true
|
| 1829 |
+
},
|
| 1830 |
+
"128228": {
|
| 1831 |
+
"content": "<|reserved_special_token_220|>",
|
| 1832 |
+
"lstrip": false,
|
| 1833 |
+
"normalized": false,
|
| 1834 |
+
"rstrip": false,
|
| 1835 |
+
"single_word": false,
|
| 1836 |
+
"special": true
|
| 1837 |
+
},
|
| 1838 |
+
"128229": {
|
| 1839 |
+
"content": "<|reserved_special_token_221|>",
|
| 1840 |
+
"lstrip": false,
|
| 1841 |
+
"normalized": false,
|
| 1842 |
+
"rstrip": false,
|
| 1843 |
+
"single_word": false,
|
| 1844 |
+
"special": true
|
| 1845 |
+
},
|
| 1846 |
+
"128230": {
|
| 1847 |
+
"content": "<|reserved_special_token_222|>",
|
| 1848 |
+
"lstrip": false,
|
| 1849 |
+
"normalized": false,
|
| 1850 |
+
"rstrip": false,
|
| 1851 |
+
"single_word": false,
|
| 1852 |
+
"special": true
|
| 1853 |
+
},
|
| 1854 |
+
"128231": {
|
| 1855 |
+
"content": "<|reserved_special_token_223|>",
|
| 1856 |
+
"lstrip": false,
|
| 1857 |
+
"normalized": false,
|
| 1858 |
+
"rstrip": false,
|
| 1859 |
+
"single_word": false,
|
| 1860 |
+
"special": true
|
| 1861 |
+
},
|
| 1862 |
+
"128232": {
|
| 1863 |
+
"content": "<|reserved_special_token_224|>",
|
| 1864 |
+
"lstrip": false,
|
| 1865 |
+
"normalized": false,
|
| 1866 |
+
"rstrip": false,
|
| 1867 |
+
"single_word": false,
|
| 1868 |
+
"special": true
|
| 1869 |
+
},
|
| 1870 |
+
"128233": {
|
| 1871 |
+
"content": "<|reserved_special_token_225|>",
|
| 1872 |
+
"lstrip": false,
|
| 1873 |
+
"normalized": false,
|
| 1874 |
+
"rstrip": false,
|
| 1875 |
+
"single_word": false,
|
| 1876 |
+
"special": true
|
| 1877 |
+
},
|
| 1878 |
+
"128234": {
|
| 1879 |
+
"content": "<|reserved_special_token_226|>",
|
| 1880 |
+
"lstrip": false,
|
| 1881 |
+
"normalized": false,
|
| 1882 |
+
"rstrip": false,
|
| 1883 |
+
"single_word": false,
|
| 1884 |
+
"special": true
|
| 1885 |
+
},
|
| 1886 |
+
"128235": {
|
| 1887 |
+
"content": "<|reserved_special_token_227|>",
|
| 1888 |
+
"lstrip": false,
|
| 1889 |
+
"normalized": false,
|
| 1890 |
+
"rstrip": false,
|
| 1891 |
+
"single_word": false,
|
| 1892 |
+
"special": true
|
| 1893 |
+
},
|
| 1894 |
+
"128236": {
|
| 1895 |
+
"content": "<|reserved_special_token_228|>",
|
| 1896 |
+
"lstrip": false,
|
| 1897 |
+
"normalized": false,
|
| 1898 |
+
"rstrip": false,
|
| 1899 |
+
"single_word": false,
|
| 1900 |
+
"special": true
|
| 1901 |
+
},
|
| 1902 |
+
"128237": {
|
| 1903 |
+
"content": "<|reserved_special_token_229|>",
|
| 1904 |
+
"lstrip": false,
|
| 1905 |
+
"normalized": false,
|
| 1906 |
+
"rstrip": false,
|
| 1907 |
+
"single_word": false,
|
| 1908 |
+
"special": true
|
| 1909 |
+
},
|
| 1910 |
+
"128238": {
|
| 1911 |
+
"content": "<|reserved_special_token_230|>",
|
| 1912 |
+
"lstrip": false,
|
| 1913 |
+
"normalized": false,
|
| 1914 |
+
"rstrip": false,
|
| 1915 |
+
"single_word": false,
|
| 1916 |
+
"special": true
|
| 1917 |
+
},
|
| 1918 |
+
"128239": {
|
| 1919 |
+
"content": "<|reserved_special_token_231|>",
|
| 1920 |
+
"lstrip": false,
|
| 1921 |
+
"normalized": false,
|
| 1922 |
+
"rstrip": false,
|
| 1923 |
+
"single_word": false,
|
| 1924 |
+
"special": true
|
| 1925 |
+
},
|
| 1926 |
+
"128240": {
|
| 1927 |
+
"content": "<|reserved_special_token_232|>",
|
| 1928 |
+
"lstrip": false,
|
| 1929 |
+
"normalized": false,
|
| 1930 |
+
"rstrip": false,
|
| 1931 |
+
"single_word": false,
|
| 1932 |
+
"special": true
|
| 1933 |
+
},
|
| 1934 |
+
"128241": {
|
| 1935 |
+
"content": "<|reserved_special_token_233|>",
|
| 1936 |
+
"lstrip": false,
|
| 1937 |
+
"normalized": false,
|
| 1938 |
+
"rstrip": false,
|
| 1939 |
+
"single_word": false,
|
| 1940 |
+
"special": true
|
| 1941 |
+
},
|
| 1942 |
+
"128242": {
|
| 1943 |
+
"content": "<|reserved_special_token_234|>",
|
| 1944 |
+
"lstrip": false,
|
| 1945 |
+
"normalized": false,
|
| 1946 |
+
"rstrip": false,
|
| 1947 |
+
"single_word": false,
|
| 1948 |
+
"special": true
|
| 1949 |
+
},
|
| 1950 |
+
"128243": {
|
| 1951 |
+
"content": "<|reserved_special_token_235|>",
|
| 1952 |
+
"lstrip": false,
|
| 1953 |
+
"normalized": false,
|
| 1954 |
+
"rstrip": false,
|
| 1955 |
+
"single_word": false,
|
| 1956 |
+
"special": true
|
| 1957 |
+
},
|
| 1958 |
+
"128244": {
|
| 1959 |
+
"content": "<|reserved_special_token_236|>",
|
| 1960 |
+
"lstrip": false,
|
| 1961 |
+
"normalized": false,
|
| 1962 |
+
"rstrip": false,
|
| 1963 |
+
"single_word": false,
|
| 1964 |
+
"special": true
|
| 1965 |
+
},
|
| 1966 |
+
"128245": {
|
| 1967 |
+
"content": "<|reserved_special_token_237|>",
|
| 1968 |
+
"lstrip": false,
|
| 1969 |
+
"normalized": false,
|
| 1970 |
+
"rstrip": false,
|
| 1971 |
+
"single_word": false,
|
| 1972 |
+
"special": true
|
| 1973 |
+
},
|
| 1974 |
+
"128246": {
|
| 1975 |
+
"content": "<|reserved_special_token_238|>",
|
| 1976 |
+
"lstrip": false,
|
| 1977 |
+
"normalized": false,
|
| 1978 |
+
"rstrip": false,
|
| 1979 |
+
"single_word": false,
|
| 1980 |
+
"special": true
|
| 1981 |
+
},
|
| 1982 |
+
"128247": {
|
| 1983 |
+
"content": "<|reserved_special_token_239|>",
|
| 1984 |
+
"lstrip": false,
|
| 1985 |
+
"normalized": false,
|
| 1986 |
+
"rstrip": false,
|
| 1987 |
+
"single_word": false,
|
| 1988 |
+
"special": true
|
| 1989 |
+
},
|
| 1990 |
+
"128248": {
|
| 1991 |
+
"content": "<|reserved_special_token_240|>",
|
| 1992 |
+
"lstrip": false,
|
| 1993 |
+
"normalized": false,
|
| 1994 |
+
"rstrip": false,
|
| 1995 |
+
"single_word": false,
|
| 1996 |
+
"special": true
|
| 1997 |
+
},
|
| 1998 |
+
"128249": {
|
| 1999 |
+
"content": "<|reserved_special_token_241|>",
|
| 2000 |
+
"lstrip": false,
|
| 2001 |
+
"normalized": false,
|
| 2002 |
+
"rstrip": false,
|
| 2003 |
+
"single_word": false,
|
| 2004 |
+
"special": true
|
| 2005 |
+
},
|
| 2006 |
+
"128250": {
|
| 2007 |
+
"content": "<|reserved_special_token_242|>",
|
| 2008 |
+
"lstrip": false,
|
| 2009 |
+
"normalized": false,
|
| 2010 |
+
"rstrip": false,
|
| 2011 |
+
"single_word": false,
|
| 2012 |
+
"special": true
|
| 2013 |
+
},
|
| 2014 |
+
"128251": {
|
| 2015 |
+
"content": "<|reserved_special_token_243|>",
|
| 2016 |
+
"lstrip": false,
|
| 2017 |
+
"normalized": false,
|
| 2018 |
+
"rstrip": false,
|
| 2019 |
+
"single_word": false,
|
| 2020 |
+
"special": true
|
| 2021 |
+
},
|
| 2022 |
+
"128252": {
|
| 2023 |
+
"content": "<|reserved_special_token_244|>",
|
| 2024 |
+
"lstrip": false,
|
| 2025 |
+
"normalized": false,
|
| 2026 |
+
"rstrip": false,
|
| 2027 |
+
"single_word": false,
|
| 2028 |
+
"special": true
|
| 2029 |
+
},
|
| 2030 |
+
"128253": {
|
| 2031 |
+
"content": "<|reserved_special_token_245|>",
|
| 2032 |
+
"lstrip": false,
|
| 2033 |
+
"normalized": false,
|
| 2034 |
+
"rstrip": false,
|
| 2035 |
+
"single_word": false,
|
| 2036 |
+
"special": true
|
| 2037 |
+
},
|
| 2038 |
+
"128254": {
|
| 2039 |
+
"content": "<|reserved_special_token_246|>",
|
| 2040 |
+
"lstrip": false,
|
| 2041 |
+
"normalized": false,
|
| 2042 |
+
"rstrip": false,
|
| 2043 |
+
"single_word": false,
|
| 2044 |
+
"special": true
|
| 2045 |
+
},
|
| 2046 |
+
"128255": {
|
| 2047 |
+
"content": "<|reserved_special_token_247|>",
|
| 2048 |
+
"lstrip": false,
|
| 2049 |
+
"normalized": false,
|
| 2050 |
+
"rstrip": false,
|
| 2051 |
+
"single_word": false,
|
| 2052 |
+
"special": true
|
| 2053 |
+
}
|
| 2054 |
+
},
|
| 2055 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
| 2056 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}",
|
| 2057 |
+
"clean_up_tokenization_spaces": false,
|
| 2058 |
+
"eos_token": "<|end▁of▁sentence|>",
|
| 2059 |
+
"legacy": true,
|
| 2060 |
+
"model_max_length": 16384,
|
| 2061 |
+
"pad_token": "<|end▁of▁sentence|>",
|
| 2062 |
+
"sp_model_kwargs": {},
|
| 2063 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 2064 |
+
"unk_token": null,
|
| 2065 |
+
"use_default_system_prompt": false
|
| 2066 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9987849331713244,
|
| 3 |
+
"total_flos": 1.267367944707375e+18,
|
| 4 |
+
"train_loss": 0.9162624978671109,
|
| 5 |
+
"train_runtime": 10821.8058,
|
| 6 |
+
"train_samples": 37443,
|
| 7 |
+
"train_samples_per_second": 2.433,
|
| 8 |
+
"train_steps_per_second": 0.038
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9987849331713244,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 411,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012150668286755772,
|
| 13 |
+
"grad_norm": 4.5974345207214355,
|
| 14 |
+
"learning_rate": 4.761904761904762e-06,
|
| 15 |
+
"loss": 1.3953,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.024301336573511544,
|
| 20 |
+
"grad_norm": 2.528956651687622,
|
| 21 |
+
"learning_rate": 9.523809523809525e-06,
|
| 22 |
+
"loss": 1.2041,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03645200486026731,
|
| 27 |
+
"grad_norm": 1.4799861907958984,
|
| 28 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 29 |
+
"loss": 1.1068,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04860267314702309,
|
| 34 |
+
"grad_norm": 1.4184110164642334,
|
| 35 |
+
"learning_rate": 1.904761904761905e-05,
|
| 36 |
+
"loss": 1.0285,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.060753341433778855,
|
| 41 |
+
"grad_norm": 1.0306570529937744,
|
| 42 |
+
"learning_rate": 1.9994809335686152e-05,
|
| 43 |
+
"loss": 1.0168,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07290400972053462,
|
| 48 |
+
"grad_norm": 0.8752269744873047,
|
| 49 |
+
"learning_rate": 1.9973731496914914e-05,
|
| 50 |
+
"loss": 0.9848,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0850546780072904,
|
| 55 |
+
"grad_norm": 0.8289946913719177,
|
| 56 |
+
"learning_rate": 1.9936476229183133e-05,
|
| 57 |
+
"loss": 0.9947,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09720534629404617,
|
| 62 |
+
"grad_norm": 0.8398821353912354,
|
| 63 |
+
"learning_rate": 1.9883103960671305e-05,
|
| 64 |
+
"loss": 0.9783,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10935601458080195,
|
| 69 |
+
"grad_norm": 0.8018831610679626,
|
| 70 |
+
"learning_rate": 1.9813701261394136e-05,
|
| 71 |
+
"loss": 0.9788,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.12150668286755771,
|
| 76 |
+
"grad_norm": 0.8563551306724548,
|
| 77 |
+
"learning_rate": 1.9728380702783644e-05,
|
| 78 |
+
"loss": 0.9635,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1336573511543135,
|
| 83 |
+
"grad_norm": 0.746189296245575,
|
| 84 |
+
"learning_rate": 1.962728067509791e-05,
|
| 85 |
+
"loss": 0.9706,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.14580801944106925,
|
| 90 |
+
"grad_norm": 0.8066502809524536,
|
| 91 |
+
"learning_rate": 1.9510565162951538e-05,
|
| 92 |
+
"loss": 0.9456,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.15795868772782504,
|
| 97 |
+
"grad_norm": 0.7983813285827637,
|
| 98 |
+
"learning_rate": 1.9378423479332045e-05,
|
| 99 |
+
"loss": 0.9386,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1701093560145808,
|
| 104 |
+
"grad_norm": 0.7811228632926941,
|
| 105 |
+
"learning_rate": 1.923106995853349e-05,
|
| 106 |
+
"loss": 0.9432,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1822600243013366,
|
| 111 |
+
"grad_norm": 0.7911136746406555,
|
| 112 |
+
"learning_rate": 1.9068743608505454e-05,
|
| 113 |
+
"loss": 0.9538,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.19441069258809235,
|
| 118 |
+
"grad_norm": 0.7658519744873047,
|
| 119 |
+
"learning_rate": 1.8891707723181294e-05,
|
| 120 |
+
"loss": 0.9526,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2065613608748481,
|
| 125 |
+
"grad_norm": 0.8204901814460754,
|
| 126 |
+
"learning_rate": 1.8700249455414394e-05,
|
| 127 |
+
"loss": 0.937,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2187120291616039,
|
| 132 |
+
"grad_norm": 0.760960042476654,
|
| 133 |
+
"learning_rate": 1.8494679351215212e-05,
|
| 134 |
+
"loss": 0.9267,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.23086269744835966,
|
| 139 |
+
"grad_norm": 0.804595947265625,
|
| 140 |
+
"learning_rate": 1.82753308460445e-05,
|
| 141 |
+
"loss": 0.9276,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.24301336573511542,
|
| 146 |
+
"grad_norm": 2.3202602863311768,
|
| 147 |
+
"learning_rate": 1.804255972397977e-05,
|
| 148 |
+
"loss": 0.923,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2551640340218712,
|
| 153 |
+
"grad_norm": 0.7664303779602051,
|
| 154 |
+
"learning_rate": 1.7796743540632226e-05,
|
| 155 |
+
"loss": 0.9085,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.267314702308627,
|
| 160 |
+
"grad_norm": 0.8157963752746582,
|
| 161 |
+
"learning_rate": 1.753828101075017e-05,
|
| 162 |
+
"loss": 0.9501,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.27946537059538273,
|
| 167 |
+
"grad_norm": 0.8094449639320374,
|
| 168 |
+
"learning_rate": 1.7267591361502233e-05,
|
| 169 |
+
"loss": 0.9271,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2916160388821385,
|
| 174 |
+
"grad_norm": 0.9288702011108398,
|
| 175 |
+
"learning_rate": 1.6985113652489374e-05,
|
| 176 |
+
"loss": 0.9571,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3037667071688943,
|
| 181 |
+
"grad_norm": 0.84999018907547,
|
| 182 |
+
"learning_rate": 1.6691306063588583e-05,
|
| 183 |
+
"loss": 0.9042,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3159173754556501,
|
| 188 |
+
"grad_norm": 0.8100440502166748,
|
| 189 |
+
"learning_rate": 1.638664515178348e-05,
|
| 190 |
+
"loss": 0.9104,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.32806804374240583,
|
| 195 |
+
"grad_norm": 0.7512496113777161,
|
| 196 |
+
"learning_rate": 1.6071625078187113e-05,
|
| 197 |
+
"loss": 0.9129,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3402187120291616,
|
| 202 |
+
"grad_norm": 0.7866060733795166,
|
| 203 |
+
"learning_rate": 1.574675680651084e-05,
|
| 204 |
+
"loss": 0.9113,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.35236938031591736,
|
| 209 |
+
"grad_norm": 0.7891241908073425,
|
| 210 |
+
"learning_rate": 1.5412567274279316e-05,
|
| 211 |
+
"loss": 0.9286,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3645200486026732,
|
| 216 |
+
"grad_norm": 0.7657147645950317,
|
| 217 |
+
"learning_rate": 1.5069598538135905e-05,
|
| 218 |
+
"loss": 0.9302,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.37667071688942894,
|
| 223 |
+
"grad_norm": 0.7555293440818787,
|
| 224 |
+
"learning_rate": 1.471840689462482e-05,
|
| 225 |
+
"loss": 0.914,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3888213851761847,
|
| 230 |
+
"grad_norm": 0.7541491389274597,
|
| 231 |
+
"learning_rate": 1.4359561977876102e-05,
|
| 232 |
+
"loss": 0.9241,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.40097205346294046,
|
| 237 |
+
"grad_norm": 0.7439760565757751,
|
| 238 |
+
"learning_rate": 1.3993645835656955e-05,
|
| 239 |
+
"loss": 0.8976,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4131227217496962,
|
| 244 |
+
"grad_norm": 0.7437750697135925,
|
| 245 |
+
"learning_rate": 1.362125198528817e-05,
|
| 246 |
+
"loss": 0.9033,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.425273390036452,
|
| 251 |
+
"grad_norm": 0.7202824354171753,
|
| 252 |
+
"learning_rate": 1.3242984450956829e-05,
|
| 253 |
+
"loss": 0.9024,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4374240583232078,
|
| 258 |
+
"grad_norm": 0.7379337549209595,
|
| 259 |
+
"learning_rate": 1.2859456783986892e-05,
|
| 260 |
+
"loss": 0.8918,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.44957472660996356,
|
| 265 |
+
"grad_norm": 0.7616682648658752,
|
| 266 |
+
"learning_rate": 1.2471291067656696e-05,
|
| 267 |
+
"loss": 0.9167,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4617253948967193,
|
| 272 |
+
"grad_norm": 0.7680121660232544,
|
| 273 |
+
"learning_rate": 1.2079116908177592e-05,
|
| 274 |
+
"loss": 0.8958,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4738760631834751,
|
| 279 |
+
"grad_norm": 0.7707135081291199,
|
| 280 |
+
"learning_rate": 1.1683570413470384e-05,
|
| 281 |
+
"loss": 0.9227,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.48602673147023084,
|
| 286 |
+
"grad_norm": 0.7425935864448547,
|
| 287 |
+
"learning_rate": 1.1285293161395948e-05,
|
| 288 |
+
"loss": 0.8913,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.49817739975698666,
|
| 293 |
+
"grad_norm": 0.7188636660575867,
|
| 294 |
+
"learning_rate": 1.0884931159113585e-05,
|
| 295 |
+
"loss": 0.8897,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5103280680437424,
|
| 300 |
+
"grad_norm": 0.7420693039894104,
|
| 301 |
+
"learning_rate": 1.0483133795255072e-05,
|
| 302 |
+
"loss": 0.9006,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5224787363304981,
|
| 307 |
+
"grad_norm": 0.6850030422210693,
|
| 308 |
+
"learning_rate": 1.0080552786613899e-05,
|
| 309 |
+
"loss": 0.8779,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.534629404617254,
|
| 314 |
+
"grad_norm": 0.6989702582359314,
|
| 315 |
+
"learning_rate": 9.677841121058274e-06,
|
| 316 |
+
"loss": 0.8798,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5467800729040098,
|
| 321 |
+
"grad_norm": 0.7223166823387146,
|
| 322 |
+
"learning_rate": 9.275651998382377e-06,
|
| 323 |
+
"loss": 0.8698,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5589307411907655,
|
| 328 |
+
"grad_norm": 0.6972896456718445,
|
| 329 |
+
"learning_rate": 8.874637770813947e-06,
|
| 330 |
+
"loss": 0.8872,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5710814094775213,
|
| 335 |
+
"grad_norm": 0.7595990300178528,
|
| 336 |
+
"learning_rate": 8.475448884896546e-06,
|
| 337 |
+
"loss": 0.8884,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.583232077764277,
|
| 342 |
+
"grad_norm": 0.7290850281715393,
|
| 343 |
+
"learning_rate": 8.078732826462917e-06,
|
| 344 |
+
"loss": 0.9027,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5953827460510328,
|
| 349 |
+
"grad_norm": 0.7032327055931091,
|
| 350 |
+
"learning_rate": 7.685133070410571e-06,
|
| 351 |
+
"loss": 0.8746,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6075334143377886,
|
| 356 |
+
"grad_norm": 0.7111395001411438,
|
| 357 |
+
"learning_rate": 7.2952880369831635e-06,
|
| 358 |
+
"loss": 0.8936,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6196840826245443,
|
| 363 |
+
"grad_norm": 0.7329614162445068,
|
| 364 |
+
"learning_rate": 6.909830056250527e-06,
|
| 365 |
+
"loss": 0.902,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6318347509113001,
|
| 370 |
+
"grad_norm": 0.7125659584999084,
|
| 371 |
+
"learning_rate": 6.529384342466971e-06,
|
| 372 |
+
"loss": 0.8933,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6439854191980559,
|
| 377 |
+
"grad_norm": 0.7025656700134277,
|
| 378 |
+
"learning_rate": 6.154567979971493e-06,
|
| 379 |
+
"loss": 0.8746,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6561360874848117,
|
| 384 |
+
"grad_norm": 0.7765396237373352,
|
| 385 |
+
"learning_rate": 5.785988922274711e-06,
|
| 386 |
+
"loss": 0.8776,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6682867557715675,
|
| 391 |
+
"grad_norm": 0.7155898213386536,
|
| 392 |
+
"learning_rate": 5.424245005956048e-06,
|
| 393 |
+
"loss": 0.8769,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6804374240583232,
|
| 398 |
+
"grad_norm": 0.6775897145271301,
|
| 399 |
+
"learning_rate": 5.069922980970626e-06,
|
| 400 |
+
"loss": 0.8598,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.692588092345079,
|
| 405 |
+
"grad_norm": 0.6870752573013306,
|
| 406 |
+
"learning_rate": 4.7235975589386715e-06,
|
| 407 |
+
"loss": 0.8896,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7047387606318347,
|
| 412 |
+
"grad_norm": 0.8218388557434082,
|
| 413 |
+
"learning_rate": 4.385830480961192e-06,
|
| 414 |
+
"loss": 0.8667,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7168894289185905,
|
| 419 |
+
"grad_norm": 0.7360238432884216,
|
| 420 |
+
"learning_rate": 4.057169606473828e-06,
|
| 421 |
+
"loss": 0.8857,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7290400972053463,
|
| 426 |
+
"grad_norm": 0.7152702212333679,
|
| 427 |
+
"learning_rate": 3.738148024616863e-06,
|
| 428 |
+
"loss": 0.8634,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.741190765492102,
|
| 433 |
+
"grad_norm": 0.670099675655365,
|
| 434 |
+
"learning_rate": 3.4292831895626944e-06,
|
| 435 |
+
"loss": 0.8742,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7533414337788579,
|
| 440 |
+
"grad_norm": 0.6950808763504028,
|
| 441 |
+
"learning_rate": 3.131076081203247e-06,
|
| 442 |
+
"loss": 0.8554,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.7654921020656136,
|
| 447 |
+
"grad_norm": 0.6677831411361694,
|
| 448 |
+
"learning_rate": 2.8440103925587904e-06,
|
| 449 |
+
"loss": 0.8527,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7776427703523694,
|
| 454 |
+
"grad_norm": 0.7251385450363159,
|
| 455 |
+
"learning_rate": 2.5685517452260566e-06,
|
| 456 |
+
"loss": 0.8745,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7897934386391251,
|
| 461 |
+
"grad_norm": 0.6926601529121399,
|
| 462 |
+
"learning_rate": 2.3051469341383403e-06,
|
| 463 |
+
"loss": 0.8918,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8019441069258809,
|
| 468 |
+
"grad_norm": 0.7035492062568665,
|
| 469 |
+
"learning_rate": 2.0542232028624585e-06,
|
| 470 |
+
"loss": 0.8701,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8140947752126367,
|
| 475 |
+
"grad_norm": 0.6695080399513245,
|
| 476 |
+
"learning_rate": 1.8161875506081294e-06,
|
| 477 |
+
"loss": 0.875,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8262454434993924,
|
| 482 |
+
"grad_norm": 0.6605943441390991,
|
| 483 |
+
"learning_rate": 1.5914260720737796e-06,
|
| 484 |
+
"loss": 0.8567,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8383961117861483,
|
| 489 |
+
"grad_norm": 0.6579225659370422,
|
| 490 |
+
"learning_rate": 1.3803033311995072e-06,
|
| 491 |
+
"loss": 0.8646,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.850546780072904,
|
| 496 |
+
"grad_norm": 0.663512110710144,
|
| 497 |
+
"learning_rate": 1.1831617698430609e-06,
|
| 498 |
+
"loss": 0.8685,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8626974483596598,
|
| 503 |
+
"grad_norm": 0.6766116619110107,
|
| 504 |
+
"learning_rate": 1.0003211523378798e-06,
|
| 505 |
+
"loss": 0.8794,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8748481166464156,
|
| 510 |
+
"grad_norm": 0.6653870344161987,
|
| 511 |
+
"learning_rate": 8.320780468341761e-07,
|
| 512 |
+
"loss": 0.8728,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8869987849331713,
|
| 517 |
+
"grad_norm": 0.6814940571784973,
|
| 518 |
+
"learning_rate": 6.787053442643233e-07,
|
| 519 |
+
"loss": 0.8616,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8991494532199271,
|
| 524 |
+
"grad_norm": 0.6656913757324219,
|
| 525 |
+
"learning_rate": 5.404518157127481e-07,
|
| 526 |
+
"loss": 0.8737,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9113001215066828,
|
| 531 |
+
"grad_norm": 0.6845870018005371,
|
| 532 |
+
"learning_rate": 4.1754170890833777e-07,
|
| 533 |
+
"loss": 0.8772,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9234507897934386,
|
| 538 |
+
"grad_norm": 0.6904654502868652,
|
| 539 |
+
"learning_rate": 3.101743844937943e-07,
|
| 540 |
+
"loss": 0.8678,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.9356014580801945,
|
| 545 |
+
"grad_norm": 0.6672822833061218,
|
| 546 |
+
"learning_rate": 2.1852399266194312e-07,
|
| 547 |
+
"loss": 0.8726,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9477521263669502,
|
| 552 |
+
"grad_norm": 0.6618822813034058,
|
| 553 |
+
"learning_rate": 1.4273919068349184e-07,
|
| 554 |
+
"loss": 0.8508,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.959902794653706,
|
| 559 |
+
"grad_norm": 0.6553758382797241,
|
| 560 |
+
"learning_rate": 8.29429017843797e-08,
|
| 561 |
+
"loss": 0.8737,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.9720534629404617,
|
| 566 |
+
"grad_norm": 0.6471725106239319,
|
| 567 |
+
"learning_rate": 3.923211576387087e-08,
|
| 568 |
+
"loss": 0.8588,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9842041312272175,
|
| 573 |
+
"grad_norm": 0.6723016500473022,
|
| 574 |
+
"learning_rate": 1.1677731676733584e-08,
|
| 575 |
+
"loss": 0.881,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9963547995139733,
|
| 580 |
+
"grad_norm": 0.640786349773407,
|
| 581 |
+
"learning_rate": 3.244428347204398e-10,
|
| 582 |
+
"loss": 0.8539,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9987849331713244,
|
| 587 |
+
"step": 411,
|
| 588 |
+
"total_flos": 1.267367944707375e+18,
|
| 589 |
+
"train_loss": 0.9162624978671109,
|
| 590 |
+
"train_runtime": 10821.8058,
|
| 591 |
+
"train_samples_per_second": 2.433,
|
| 592 |
+
"train_steps_per_second": 0.038
|
| 593 |
+
}
|
| 594 |
+
],
|
| 595 |
+
"logging_steps": 5,
|
| 596 |
+
"max_steps": 411,
|
| 597 |
+
"num_input_tokens_seen": 0,
|
| 598 |
+
"num_train_epochs": 1,
|
| 599 |
+
"save_steps": 500,
|
| 600 |
+
"stateful_callbacks": {
|
| 601 |
+
"TrainerControl": {
|
| 602 |
+
"args": {
|
| 603 |
+
"should_epoch_stop": false,
|
| 604 |
+
"should_evaluate": false,
|
| 605 |
+
"should_log": false,
|
| 606 |
+
"should_save": true,
|
| 607 |
+
"should_training_stop": true
|
| 608 |
+
},
|
| 609 |
+
"attributes": {}
|
| 610 |
+
}
|
| 611 |
+
},
|
| 612 |
+
"total_flos": 1.267367944707375e+18,
|
| 613 |
+
"train_batch_size": 4,
|
| 614 |
+
"trial_name": null,
|
| 615 |
+
"trial_params": null
|
| 616 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8deb7a32054ef06868ca2e2fbc756442b4ba5cf85a3d74600be5f56bbd108a05
|
| 3 |
+
size 6673
|