Upload folder using huggingface_hub
Browse files- README.md +74 -0
- all_results.json +22 -0
- config.json +29 -0
- eval_results.json +16 -0
- generation_config.json +12 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +298 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2063 -0
- train_results.json +9 -0
- trainer_state.json +1468 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- princeton-nlp/llama3-ultrafeedback
|
| 9 |
+
model-index:
|
| 10 |
+
- name: llama-3-8b-instruct-simpo
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# llama-3-8b-instruct-simpo
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the princeton-nlp/llama3-ultrafeedback dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 132.3632
|
| 22 |
+
- Rewards/chosen: -0.8503
|
| 23 |
+
- Rewards/rejected: -0.8889
|
| 24 |
+
- Rewards/accuracies: 0.5040
|
| 25 |
+
- Rewards/margins: 0.0387
|
| 26 |
+
- Logps/rejected: -0.3556
|
| 27 |
+
- Logps/chosen: -0.3401
|
| 28 |
+
- Logits/rejected: -1.2982
|
| 29 |
+
- Logits/chosen: -1.3372
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 1e-06
|
| 49 |
+
- train_batch_size: 2
|
| 50 |
+
- eval_batch_size: 4
|
| 51 |
+
- seed: 42
|
| 52 |
+
- distributed_type: multi-GPU
|
| 53 |
+
- num_devices: 8
|
| 54 |
+
- gradient_accumulation_steps: 8
|
| 55 |
+
- total_train_batch_size: 128
|
| 56 |
+
- total_eval_batch_size: 32
|
| 57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 58 |
+
- lr_scheduler_type: cosine
|
| 59 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 60 |
+
- num_epochs: 1
|
| 61 |
+
|
| 62 |
+
### Training results
|
| 63 |
+
|
| 64 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
| 65 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
| 66 |
+
| 196.6313 | 0.8549 | 400 | 132.3632 | -0.8503 | -0.8889 | 0.5040 | 0.0387 | -0.3556 | -0.3401 | -1.2982 | -1.3372 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.41.2
|
| 72 |
+
- Pytorch 2.2.0
|
| 73 |
+
- Datasets 2.20.0
|
| 74 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9981298423724285,
|
| 3 |
+
"eval_logits/chosen": -1.342084288597107,
|
| 4 |
+
"eval_logits/rejected": -1.3028345108032227,
|
| 5 |
+
"eval_logps/chosen": -0.33998000621795654,
|
| 6 |
+
"eval_logps/rejected": -0.35521572828292847,
|
| 7 |
+
"eval_loss": 261.97705078125,
|
| 8 |
+
"eval_rewards/accuracies": 0.5040322542190552,
|
| 9 |
+
"eval_rewards/chosen": -0.8499498963356018,
|
| 10 |
+
"eval_rewards/margins": 0.03808927908539772,
|
| 11 |
+
"eval_rewards/rejected": -0.888039231300354,
|
| 12 |
+
"eval_runtime": 68.7646,
|
| 13 |
+
"eval_samples": 1961,
|
| 14 |
+
"eval_samples_per_second": 28.518,
|
| 15 |
+
"eval_steps_per_second": 0.902,
|
| 16 |
+
"total_flos": 0.0,
|
| 17 |
+
"train_loss": 444.38003229635433,
|
| 18 |
+
"train_runtime": 7255.1322,
|
| 19 |
+
"train_samples": 59876,
|
| 20 |
+
"train_samples_per_second": 8.253,
|
| 21 |
+
"train_steps_per_second": 0.064
|
| 22 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128009,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 500000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.41.2",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 128256
|
| 29 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9981298423724285,
|
| 3 |
+
"eval_logits/chosen": -1.342084288597107,
|
| 4 |
+
"eval_logits/rejected": -1.3028345108032227,
|
| 5 |
+
"eval_logps/chosen": -0.33998000621795654,
|
| 6 |
+
"eval_logps/rejected": -0.35521572828292847,
|
| 7 |
+
"eval_loss": 261.97705078125,
|
| 8 |
+
"eval_rewards/accuracies": 0.5040322542190552,
|
| 9 |
+
"eval_rewards/chosen": -0.8499498963356018,
|
| 10 |
+
"eval_rewards/margins": 0.03808927908539772,
|
| 11 |
+
"eval_rewards/rejected": -0.888039231300354,
|
| 12 |
+
"eval_runtime": 68.7646,
|
| 13 |
+
"eval_samples": 1961,
|
| 14 |
+
"eval_samples_per_second": 28.518,
|
| 15 |
+
"eval_steps_per_second": 0.902
|
| 16 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128009
|
| 7 |
+
],
|
| 8 |
+
"max_length": 4096,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.41.2"
|
| 12 |
+
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4579489e820a288a9df9317f490792af59cb663a30d7dcb3d462db047578f600
|
| 3 |
+
size 4976698672
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c63451d627b31fa0f9013c52119dc12f4232bcfdcb7f809f8dd990910eb8d8a6
|
| 3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bb4dca0f2b704e29e50f16794e70af1924a7036c7dd1ca01b4c173249214b25
|
| 3 |
+
size 4915916176
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25ccb1a13fde9209bfdba10f64990312ab186bb5e74c6b3dcc9a90abcdffcca7
|
| 3 |
+
size 1168138808
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16060522496
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 297 |
+
}
|
| 298 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|reserved_special_token_2|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_3|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|reserved_special_token_4|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|reserved_special_token_5|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_6|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_7|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_8|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_9|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_10|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_11|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_12|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_13|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_14|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_15|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_16|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_17|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_18|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_19|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_20|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_21|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_22|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_23|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_24|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_25|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_26|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_27|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_28|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_29|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_30|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_31|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_32|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_33|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_34|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_35|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_36|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_37|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_38|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_39|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_40|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_41|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_42|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_43|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_44|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_45|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_46|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_47|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_48|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_49|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_50|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_51|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_52|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_53|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_54|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_55|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_56|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_57|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_58|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_59|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_60|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_61|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_62|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_63|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_64|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_65|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_66|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_67|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_68|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_69|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_70|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_71|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_72|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_73|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_74|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_75|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_76|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_77|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_78|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_79|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_80|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_81|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_82|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_83|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_84|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_85|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_86|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_87|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_88|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_89|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_90|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_91|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_92|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_93|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_94|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_95|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_96|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_97|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_98|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_99|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_100|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_101|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_102|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_103|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_104|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_105|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_106|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_107|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_108|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_109|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_110|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_111|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_112|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_113|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_114|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_115|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_116|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_117|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_118|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_119|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_120|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_121|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_122|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_123|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_124|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_125|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_126|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_127|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_128|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_129|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_130|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_131|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_132|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_133|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_134|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_135|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_136|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_137|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_138|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_139|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_140|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_141|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_142|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_143|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_144|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_145|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_146|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_147|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_148|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_149|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_150|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_151|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_152|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_153|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_154|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_155|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_156|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_157|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_158|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_159|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_160|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_161|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_162|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_163|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_164|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_165|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_166|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_167|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_168|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_169|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_170|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_171|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_172|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_173|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_174|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_175|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_176|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_177|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_178|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_179|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_180|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_181|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_182|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_183|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_184|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_185|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_186|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_187|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_188|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_189|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_190|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_191|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_192|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_193|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_194|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_195|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_196|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_197|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_198|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_199|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_200|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_201|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_202|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_203|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_204|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_205|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_206|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_207|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_208|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_209|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_210|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_211|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_212|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_213|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_214|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_215|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_216|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_217|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_218|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_219|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_220|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_221|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_222|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_223|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_224|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_225|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_226|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_227|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_228|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_229|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_230|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_231|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_232|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_233|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_234|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_235|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_236|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_237|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_238|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_239|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_240|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_241|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_242|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_243|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_244|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_245|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_246|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_247|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_248|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_249|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_250|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 2048,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9981298423724285,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 444.38003229635433,
|
| 5 |
+
"train_runtime": 7255.1322,
|
| 6 |
+
"train_samples": 59876,
|
| 7 |
+
"train_samples_per_second": 8.253,
|
| 8 |
+
"train_steps_per_second": 0.064
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1468 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9981298423724285,
|
| 5 |
+
"eval_steps": 400,
|
| 6 |
+
"global_step": 467,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0021373230029388193,
|
| 13 |
+
"grad_norm": 23814117.69119963,
|
| 14 |
+
"learning_rate": 2.127659574468085e-08,
|
| 15 |
+
"logits/chosen": -1.1381689310073853,
|
| 16 |
+
"logits/rejected": -0.9913416504859924,
|
| 17 |
+
"logps/chosen": -0.2839311361312866,
|
| 18 |
+
"logps/rejected": -0.29555341601371765,
|
| 19 |
+
"loss": 305.9593,
|
| 20 |
+
"rewards/accuracies": 0.625,
|
| 21 |
+
"rewards/chosen": -0.7098277807235718,
|
| 22 |
+
"rewards/margins": 0.029055725783109665,
|
| 23 |
+
"rewards/rejected": -0.7388835549354553,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.010686615014694095,
|
| 28 |
+
"grad_norm": 1974395.8030804002,
|
| 29 |
+
"learning_rate": 1.0638297872340425e-07,
|
| 30 |
+
"logits/chosen": -0.9901005029678345,
|
| 31 |
+
"logits/rejected": -0.9188694953918457,
|
| 32 |
+
"logps/chosen": -0.26972177624702454,
|
| 33 |
+
"logps/rejected": -0.2686304748058319,
|
| 34 |
+
"loss": 266.3214,
|
| 35 |
+
"rewards/accuracies": 0.546875,
|
| 36 |
+
"rewards/chosen": -0.6743044853210449,
|
| 37 |
+
"rewards/margins": -0.002728263381868601,
|
| 38 |
+
"rewards/rejected": -0.6715761423110962,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02137323002938819,
|
| 43 |
+
"grad_norm": 46220091.26670953,
|
| 44 |
+
"learning_rate": 2.127659574468085e-07,
|
| 45 |
+
"logits/chosen": -0.9833618998527527,
|
| 46 |
+
"logits/rejected": -0.9393731951713562,
|
| 47 |
+
"logps/chosen": -0.27256160974502563,
|
| 48 |
+
"logps/rejected": -0.273215115070343,
|
| 49 |
+
"loss": 185.9952,
|
| 50 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 51 |
+
"rewards/chosen": -0.6814040541648865,
|
| 52 |
+
"rewards/margins": 0.0016337722772732377,
|
| 53 |
+
"rewards/rejected": -0.6830377578735352,
|
| 54 |
+
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.03205984504408229,
|
| 58 |
+
"grad_norm": 474920.2122214309,
|
| 59 |
+
"learning_rate": 3.1914893617021275e-07,
|
| 60 |
+
"logits/chosen": -0.963974118232727,
|
| 61 |
+
"logits/rejected": -0.9196063876152039,
|
| 62 |
+
"logps/chosen": -0.29573556780815125,
|
| 63 |
+
"logps/rejected": -0.28305521607398987,
|
| 64 |
+
"loss": 125.1317,
|
| 65 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 66 |
+
"rewards/chosen": -0.7393389940261841,
|
| 67 |
+
"rewards/margins": -0.0317009761929512,
|
| 68 |
+
"rewards/rejected": -0.7076379656791687,
|
| 69 |
+
"step": 15
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.04274646005877638,
|
| 73 |
+
"grad_norm": 4515133.468491916,
|
| 74 |
+
"learning_rate": 4.25531914893617e-07,
|
| 75 |
+
"logits/chosen": -0.976075291633606,
|
| 76 |
+
"logits/rejected": -0.9759608507156372,
|
| 77 |
+
"logps/chosen": -0.2616123557090759,
|
| 78 |
+
"logps/rejected": -0.27002111077308655,
|
| 79 |
+
"loss": 127.9034,
|
| 80 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 81 |
+
"rewards/chosen": -0.6540309190750122,
|
| 82 |
+
"rewards/margins": 0.02102179452776909,
|
| 83 |
+
"rewards/rejected": -0.6750527620315552,
|
| 84 |
+
"step": 20
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.053433075073470476,
|
| 88 |
+
"grad_norm": 5165268.674113416,
|
| 89 |
+
"learning_rate": 5.319148936170212e-07,
|
| 90 |
+
"logits/chosen": -1.0451716184616089,
|
| 91 |
+
"logits/rejected": -1.0216295719146729,
|
| 92 |
+
"logps/chosen": -0.28275421261787415,
|
| 93 |
+
"logps/rejected": -0.2863079905509949,
|
| 94 |
+
"loss": 161.215,
|
| 95 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 96 |
+
"rewards/chosen": -0.7068854570388794,
|
| 97 |
+
"rewards/margins": 0.0088844895362854,
|
| 98 |
+
"rewards/rejected": -0.7157700657844543,
|
| 99 |
+
"step": 25
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.06411969008816458,
|
| 103 |
+
"grad_norm": 143372948.8120165,
|
| 104 |
+
"learning_rate": 6.382978723404255e-07,
|
| 105 |
+
"logits/chosen": -1.071578025817871,
|
| 106 |
+
"logits/rejected": -0.9856084585189819,
|
| 107 |
+
"logps/chosen": -0.2763022780418396,
|
| 108 |
+
"logps/rejected": -0.2745462656021118,
|
| 109 |
+
"loss": 388.8185,
|
| 110 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 111 |
+
"rewards/chosen": -0.6907557249069214,
|
| 112 |
+
"rewards/margins": -0.0043900711461901665,
|
| 113 |
+
"rewards/rejected": -0.6863657236099243,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07480630510285867,
|
| 118 |
+
"grad_norm": 1184929.3556330686,
|
| 119 |
+
"learning_rate": 7.446808510638297e-07,
|
| 120 |
+
"logits/chosen": -1.01273512840271,
|
| 121 |
+
"logits/rejected": -0.9335028529167175,
|
| 122 |
+
"logps/chosen": -0.27808648347854614,
|
| 123 |
+
"logps/rejected": -0.29893654584884644,
|
| 124 |
+
"loss": 115.7746,
|
| 125 |
+
"rewards/accuracies": 0.5625,
|
| 126 |
+
"rewards/chosen": -0.695216178894043,
|
| 127 |
+
"rewards/margins": 0.05212521553039551,
|
| 128 |
+
"rewards/rejected": -0.7473413348197937,
|
| 129 |
+
"step": 35
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.08549292011755276,
|
| 133 |
+
"grad_norm": 1877904.3293607633,
|
| 134 |
+
"learning_rate": 8.51063829787234e-07,
|
| 135 |
+
"logits/chosen": -0.9277470707893372,
|
| 136 |
+
"logits/rejected": -0.9166946411132812,
|
| 137 |
+
"logps/chosen": -0.2787823975086212,
|
| 138 |
+
"logps/rejected": -0.2824743986129761,
|
| 139 |
+
"loss": 138.8757,
|
| 140 |
+
"rewards/accuracies": 0.512499988079071,
|
| 141 |
+
"rewards/chosen": -0.6969559788703918,
|
| 142 |
+
"rewards/margins": 0.009230067022144794,
|
| 143 |
+
"rewards/rejected": -0.7061859965324402,
|
| 144 |
+
"step": 40
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.09617953513224686,
|
| 148 |
+
"grad_norm": 2671724.397751134,
|
| 149 |
+
"learning_rate": 9.574468085106384e-07,
|
| 150 |
+
"logits/chosen": -0.9359474182128906,
|
| 151 |
+
"logits/rejected": -0.8535245060920715,
|
| 152 |
+
"logps/chosen": -0.33036336302757263,
|
| 153 |
+
"logps/rejected": -0.33015647530555725,
|
| 154 |
+
"loss": 104.7933,
|
| 155 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 156 |
+
"rewards/chosen": -0.8259084820747375,
|
| 157 |
+
"rewards/margins": -0.0005173005047254264,
|
| 158 |
+
"rewards/rejected": -0.8253911733627319,
|
| 159 |
+
"step": 45
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.10686615014694095,
|
| 163 |
+
"grad_norm": 79521388.74298675,
|
| 164 |
+
"learning_rate": 9.998741174712533e-07,
|
| 165 |
+
"logits/chosen": -0.9259702563285828,
|
| 166 |
+
"logits/rejected": -0.9349774122238159,
|
| 167 |
+
"logps/chosen": -0.2925248146057129,
|
| 168 |
+
"logps/rejected": -0.3076633810997009,
|
| 169 |
+
"loss": 175.2819,
|
| 170 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 171 |
+
"rewards/chosen": -0.731312096118927,
|
| 172 |
+
"rewards/margins": 0.0378464013338089,
|
| 173 |
+
"rewards/rejected": -0.7691584825515747,
|
| 174 |
+
"step": 50
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.11755276516163506,
|
| 178 |
+
"grad_norm": 327828.43192551495,
|
| 179 |
+
"learning_rate": 9.991050648838675e-07,
|
| 180 |
+
"logits/chosen": -0.9278720021247864,
|
| 181 |
+
"logits/rejected": -0.8686744570732117,
|
| 182 |
+
"logps/chosen": -0.2634710669517517,
|
| 183 |
+
"logps/rejected": -0.27794915437698364,
|
| 184 |
+
"loss": 2695.6354,
|
| 185 |
+
"rewards/accuracies": 0.625,
|
| 186 |
+
"rewards/chosen": -0.6586776971817017,
|
| 187 |
+
"rewards/margins": 0.03619522601366043,
|
| 188 |
+
"rewards/rejected": -0.6948728561401367,
|
| 189 |
+
"step": 55
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.12823938017632916,
|
| 193 |
+
"grad_norm": 899122.206242127,
|
| 194 |
+
"learning_rate": 9.97637968732563e-07,
|
| 195 |
+
"logits/chosen": -0.9561047554016113,
|
| 196 |
+
"logits/rejected": -0.9336016774177551,
|
| 197 |
+
"logps/chosen": -0.2656118869781494,
|
| 198 |
+
"logps/rejected": -0.28187674283981323,
|
| 199 |
+
"loss": 105.9757,
|
| 200 |
+
"rewards/accuracies": 0.5625,
|
| 201 |
+
"rewards/chosen": -0.6640297174453735,
|
| 202 |
+
"rewards/margins": 0.0406620129942894,
|
| 203 |
+
"rewards/rejected": -0.7046917080879211,
|
| 204 |
+
"step": 60
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.13892599519102325,
|
| 208 |
+
"grad_norm": 377242.1086806779,
|
| 209 |
+
"learning_rate": 9.954748808839674e-07,
|
| 210 |
+
"logits/chosen": -0.956866443157196,
|
| 211 |
+
"logits/rejected": -1.005385398864746,
|
| 212 |
+
"logps/chosen": -0.2731708288192749,
|
| 213 |
+
"logps/rejected": -0.26419904828071594,
|
| 214 |
+
"loss": 108.4874,
|
| 215 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 216 |
+
"rewards/chosen": -0.682927131652832,
|
| 217 |
+
"rewards/margins": -0.02242954447865486,
|
| 218 |
+
"rewards/rejected": -0.6604975461959839,
|
| 219 |
+
"step": 65
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14961261020571734,
|
| 223 |
+
"grad_norm": 42496.77007169402,
|
| 224 |
+
"learning_rate": 9.926188266120295e-07,
|
| 225 |
+
"logits/chosen": -0.9903133511543274,
|
| 226 |
+
"logits/rejected": -0.9588413238525391,
|
| 227 |
+
"logps/chosen": -0.305401474237442,
|
| 228 |
+
"logps/rejected": -0.298237681388855,
|
| 229 |
+
"loss": 405.7784,
|
| 230 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 231 |
+
"rewards/chosen": -0.7635036706924438,
|
| 232 |
+
"rewards/margins": -0.017909497022628784,
|
| 233 |
+
"rewards/rejected": -0.7455942034721375,
|
| 234 |
+
"step": 70
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.16029922522041143,
|
| 238 |
+
"grad_norm": 523140.8331781128,
|
| 239 |
+
"learning_rate": 9.890738003669027e-07,
|
| 240 |
+
"logits/chosen": -0.9634426236152649,
|
| 241 |
+
"logits/rejected": -0.9494821429252625,
|
| 242 |
+
"logps/chosen": -0.2741475999355316,
|
| 243 |
+
"logps/rejected": -0.2895483672618866,
|
| 244 |
+
"loss": 2624.7643,
|
| 245 |
+
"rewards/accuracies": 0.5625,
|
| 246 |
+
"rewards/chosen": -0.685369074344635,
|
| 247 |
+
"rewards/margins": 0.038501907140016556,
|
| 248 |
+
"rewards/rejected": -0.7238709926605225,
|
| 249 |
+
"step": 75
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.17098584023510552,
|
| 253 |
+
"grad_norm": 37571862.32606961,
|
| 254 |
+
"learning_rate": 9.848447601883433e-07,
|
| 255 |
+
"logits/chosen": -1.0007914304733276,
|
| 256 |
+
"logits/rejected": -0.9825354814529419,
|
| 257 |
+
"logps/chosen": -0.28798869252204895,
|
| 258 |
+
"logps/rejected": -0.28025856614112854,
|
| 259 |
+
"loss": 131.06,
|
| 260 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 261 |
+
"rewards/chosen": -0.7199716567993164,
|
| 262 |
+
"rewards/margins": -0.019325237721204758,
|
| 263 |
+
"rewards/rejected": -0.7006464600563049,
|
| 264 |
+
"step": 80
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.18167245524979964,
|
| 268 |
+
"grad_norm": 8861430.225925114,
|
| 269 |
+
"learning_rate": 9.799376207714444e-07,
|
| 270 |
+
"logits/chosen": -0.9258670806884766,
|
| 271 |
+
"logits/rejected": -0.8755356073379517,
|
| 272 |
+
"logps/chosen": -0.2675308287143707,
|
| 273 |
+
"logps/rejected": -0.28247857093811035,
|
| 274 |
+
"loss": 151.0586,
|
| 275 |
+
"rewards/accuracies": 0.512499988079071,
|
| 276 |
+
"rewards/chosen": -0.6688271760940552,
|
| 277 |
+
"rewards/margins": 0.03736928477883339,
|
| 278 |
+
"rewards/rejected": -0.7061963081359863,
|
| 279 |
+
"step": 85
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.19235907026449373,
|
| 283 |
+
"grad_norm": 322999.5648039634,
|
| 284 |
+
"learning_rate": 9.743592451943998e-07,
|
| 285 |
+
"logits/chosen": -0.8945444226264954,
|
| 286 |
+
"logits/rejected": -0.8326283693313599,
|
| 287 |
+
"logps/chosen": -0.2888963222503662,
|
| 288 |
+
"logps/rejected": -0.30566543340682983,
|
| 289 |
+
"loss": 104.0617,
|
| 290 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 291 |
+
"rewards/chosen": -0.7222408056259155,
|
| 292 |
+
"rewards/margins": 0.04192278906702995,
|
| 293 |
+
"rewards/rejected": -0.764163613319397,
|
| 294 |
+
"step": 90
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.20304568527918782,
|
| 298 |
+
"grad_norm": 16202558.227455074,
|
| 299 |
+
"learning_rate": 9.681174353198686e-07,
|
| 300 |
+
"logits/chosen": -1.0018240213394165,
|
| 301 |
+
"logits/rejected": -1.024642825126648,
|
| 302 |
+
"logps/chosen": -0.2775546908378601,
|
| 303 |
+
"logps/rejected": -0.31214436888694763,
|
| 304 |
+
"loss": 185.9518,
|
| 305 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 306 |
+
"rewards/chosen": -0.6938868165016174,
|
| 307 |
+
"rewards/margins": 0.08647419512271881,
|
| 308 |
+
"rewards/rejected": -0.7803609371185303,
|
| 309 |
+
"step": 95
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.2137323002938819,
|
| 313 |
+
"grad_norm": 881275.6537233666,
|
| 314 |
+
"learning_rate": 9.612209208833646e-07,
|
| 315 |
+
"logits/chosen": -1.0630947351455688,
|
| 316 |
+
"logits/rejected": -1.0079935789108276,
|
| 317 |
+
"logps/chosen": -0.28541457653045654,
|
| 318 |
+
"logps/rejected": -0.27989768981933594,
|
| 319 |
+
"loss": 377.6484,
|
| 320 |
+
"rewards/accuracies": 0.512499988079071,
|
| 321 |
+
"rewards/chosen": -0.7135364413261414,
|
| 322 |
+
"rewards/margins": -0.01379220187664032,
|
| 323 |
+
"rewards/rejected": -0.6997443437576294,
|
| 324 |
+
"step": 100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.224418915308576,
|
| 328 |
+
"grad_norm": 1471606.598734741,
|
| 329 |
+
"learning_rate": 9.536793472839324e-07,
|
| 330 |
+
"logits/chosen": -0.9882336854934692,
|
| 331 |
+
"logits/rejected": -0.9416030645370483,
|
| 332 |
+
"logps/chosen": -0.2841026186943054,
|
| 333 |
+
"logps/rejected": -0.30027633905410767,
|
| 334 |
+
"loss": 205.1062,
|
| 335 |
+
"rewards/accuracies": 0.637499988079071,
|
| 336 |
+
"rewards/chosen": -0.7102565169334412,
|
| 337 |
+
"rewards/margins": 0.0404343381524086,
|
| 338 |
+
"rewards/rejected": -0.7506908178329468,
|
| 339 |
+
"step": 105
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2351055303232701,
|
| 343 |
+
"grad_norm": 313885.99955306284,
|
| 344 |
+
"learning_rate": 9.455032620941839e-07,
|
| 345 |
+
"logits/chosen": -0.9041908383369446,
|
| 346 |
+
"logits/rejected": -0.854825496673584,
|
| 347 |
+
"logps/chosen": -0.33143380284309387,
|
| 348 |
+
"logps/rejected": -0.3396168053150177,
|
| 349 |
+
"loss": 2658.6553,
|
| 350 |
+
"rewards/accuracies": 0.512499988079071,
|
| 351 |
+
"rewards/chosen": -0.8285845518112183,
|
| 352 |
+
"rewards/margins": 0.020457318052649498,
|
| 353 |
+
"rewards/rejected": -0.8490419387817383,
|
| 354 |
+
"step": 110
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.2457921453379642,
|
| 358 |
+
"grad_norm": 682808.4048805884,
|
| 359 |
+
"learning_rate": 9.367041003085648e-07,
|
| 360 |
+
"logits/chosen": -0.9211395978927612,
|
| 361 |
+
"logits/rejected": -0.9187518358230591,
|
| 362 |
+
"logps/chosen": -0.2765989303588867,
|
| 363 |
+
"logps/rejected": -0.2790865898132324,
|
| 364 |
+
"loss": 2651.5432,
|
| 365 |
+
"rewards/accuracies": 0.4375,
|
| 366 |
+
"rewards/chosen": -0.6914974451065063,
|
| 367 |
+
"rewards/margins": 0.006219107657670975,
|
| 368 |
+
"rewards/rejected": -0.697716474533081,
|
| 369 |
+
"step": 115
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.2564787603526583,
|
| 373 |
+
"grad_norm": 527643.1252709947,
|
| 374 |
+
"learning_rate": 9.272941683504808e-07,
|
| 375 |
+
"logits/chosen": -1.0119305849075317,
|
| 376 |
+
"logits/rejected": -0.9751386642456055,
|
| 377 |
+
"logps/chosen": -0.28785568475723267,
|
| 378 |
+
"logps/rejected": -0.31191155314445496,
|
| 379 |
+
"loss": 232.3885,
|
| 380 |
+
"rewards/accuracies": 0.5,
|
| 381 |
+
"rewards/chosen": -0.7196391820907593,
|
| 382 |
+
"rewards/margins": 0.06013970449566841,
|
| 383 |
+
"rewards/rejected": -0.7797788381576538,
|
| 384 |
+
"step": 120
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.2671653753673524,
|
| 388 |
+
"grad_norm": 57160137.92819305,
|
| 389 |
+
"learning_rate": 9.172866268606513e-07,
|
| 390 |
+
"logits/chosen": -1.0446767807006836,
|
| 391 |
+
"logits/rejected": -1.03428316116333,
|
| 392 |
+
"logps/chosen": -0.3408173620700836,
|
| 393 |
+
"logps/rejected": -0.33484262228012085,
|
| 394 |
+
"loss": 171.7718,
|
| 395 |
+
"rewards/accuracies": 0.550000011920929,
|
| 396 |
+
"rewards/chosen": -0.8520433306694031,
|
| 397 |
+
"rewards/margins": -0.014936879277229309,
|
| 398 |
+
"rewards/rejected": -0.8371064066886902,
|
| 399 |
+
"step": 125
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.2778519903820465,
|
| 403 |
+
"grad_norm": 354260.60461613233,
|
| 404 |
+
"learning_rate": 9.066954722907638e-07,
|
| 405 |
+
"logits/chosen": -1.0202778577804565,
|
| 406 |
+
"logits/rejected": -1.040438175201416,
|
| 407 |
+
"logps/chosen": -0.3069685399532318,
|
| 408 |
+
"logps/rejected": -0.3384125232696533,
|
| 409 |
+
"loss": 152.887,
|
| 410 |
+
"rewards/accuracies": 0.512499988079071,
|
| 411 |
+
"rewards/chosen": -0.7674213647842407,
|
| 412 |
+
"rewards/margins": 0.07861001789569855,
|
| 413 |
+
"rewards/rejected": -0.8460313677787781,
|
| 414 |
+
"step": 130
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.2885386053967406,
|
| 418 |
+
"grad_norm": 4161760.6479958617,
|
| 419 |
+
"learning_rate": 8.955355173281707e-07,
|
| 420 |
+
"logits/chosen": -0.9897885322570801,
|
| 421 |
+
"logits/rejected": -0.9403419494628906,
|
| 422 |
+
"logps/chosen": -0.3388122022151947,
|
| 423 |
+
"logps/rejected": -0.29513686895370483,
|
| 424 |
+
"loss": 127.9212,
|
| 425 |
+
"rewards/accuracies": 0.4375,
|
| 426 |
+
"rewards/chosen": -0.8470304608345032,
|
| 427 |
+
"rewards/margins": -0.10918829590082169,
|
| 428 |
+
"rewards/rejected": -0.7378422021865845,
|
| 429 |
+
"step": 135
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2992252204114347,
|
| 433 |
+
"grad_norm": 1984829.9018358907,
|
| 434 |
+
"learning_rate": 8.838223701790055e-07,
|
| 435 |
+
"logits/chosen": -0.9738261103630066,
|
| 436 |
+
"logits/rejected": -0.9614647030830383,
|
| 437 |
+
"logps/chosen": -0.3720606565475464,
|
| 438 |
+
"logps/rejected": -0.3473301827907562,
|
| 439 |
+
"loss": 110.1865,
|
| 440 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 441 |
+
"rewards/chosen": -0.930151641368866,
|
| 442 |
+
"rewards/margins": -0.06182613968849182,
|
| 443 |
+
"rewards/rejected": -0.8683255314826965,
|
| 444 |
+
"step": 140
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.30991183542612877,
|
| 448 |
+
"grad_norm": 1513820.1920679864,
|
| 449 |
+
"learning_rate": 8.71572412738697e-07,
|
| 450 |
+
"logits/chosen": -1.0015193223953247,
|
| 451 |
+
"logits/rejected": -0.9965044856071472,
|
| 452 |
+
"logps/chosen": -0.3061389625072479,
|
| 453 |
+
"logps/rejected": -0.3093434274196625,
|
| 454 |
+
"loss": 3025.9289,
|
| 455 |
+
"rewards/accuracies": 0.4375,
|
| 456 |
+
"rewards/chosen": -0.7653473615646362,
|
| 457 |
+
"rewards/margins": 0.008011135272681713,
|
| 458 |
+
"rewards/rejected": -0.7733586430549622,
|
| 459 |
+
"step": 145
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.32059845044082286,
|
| 463 |
+
"grad_norm": 1970591.2689892622,
|
| 464 |
+
"learning_rate": 8.588027776804058e-07,
|
| 465 |
+
"logits/chosen": -0.9444905519485474,
|
| 466 |
+
"logits/rejected": -0.9439139366149902,
|
| 467 |
+
"logps/chosen": -0.3537100851535797,
|
| 468 |
+
"logps/rejected": -0.35441845655441284,
|
| 469 |
+
"loss": 221.1807,
|
| 470 |
+
"rewards/accuracies": 0.550000011920929,
|
| 471 |
+
"rewards/chosen": -0.8842751383781433,
|
| 472 |
+
"rewards/margins": 0.0017710126703605056,
|
| 473 |
+
"rewards/rejected": -0.8860462307929993,
|
| 474 |
+
"step": 150
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.33128506545551695,
|
| 478 |
+
"grad_norm": 12808984.8595381,
|
| 479 |
+
"learning_rate": 8.455313244934324e-07,
|
| 480 |
+
"logits/chosen": -1.0120588541030884,
|
| 481 |
+
"logits/rejected": -0.9681800603866577,
|
| 482 |
+
"logps/chosen": -0.3124849796295166,
|
| 483 |
+
"logps/rejected": -0.3563632667064667,
|
| 484 |
+
"loss": 187.1941,
|
| 485 |
+
"rewards/accuracies": 0.5,
|
| 486 |
+
"rewards/chosen": -0.7812124490737915,
|
| 487 |
+
"rewards/margins": 0.10969575494527817,
|
| 488 |
+
"rewards/rejected": -0.8909081220626831,
|
| 489 |
+
"step": 155
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.34197168047021104,
|
| 493 |
+
"grad_norm": 1183315.8265051153,
|
| 494 |
+
"learning_rate": 8.317766145051057e-07,
|
| 495 |
+
"logits/chosen": -1.0060454607009888,
|
| 496 |
+
"logits/rejected": -0.9961159825325012,
|
| 497 |
+
"logps/chosen": -0.2914329171180725,
|
| 498 |
+
"logps/rejected": -0.3657309412956238,
|
| 499 |
+
"loss": 120.0758,
|
| 500 |
+
"rewards/accuracies": 0.550000011920929,
|
| 501 |
+
"rewards/chosen": -0.7285822629928589,
|
| 502 |
+
"rewards/margins": 0.1857450008392334,
|
| 503 |
+
"rewards/rejected": -0.9143272638320923,
|
| 504 |
+
"step": 160
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.3526582954849052,
|
| 508 |
+
"grad_norm": 2641730.3542562006,
|
| 509 |
+
"learning_rate": 8.175578849210894e-07,
|
| 510 |
+
"logits/chosen": -1.0412616729736328,
|
| 511 |
+
"logits/rejected": -0.9751707315444946,
|
| 512 |
+
"logps/chosen": -0.33477407693862915,
|
| 513 |
+
"logps/rejected": -0.31863099336624146,
|
| 514 |
+
"loss": 222.9428,
|
| 515 |
+
"rewards/accuracies": 0.5,
|
| 516 |
+
"rewards/chosen": -0.8369352221488953,
|
| 517 |
+
"rewards/margins": -0.04035765677690506,
|
| 518 |
+
"rewards/rejected": -0.7965775728225708,
|
| 519 |
+
"step": 165
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.36334491049959927,
|
| 523 |
+
"grad_norm": 24200663.77841142,
|
| 524 |
+
"learning_rate": 8.028950219204099e-07,
|
| 525 |
+
"logits/chosen": -1.0198957920074463,
|
| 526 |
+
"logits/rejected": -1.0187537670135498,
|
| 527 |
+
"logps/chosen": -0.35278764367103577,
|
| 528 |
+
"logps/rejected": -0.36079707741737366,
|
| 529 |
+
"loss": 175.3017,
|
| 530 |
+
"rewards/accuracies": 0.5,
|
| 531 |
+
"rewards/chosen": -0.8819690942764282,
|
| 532 |
+
"rewards/margins": 0.020023606717586517,
|
| 533 |
+
"rewards/rejected": -0.901992678642273,
|
| 534 |
+
"step": 170
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.37403152551429336,
|
| 538 |
+
"grad_norm": 423144.2753567647,
|
| 539 |
+
"learning_rate": 7.878085328428368e-07,
|
| 540 |
+
"logits/chosen": -1.0390782356262207,
|
| 541 |
+
"logits/rejected": -1.0463870763778687,
|
| 542 |
+
"logps/chosen": -0.3290930390357971,
|
| 543 |
+
"logps/rejected": -0.33625391125679016,
|
| 544 |
+
"loss": 172.6517,
|
| 545 |
+
"rewards/accuracies": 0.550000011920929,
|
| 546 |
+
"rewards/chosen": -0.8227324485778809,
|
| 547 |
+
"rewards/margins": 0.01790226623415947,
|
| 548 |
+
"rewards/rejected": -0.840634822845459,
|
| 549 |
+
"step": 175
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.38471814052898745,
|
| 553 |
+
"grad_norm": 66473449.795217186,
|
| 554 |
+
"learning_rate": 7.723195175075135e-07,
|
| 555 |
+
"logits/chosen": -1.074244737625122,
|
| 556 |
+
"logits/rejected": -1.0753021240234375,
|
| 557 |
+
"logps/chosen": -0.33172592520713806,
|
| 558 |
+
"logps/rejected": -0.34797996282577515,
|
| 559 |
+
"loss": 173.7831,
|
| 560 |
+
"rewards/accuracies": 0.5625,
|
| 561 |
+
"rewards/chosen": -0.8293148279190063,
|
| 562 |
+
"rewards/margins": 0.04063502699136734,
|
| 563 |
+
"rewards/rejected": -0.8699499368667603,
|
| 564 |
+
"step": 180
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.39540475554368154,
|
| 568 |
+
"grad_norm": 2508265.2610814595,
|
| 569 |
+
"learning_rate": 7.564496387029531e-07,
|
| 570 |
+
"logits/chosen": -1.105753779411316,
|
| 571 |
+
"logits/rejected": -1.0690752267837524,
|
| 572 |
+
"logps/chosen": -0.33374324440956116,
|
| 573 |
+
"logps/rejected": -0.3317410349845886,
|
| 574 |
+
"loss": 130.1423,
|
| 575 |
+
"rewards/accuracies": 0.5,
|
| 576 |
+
"rewards/chosen": -0.8343580961227417,
|
| 577 |
+
"rewards/margins": -0.005005507729947567,
|
| 578 |
+
"rewards/rejected": -0.8293525576591492,
|
| 579 |
+
"step": 185
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.40609137055837563,
|
| 583 |
+
"grad_norm": 1415188.1564555708,
|
| 584 |
+
"learning_rate": 7.402210918896689e-07,
|
| 585 |
+
"logits/chosen": -1.1109493970870972,
|
| 586 |
+
"logits/rejected": -1.0873216390609741,
|
| 587 |
+
"logps/chosen": -0.3215797245502472,
|
| 588 |
+
"logps/rejected": -0.34585997462272644,
|
| 589 |
+
"loss": 103.3292,
|
| 590 |
+
"rewards/accuracies": 0.5625,
|
| 591 |
+
"rewards/chosen": -0.8039493560791016,
|
| 592 |
+
"rewards/margins": 0.06070064380764961,
|
| 593 |
+
"rewards/rejected": -0.8646499514579773,
|
| 594 |
+
"step": 190
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.4167779855730697,
|
| 598 |
+
"grad_norm": 22405463.240061384,
|
| 599 |
+
"learning_rate": 7.236565741578162e-07,
|
| 600 |
+
"logits/chosen": -1.0102512836456299,
|
| 601 |
+
"logits/rejected": -0.995439350605011,
|
| 602 |
+
"logps/chosen": -0.34978950023651123,
|
| 603 |
+
"logps/rejected": -0.3523608446121216,
|
| 604 |
+
"loss": 144.2631,
|
| 605 |
+
"rewards/accuracies": 0.512499988079071,
|
| 606 |
+
"rewards/chosen": -0.8744736909866333,
|
| 607 |
+
"rewards/margins": 0.006428359542042017,
|
| 608 |
+
"rewards/rejected": -0.880902111530304,
|
| 609 |
+
"step": 195
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.4274646005877638,
|
| 613 |
+
"grad_norm": 364076.0574983151,
|
| 614 |
+
"learning_rate": 7.067792524832603e-07,
|
| 615 |
+
"logits/chosen": -1.0113328695297241,
|
| 616 |
+
"logits/rejected": -1.0017603635787964,
|
| 617 |
+
"logps/chosen": -0.3367648124694824,
|
| 618 |
+
"logps/rejected": -0.334301233291626,
|
| 619 |
+
"loss": 115.4949,
|
| 620 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 621 |
+
"rewards/chosen": -0.8419120907783508,
|
| 622 |
+
"rewards/margins": -0.006158898584544659,
|
| 623 |
+
"rewards/rejected": -0.8357530832290649,
|
| 624 |
+
"step": 200
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.4381512156024579,
|
| 628 |
+
"grad_norm": 1540771.9395518457,
|
| 629 |
+
"learning_rate": 6.896127313264642e-07,
|
| 630 |
+
"logits/chosen": -1.1025888919830322,
|
| 631 |
+
"logits/rejected": -1.0531136989593506,
|
| 632 |
+
"logps/chosen": -0.32284116744995117,
|
| 633 |
+
"logps/rejected": -0.34286996722221375,
|
| 634 |
+
"loss": 117.5218,
|
| 635 |
+
"rewards/accuracies": 0.550000011920929,
|
| 636 |
+
"rewards/chosen": -0.8071029782295227,
|
| 637 |
+
"rewards/margins": 0.05007190629839897,
|
| 638 |
+
"rewards/rejected": -0.8571747541427612,
|
| 639 |
+
"step": 205
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.448837830617152,
|
| 643 |
+
"grad_norm": 197109620.3195932,
|
| 644 |
+
"learning_rate": 6.721810196195174e-07,
|
| 645 |
+
"logits/chosen": -1.1090078353881836,
|
| 646 |
+
"logits/rejected": -1.0331655740737915,
|
| 647 |
+
"logps/chosen": -0.2971234619617462,
|
| 648 |
+
"logps/rejected": -0.3048322796821594,
|
| 649 |
+
"loss": 199.9444,
|
| 650 |
+
"rewards/accuracies": 0.38749998807907104,
|
| 651 |
+
"rewards/chosen": -0.7428085207939148,
|
| 652 |
+
"rewards/margins": 0.01927214488387108,
|
| 653 |
+
"rewards/rejected": -0.7620807886123657,
|
| 654 |
+
"step": 210
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.45952444563184613,
|
| 658 |
+
"grad_norm": 210941.10682300097,
|
| 659 |
+
"learning_rate": 6.545084971874736e-07,
|
| 660 |
+
"logits/chosen": -1.055289626121521,
|
| 661 |
+
"logits/rejected": -0.9978870153427124,
|
| 662 |
+
"logps/chosen": -0.31941694021224976,
|
| 663 |
+
"logps/rejected": -0.3496856093406677,
|
| 664 |
+
"loss": 117.6536,
|
| 665 |
+
"rewards/accuracies": 0.5,
|
| 666 |
+
"rewards/chosen": -0.7985422015190125,
|
| 667 |
+
"rewards/margins": 0.07567177712917328,
|
| 668 |
+
"rewards/rejected": -0.8742140531539917,
|
| 669 |
+
"step": 215
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.4702110606465402,
|
| 673 |
+
"grad_norm": 17774561.440666944,
|
| 674 |
+
"learning_rate": 6.3661988065096e-07,
|
| 675 |
+
"logits/chosen": -1.0686638355255127,
|
| 676 |
+
"logits/rejected": -1.0178725719451904,
|
| 677 |
+
"logps/chosen": -0.33966127038002014,
|
| 678 |
+
"logps/rejected": -0.3513311445713043,
|
| 679 |
+
"loss": 109.0363,
|
| 680 |
+
"rewards/accuracies": 0.5625,
|
| 681 |
+
"rewards/chosen": -0.8491531610488892,
|
| 682 |
+
"rewards/margins": 0.029174691066145897,
|
| 683 |
+
"rewards/rejected": -0.8783278465270996,
|
| 684 |
+
"step": 220
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.4808976756612343,
|
| 688 |
+
"grad_norm": 1448517.5044393009,
|
| 689 |
+
"learning_rate": 6.185401888577487e-07,
|
| 690 |
+
"logits/chosen": -1.0401103496551514,
|
| 691 |
+
"logits/rejected": -1.0147794485092163,
|
| 692 |
+
"logps/chosen": -0.284532368183136,
|
| 693 |
+
"logps/rejected": -0.2862989902496338,
|
| 694 |
+
"loss": 111.407,
|
| 695 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 696 |
+
"rewards/chosen": -0.7113308906555176,
|
| 697 |
+
"rewards/margins": 0.004416565410792828,
|
| 698 |
+
"rewards/rejected": -0.7157474756240845,
|
| 699 |
+
"step": 225
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.4915842906759284,
|
| 703 |
+
"grad_norm": 27408086.19895333,
|
| 704 |
+
"learning_rate": 6.002947078916364e-07,
|
| 705 |
+
"logits/chosen": -1.1030638217926025,
|
| 706 |
+
"logits/rejected": -0.9990617632865906,
|
| 707 |
+
"logps/chosen": -0.33675864338874817,
|
| 708 |
+
"logps/rejected": -0.3289005756378174,
|
| 709 |
+
"loss": 2706.1715,
|
| 710 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 711 |
+
"rewards/chosen": -0.841896653175354,
|
| 712 |
+
"rewards/margins": -0.01964510791003704,
|
| 713 |
+
"rewards/rejected": -0.8222514986991882,
|
| 714 |
+
"step": 230
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.5022709056906225,
|
| 718 |
+
"grad_norm": 317843.4109202252,
|
| 719 |
+
"learning_rate": 5.819089557075688e-07,
|
| 720 |
+
"logits/chosen": -1.0890393257141113,
|
| 721 |
+
"logits/rejected": -1.0440254211425781,
|
| 722 |
+
"logps/chosen": -0.34919267892837524,
|
| 723 |
+
"logps/rejected": -0.3513543903827667,
|
| 724 |
+
"loss": 238.4326,
|
| 725 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 726 |
+
"rewards/chosen": -0.8729816675186157,
|
| 727 |
+
"rewards/margins": 0.005404374096542597,
|
| 728 |
+
"rewards/rejected": -0.8783860206604004,
|
| 729 |
+
"step": 235
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.5129575207053166,
|
| 733 |
+
"grad_norm": 85019.6413638533,
|
| 734 |
+
"learning_rate": 5.634086464424742e-07,
|
| 735 |
+
"logits/chosen": -1.1137946844100952,
|
| 736 |
+
"logits/rejected": -1.076812505722046,
|
| 737 |
+
"logps/chosen": -0.32847946882247925,
|
| 738 |
+
"logps/rejected": -0.322710782289505,
|
| 739 |
+
"loss": 114.2576,
|
| 740 |
+
"rewards/accuracies": 0.38749998807907104,
|
| 741 |
+
"rewards/chosen": -0.8211986422538757,
|
| 742 |
+
"rewards/margins": -0.014421721920371056,
|
| 743 |
+
"rewards/rejected": -0.8067768812179565,
|
| 744 |
+
"step": 240
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5236441357200107,
|
| 748 |
+
"grad_norm": 6299240.513263524,
|
| 749 |
+
"learning_rate": 5.448196544517167e-07,
|
| 750 |
+
"logits/chosen": -1.1339685916900635,
|
| 751 |
+
"logits/rejected": -1.0941574573516846,
|
| 752 |
+
"logps/chosen": -0.3057493269443512,
|
| 753 |
+
"logps/rejected": -0.3173142373561859,
|
| 754 |
+
"loss": 145.971,
|
| 755 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 756 |
+
"rewards/chosen": -0.7643733024597168,
|
| 757 |
+
"rewards/margins": 0.028912359848618507,
|
| 758 |
+
"rewards/rejected": -0.7932857275009155,
|
| 759 |
+
"step": 245
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.5343307507347048,
|
| 763 |
+
"grad_norm": 847488.7365746452,
|
| 764 |
+
"learning_rate": 5.26167978121472e-07,
|
| 765 |
+
"logits/chosen": -1.1527339220046997,
|
| 766 |
+
"logits/rejected": -1.114386796951294,
|
| 767 |
+
"logps/chosen": -0.3197785019874573,
|
| 768 |
+
"logps/rejected": -0.3439500629901886,
|
| 769 |
+
"loss": 2684.4785,
|
| 770 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 771 |
+
"rewards/chosen": -0.7994462251663208,
|
| 772 |
+
"rewards/margins": 0.060428936034440994,
|
| 773 |
+
"rewards/rejected": -0.8598750829696655,
|
| 774 |
+
"step": 250
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.5450173657493989,
|
| 778 |
+
"grad_norm": 231777.21031654373,
|
| 779 |
+
"learning_rate": 5.074797035076318e-07,
|
| 780 |
+
"logits/chosen": -1.0928058624267578,
|
| 781 |
+
"logits/rejected": -1.079099416732788,
|
| 782 |
+
"logps/chosen": -0.3362935483455658,
|
| 783 |
+
"logps/rejected": -0.36446088552474976,
|
| 784 |
+
"loss": 94.7642,
|
| 785 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 786 |
+
"rewards/chosen": -0.8407338261604309,
|
| 787 |
+
"rewards/margins": 0.0704183503985405,
|
| 788 |
+
"rewards/rejected": -0.911152184009552,
|
| 789 |
+
"step": 255
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.555703980764093,
|
| 793 |
+
"grad_norm": 147041.27143323392,
|
| 794 |
+
"learning_rate": 4.887809678520975e-07,
|
| 795 |
+
"logits/chosen": -1.0703433752059937,
|
| 796 |
+
"logits/rejected": -1.0498476028442383,
|
| 797 |
+
"logps/chosen": -0.29196763038635254,
|
| 798 |
+
"logps/rejected": -0.3219326138496399,
|
| 799 |
+
"loss": 84.8449,
|
| 800 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 801 |
+
"rewards/chosen": -0.7299190759658813,
|
| 802 |
+
"rewards/margins": 0.07491237670183182,
|
| 803 |
+
"rewards/rejected": -0.8048315048217773,
|
| 804 |
+
"step": 260
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.566390595778787,
|
| 808 |
+
"grad_norm": 435566096526.86523,
|
| 809 |
+
"learning_rate": 4.700979230274829e-07,
|
| 810 |
+
"logits/chosen": -1.0955275297164917,
|
| 811 |
+
"logits/rejected": -1.0940407514572144,
|
| 812 |
+
"logps/chosen": -0.3326551914215088,
|
| 813 |
+
"logps/rejected": -0.35088759660720825,
|
| 814 |
+
"loss": 887.0658,
|
| 815 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 816 |
+
"rewards/chosen": -0.831637978553772,
|
| 817 |
+
"rewards/margins": 0.04558102414011955,
|
| 818 |
+
"rewards/rejected": -0.877219021320343,
|
| 819 |
+
"step": 265
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.5770772107934812,
|
| 823 |
+
"grad_norm": 3520938.773348992,
|
| 824 |
+
"learning_rate": 4.514566989613559e-07,
|
| 825 |
+
"logits/chosen": -1.086938500404358,
|
| 826 |
+
"logits/rejected": -1.0884182453155518,
|
| 827 |
+
"logps/chosen": -0.3024354875087738,
|
| 828 |
+
"logps/rejected": -0.29867392778396606,
|
| 829 |
+
"loss": 228.8071,
|
| 830 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 831 |
+
"rewards/chosen": -0.7560887336730957,
|
| 832 |
+
"rewards/margins": -0.009403971955180168,
|
| 833 |
+
"rewards/rejected": -0.7466848492622375,
|
| 834 |
+
"step": 270
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.5877638258081752,
|
| 838 |
+
"grad_norm": 62256.73172967315,
|
| 839 |
+
"learning_rate": 4.328833670911724e-07,
|
| 840 |
+
"logits/chosen": -0.9738815426826477,
|
| 841 |
+
"logits/rejected": -0.9222286343574524,
|
| 842 |
+
"logps/chosen": -0.2884615659713745,
|
| 843 |
+
"logps/rejected": -0.3087163269519806,
|
| 844 |
+
"loss": 1419.8171,
|
| 845 |
+
"rewards/accuracies": 0.4375,
|
| 846 |
+
"rewards/chosen": -0.721153974533081,
|
| 847 |
+
"rewards/margins": 0.05063692852854729,
|
| 848 |
+
"rewards/rejected": -0.7717908620834351,
|
| 849 |
+
"step": 275
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5984504408228694,
|
| 853 |
+
"grad_norm": 803294.007310266,
|
| 854 |
+
"learning_rate": 4.144039039010124e-07,
|
| 855 |
+
"logits/chosen": -1.1537045240402222,
|
| 856 |
+
"logits/rejected": -1.0968632698059082,
|
| 857 |
+
"logps/chosen": -0.33216923475265503,
|
| 858 |
+
"logps/rejected": -0.2991081774234772,
|
| 859 |
+
"loss": 301.7224,
|
| 860 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 861 |
+
"rewards/chosen": -0.8304230570793152,
|
| 862 |
+
"rewards/margins": -0.08265267312526703,
|
| 863 |
+
"rewards/rejected": -0.7477704286575317,
|
| 864 |
+
"step": 280
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.6091370558375635,
|
| 868 |
+
"grad_norm": 263927.3164272957,
|
| 869 |
+
"learning_rate": 3.960441545911204e-07,
|
| 870 |
+
"logits/chosen": -1.044985055923462,
|
| 871 |
+
"logits/rejected": -1.0020415782928467,
|
| 872 |
+
"logps/chosen": -0.3105274736881256,
|
| 873 |
+
"logps/rejected": -0.3335118591785431,
|
| 874 |
+
"loss": 104.0724,
|
| 875 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 876 |
+
"rewards/chosen": -0.7763187289237976,
|
| 877 |
+
"rewards/margins": 0.057460904121398926,
|
| 878 |
+
"rewards/rejected": -0.8337796330451965,
|
| 879 |
+
"step": 285
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.6198236708522575,
|
| 883 |
+
"grad_norm": 4071370.4437897406,
|
| 884 |
+
"learning_rate": 3.778297969310529e-07,
|
| 885 |
+
"logits/chosen": -1.071925163269043,
|
| 886 |
+
"logits/rejected": -1.0407798290252686,
|
| 887 |
+
"logps/chosen": -0.3102174699306488,
|
| 888 |
+
"logps/rejected": -0.33250361680984497,
|
| 889 |
+
"loss": 156.4641,
|
| 890 |
+
"rewards/accuracies": 0.512499988079071,
|
| 891 |
+
"rewards/chosen": -0.7755436897277832,
|
| 892 |
+
"rewards/margins": 0.055715300142765045,
|
| 893 |
+
"rewards/rejected": -0.8312589526176453,
|
| 894 |
+
"step": 290
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.6305102858669517,
|
| 898 |
+
"grad_norm": 965178.0635991972,
|
| 899 |
+
"learning_rate": 3.5978630534699865e-07,
|
| 900 |
+
"logits/chosen": -1.1488522291183472,
|
| 901 |
+
"logits/rejected": -1.1228643655776978,
|
| 902 |
+
"logps/chosen": -0.3139174282550812,
|
| 903 |
+
"logps/rejected": -0.32147642970085144,
|
| 904 |
+
"loss": 134.6723,
|
| 905 |
+
"rewards/accuracies": 0.550000011920929,
|
| 906 |
+
"rewards/chosen": -0.784793496131897,
|
| 907 |
+
"rewards/margins": 0.01889752224087715,
|
| 908 |
+
"rewards/rejected": -0.8036910891532898,
|
| 909 |
+
"step": 295
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.6411969008816457,
|
| 913 |
+
"grad_norm": 20365408.82604466,
|
| 914 |
+
"learning_rate": 3.4193891529348795e-07,
|
| 915 |
+
"logits/chosen": -1.0468319654464722,
|
| 916 |
+
"logits/rejected": -1.0043448209762573,
|
| 917 |
+
"logps/chosen": -0.3311859369277954,
|
| 918 |
+
"logps/rejected": -0.3362448513507843,
|
| 919 |
+
"loss": 120.3211,
|
| 920 |
+
"rewards/accuracies": 0.4375,
|
| 921 |
+
"rewards/chosen": -0.8279649019241333,
|
| 922 |
+
"rewards/margins": 0.012647300958633423,
|
| 923 |
+
"rewards/rejected": -0.8406121134757996,
|
| 924 |
+
"step": 300
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.6518835158963399,
|
| 928 |
+
"grad_norm": 68905.1696103493,
|
| 929 |
+
"learning_rate": 3.243125879593286e-07,
|
| 930 |
+
"logits/chosen": -1.1107118129730225,
|
| 931 |
+
"logits/rejected": -1.0741993188858032,
|
| 932 |
+
"logps/chosen": -0.3406161665916443,
|
| 933 |
+
"logps/rejected": -0.32983919978141785,
|
| 934 |
+
"loss": 118.2299,
|
| 935 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 936 |
+
"rewards/chosen": -0.8515404462814331,
|
| 937 |
+
"rewards/margins": -0.026942413300275803,
|
| 938 |
+
"rewards/rejected": -0.8245980143547058,
|
| 939 |
+
"step": 305
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.6625701309110339,
|
| 943 |
+
"grad_norm": 3378905.921798347,
|
| 944 |
+
"learning_rate": 3.069319753571269e-07,
|
| 945 |
+
"logits/chosen": -1.069124460220337,
|
| 946 |
+
"logits/rejected": -1.110024094581604,
|
| 947 |
+
"logps/chosen": -0.3401089012622833,
|
| 948 |
+
"logps/rejected": -0.37533271312713623,
|
| 949 |
+
"loss": 151.3316,
|
| 950 |
+
"rewards/accuracies": 0.5,
|
| 951 |
+
"rewards/chosen": -0.8502721786499023,
|
| 952 |
+
"rewards/margins": 0.08805962651968002,
|
| 953 |
+
"rewards/rejected": -0.9383317828178406,
|
| 954 |
+
"step": 310
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.673256745925728,
|
| 958 |
+
"grad_norm": 27112706002.48435,
|
| 959 |
+
"learning_rate": 2.898213858452173e-07,
|
| 960 |
+
"logits/chosen": -1.2464616298675537,
|
| 961 |
+
"logits/rejected": -1.1925503015518188,
|
| 962 |
+
"logps/chosen": -0.34163057804107666,
|
| 963 |
+
"logps/rejected": -0.34519410133361816,
|
| 964 |
+
"loss": 951.2437,
|
| 965 |
+
"rewards/accuracies": 0.512499988079071,
|
| 966 |
+
"rewards/chosen": -0.8540765047073364,
|
| 967 |
+
"rewards/margins": 0.00890885479748249,
|
| 968 |
+
"rewards/rejected": -0.8629853129386902,
|
| 969 |
+
"step": 315
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.6839433609404221,
|
| 973 |
+
"grad_norm": 34759765.70829812,
|
| 974 |
+
"learning_rate": 2.730047501302266e-07,
|
| 975 |
+
"logits/chosen": -1.1456632614135742,
|
| 976 |
+
"logits/rejected": -1.1187629699707031,
|
| 977 |
+
"logps/chosen": -0.3103678226470947,
|
| 978 |
+
"logps/rejected": -0.35759711265563965,
|
| 979 |
+
"loss": 140.3946,
|
| 980 |
+
"rewards/accuracies": 0.574999988079071,
|
| 981 |
+
"rewards/chosen": -0.7759194374084473,
|
| 982 |
+
"rewards/margins": 0.11807328462600708,
|
| 983 |
+
"rewards/rejected": -0.8939927816390991,
|
| 984 |
+
"step": 320
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.6946299759551162,
|
| 988 |
+
"grad_norm": 250533.47771917153,
|
| 989 |
+
"learning_rate": 2.5650558779781635e-07,
|
| 990 |
+
"logits/chosen": -1.0254387855529785,
|
| 991 |
+
"logits/rejected": -1.0484802722930908,
|
| 992 |
+
"logps/chosen": -0.3333364427089691,
|
| 993 |
+
"logps/rejected": -0.3406026363372803,
|
| 994 |
+
"loss": 110.2831,
|
| 995 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 996 |
+
"rewards/chosen": -0.8333410024642944,
|
| 997 |
+
"rewards/margins": 0.01816548779606819,
|
| 998 |
+
"rewards/rejected": -0.8515065312385559,
|
| 999 |
+
"step": 325
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.7053165909698104,
|
| 1003 |
+
"grad_norm": 112400196.05235167,
|
| 1004 |
+
"learning_rate": 2.403469744184154e-07,
|
| 1005 |
+
"logits/chosen": -1.15934157371521,
|
| 1006 |
+
"logits/rejected": -1.1072492599487305,
|
| 1007 |
+
"logps/chosen": -0.3412119746208191,
|
| 1008 |
+
"logps/rejected": -0.37822234630584717,
|
| 1009 |
+
"loss": 171.9244,
|
| 1010 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1011 |
+
"rewards/chosen": -0.8530298471450806,
|
| 1012 |
+
"rewards/margins": 0.09252593666315079,
|
| 1013 |
+
"rewards/rejected": -0.9455558061599731,
|
| 1014 |
+
"step": 330
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.7160032059845044,
|
| 1018 |
+
"grad_norm": 9446757.557474248,
|
| 1019 |
+
"learning_rate": 2.2455150927394878e-07,
|
| 1020 |
+
"logits/chosen": -1.1374088525772095,
|
| 1021 |
+
"logits/rejected": -1.1560612916946411,
|
| 1022 |
+
"logps/chosen": -0.3190115988254547,
|
| 1023 |
+
"logps/rejected": -0.34075072407722473,
|
| 1024 |
+
"loss": 93.1427,
|
| 1025 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1026 |
+
"rewards/chosen": -0.7975289225578308,
|
| 1027 |
+
"rewards/margins": 0.05434788018465042,
|
| 1028 |
+
"rewards/rejected": -0.8518768548965454,
|
| 1029 |
+
"step": 335
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.7266898209991985,
|
| 1033 |
+
"grad_norm": 16695168.934409656,
|
| 1034 |
+
"learning_rate": 2.0914128375069722e-07,
|
| 1035 |
+
"logits/chosen": -1.0877724885940552,
|
| 1036 |
+
"logits/rejected": -1.0620936155319214,
|
| 1037 |
+
"logps/chosen": -0.30620652437210083,
|
| 1038 |
+
"logps/rejected": -0.33592310547828674,
|
| 1039 |
+
"loss": 120.7583,
|
| 1040 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1041 |
+
"rewards/chosen": -0.7655162811279297,
|
| 1042 |
+
"rewards/margins": 0.07429146766662598,
|
| 1043 |
+
"rewards/rejected": -0.8398076891899109,
|
| 1044 |
+
"step": 340
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.7373764360138926,
|
| 1048 |
+
"grad_norm": 4144624.6729695094,
|
| 1049 |
+
"learning_rate": 1.9413785044249676e-07,
|
| 1050 |
+
"logits/chosen": -1.0486472845077515,
|
| 1051 |
+
"logits/rejected": -1.0094027519226074,
|
| 1052 |
+
"logps/chosen": -0.30639034509658813,
|
| 1053 |
+
"logps/rejected": -0.321176141500473,
|
| 1054 |
+
"loss": 164.1478,
|
| 1055 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1056 |
+
"rewards/chosen": -0.765975832939148,
|
| 1057 |
+
"rewards/margins": 0.03696460276842117,
|
| 1058 |
+
"rewards/rejected": -0.8029405474662781,
|
| 1059 |
+
"step": 345
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7480630510285867,
|
| 1063 |
+
"grad_norm": 23390472.719695035,
|
| 1064 |
+
"learning_rate": 1.7956219300748792e-07,
|
| 1065 |
+
"logits/chosen": -1.1522271633148193,
|
| 1066 |
+
"logits/rejected": -1.1415410041809082,
|
| 1067 |
+
"logps/chosen": -0.34453052282333374,
|
| 1068 |
+
"logps/rejected": -0.3794510066509247,
|
| 1069 |
+
"loss": 555.5947,
|
| 1070 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1071 |
+
"rewards/chosen": -0.8613262176513672,
|
| 1072 |
+
"rewards/margins": 0.08730128407478333,
|
| 1073 |
+
"rewards/rejected": -0.9486274719238281,
|
| 1074 |
+
"step": 350
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7587496660432808,
|
| 1078 |
+
"grad_norm": 1280169.965933302,
|
| 1079 |
+
"learning_rate": 1.6543469682057104e-07,
|
| 1080 |
+
"logits/chosen": -1.1356937885284424,
|
| 1081 |
+
"logits/rejected": -1.0751426219940186,
|
| 1082 |
+
"logps/chosen": -0.3311988413333893,
|
| 1083 |
+
"logps/rejected": -0.3161237835884094,
|
| 1084 |
+
"loss": 82.217,
|
| 1085 |
+
"rewards/accuracies": 0.5,
|
| 1086 |
+
"rewards/chosen": -0.827997088432312,
|
| 1087 |
+
"rewards/margins": -0.037687692791223526,
|
| 1088 |
+
"rewards/rejected": -0.7903094291687012,
|
| 1089 |
+
"step": 355
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.7694362810579749,
|
| 1093 |
+
"grad_norm": 1956574.339469866,
|
| 1094 |
+
"learning_rate": 1.5177512046261666e-07,
|
| 1095 |
+
"logits/chosen": -1.1374176740646362,
|
| 1096 |
+
"logits/rejected": -1.164374589920044,
|
| 1097 |
+
"logps/chosen": -0.3486614227294922,
|
| 1098 |
+
"logps/rejected": -0.3802019953727722,
|
| 1099 |
+
"loss": 102.3601,
|
| 1100 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1101 |
+
"rewards/chosen": -0.8716535568237305,
|
| 1102 |
+
"rewards/margins": 0.07885149866342545,
|
| 1103 |
+
"rewards/rejected": -0.9505050778388977,
|
| 1104 |
+
"step": 360
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.7801228960726689,
|
| 1108 |
+
"grad_norm": 84129.78530171402,
|
| 1109 |
+
"learning_rate": 1.3860256808630427e-07,
|
| 1110 |
+
"logits/chosen": -1.137064814567566,
|
| 1111 |
+
"logits/rejected": -1.0832656621932983,
|
| 1112 |
+
"logps/chosen": -0.32139506936073303,
|
| 1113 |
+
"logps/rejected": -0.3225245177745819,
|
| 1114 |
+
"loss": 117.2444,
|
| 1115 |
+
"rewards/accuracies": 0.5,
|
| 1116 |
+
"rewards/chosen": -0.8034876585006714,
|
| 1117 |
+
"rewards/margins": 0.0028236303478479385,
|
| 1118 |
+
"rewards/rejected": -0.806311309337616,
|
| 1119 |
+
"step": 365
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.7908095110873631,
|
| 1123 |
+
"grad_norm": 4136765.760326951,
|
| 1124 |
+
"learning_rate": 1.2593546269723647e-07,
|
| 1125 |
+
"logits/chosen": -1.1603561639785767,
|
| 1126 |
+
"logits/rejected": -1.1292134523391724,
|
| 1127 |
+
"logps/chosen": -0.33979296684265137,
|
| 1128 |
+
"logps/rejected": -0.35157322883605957,
|
| 1129 |
+
"loss": 106.6815,
|
| 1130 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1131 |
+
"rewards/chosen": -0.8494824171066284,
|
| 1132 |
+
"rewards/margins": 0.029450654983520508,
|
| 1133 |
+
"rewards/rejected": -0.8789331316947937,
|
| 1134 |
+
"step": 370
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.8014961261020572,
|
| 1138 |
+
"grad_norm": 14999761.486437708,
|
| 1139 |
+
"learning_rate": 1.1379152038770029e-07,
|
| 1140 |
+
"logits/chosen": -1.1542747020721436,
|
| 1141 |
+
"logits/rejected": -1.172849416732788,
|
| 1142 |
+
"logps/chosen": -0.31457456946372986,
|
| 1143 |
+
"logps/rejected": -0.369545042514801,
|
| 1144 |
+
"loss": 120.5736,
|
| 1145 |
+
"rewards/accuracies": 0.612500011920929,
|
| 1146 |
+
"rewards/chosen": -0.7864364385604858,
|
| 1147 |
+
"rewards/margins": 0.1374262273311615,
|
| 1148 |
+
"rewards/rejected": -0.923862636089325,
|
| 1149 |
+
"step": 375
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.8121827411167513,
|
| 1153 |
+
"grad_norm": 244556.56746403236,
|
| 1154 |
+
"learning_rate": 1.0218772555910954e-07,
|
| 1155 |
+
"logits/chosen": -1.2167600393295288,
|
| 1156 |
+
"logits/rejected": -1.1646716594696045,
|
| 1157 |
+
"logps/chosen": -0.37414881587028503,
|
| 1158 |
+
"logps/rejected": -0.3576270043849945,
|
| 1159 |
+
"loss": 113.0907,
|
| 1160 |
+
"rewards/accuracies": 0.4375,
|
| 1161 |
+
"rewards/chosen": -0.9353721737861633,
|
| 1162 |
+
"rewards/margins": -0.041304655373096466,
|
| 1163 |
+
"rewards/rejected": -0.8940675854682922,
|
| 1164 |
+
"step": 380
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.8228693561314454,
|
| 1168 |
+
"grad_norm": 1775127.4439502584,
|
| 1169 |
+
"learning_rate": 9.114030716778432e-08,
|
| 1170 |
+
"logits/chosen": -1.1325044631958008,
|
| 1171 |
+
"logits/rejected": -1.110126256942749,
|
| 1172 |
+
"logps/chosen": -0.3134748637676239,
|
| 1173 |
+
"logps/rejected": -0.35259318351745605,
|
| 1174 |
+
"loss": 114.6353,
|
| 1175 |
+
"rewards/accuracies": 0.512499988079071,
|
| 1176 |
+
"rewards/chosen": -0.7836871147155762,
|
| 1177 |
+
"rewards/margins": 0.09779568761587143,
|
| 1178 |
+
"rewards/rejected": -0.8814828991889954,
|
| 1179 |
+
"step": 385
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.8335559711461394,
|
| 1183 |
+
"grad_norm": 138946.22290507445,
|
| 1184 |
+
"learning_rate": 8.066471602728803e-08,
|
| 1185 |
+
"logits/chosen": -1.220655083656311,
|
| 1186 |
+
"logits/rejected": -1.1926963329315186,
|
| 1187 |
+
"logps/chosen": -0.33643871545791626,
|
| 1188 |
+
"logps/rejected": -0.3400726318359375,
|
| 1189 |
+
"loss": 205.2888,
|
| 1190 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1191 |
+
"rewards/chosen": -0.8410967588424683,
|
| 1192 |
+
"rewards/margins": 0.009084770455956459,
|
| 1193 |
+
"rewards/rejected": -0.8501815795898438,
|
| 1194 |
+
"step": 390
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.8442425861608336,
|
| 1198 |
+
"grad_norm": 1993392.8238311838,
|
| 1199 |
+
"learning_rate": 7.077560319906694e-08,
|
| 1200 |
+
"logits/chosen": -1.0875790119171143,
|
| 1201 |
+
"logits/rejected": -1.0107152462005615,
|
| 1202 |
+
"logps/chosen": -0.3748469948768616,
|
| 1203 |
+
"logps/rejected": -0.380262553691864,
|
| 1204 |
+
"loss": 150.502,
|
| 1205 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 1206 |
+
"rewards/chosen": -0.9371173977851868,
|
| 1207 |
+
"rewards/margins": 0.013538897037506104,
|
| 1208 |
+
"rewards/rejected": -0.950656533241272,
|
| 1209 |
+
"step": 395
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.8549292011755276,
|
| 1213 |
+
"grad_norm": 42068510.12370043,
|
| 1214 |
+
"learning_rate": 6.148679950161672e-08,
|
| 1215 |
+
"logits/chosen": -1.1116609573364258,
|
| 1216 |
+
"logits/rejected": -1.0628454685211182,
|
| 1217 |
+
"logps/chosen": -0.36634019017219543,
|
| 1218 |
+
"logps/rejected": -0.35744190216064453,
|
| 1219 |
+
"loss": 196.6313,
|
| 1220 |
+
"rewards/accuracies": 0.5,
|
| 1221 |
+
"rewards/chosen": -0.9158504605293274,
|
| 1222 |
+
"rewards/margins": -0.022245775908231735,
|
| 1223 |
+
"rewards/rejected": -0.8936047554016113,
|
| 1224 |
+
"step": 400
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.8549292011755276,
|
| 1228 |
+
"eval_logits/chosen": -1.337195634841919,
|
| 1229 |
+
"eval_logits/rejected": -1.2981722354888916,
|
| 1230 |
+
"eval_logps/chosen": -0.3401065170764923,
|
| 1231 |
+
"eval_logps/rejected": -0.35557428002357483,
|
| 1232 |
+
"eval_loss": 132.36317443847656,
|
| 1233 |
+
"eval_rewards/accuracies": 0.5040322542190552,
|
| 1234 |
+
"eval_rewards/chosen": -0.8502662181854248,
|
| 1235 |
+
"eval_rewards/margins": 0.038669489324092865,
|
| 1236 |
+
"eval_rewards/rejected": -0.8889357447624207,
|
| 1237 |
+
"eval_runtime": 72.0543,
|
| 1238 |
+
"eval_samples_per_second": 27.216,
|
| 1239 |
+
"eval_steps_per_second": 0.86,
|
| 1240 |
+
"step": 400
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 0.8656158161902218,
|
| 1244 |
+
"grad_norm": 5594982.665070933,
|
| 1245 |
+
"learning_rate": 5.2811296166831666e-08,
|
| 1246 |
+
"logits/chosen": -1.1403666734695435,
|
| 1247 |
+
"logits/rejected": -1.0579333305358887,
|
| 1248 |
+
"logps/chosen": -0.34073713421821594,
|
| 1249 |
+
"logps/rejected": -0.33352339267730713,
|
| 1250 |
+
"loss": 122.7746,
|
| 1251 |
+
"rewards/accuracies": 0.4375,
|
| 1252 |
+
"rewards/chosen": -0.8518427610397339,
|
| 1253 |
+
"rewards/margins": -0.01803441345691681,
|
| 1254 |
+
"rewards/rejected": -0.833808422088623,
|
| 1255 |
+
"step": 405
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8763024312049158,
|
| 1259 |
+
"grad_norm": 365339.7208405054,
|
| 1260 |
+
"learning_rate": 4.4761226670592066e-08,
|
| 1261 |
+
"logits/chosen": -1.0983816385269165,
|
| 1262 |
+
"logits/rejected": -1.0836502313613892,
|
| 1263 |
+
"logps/chosen": -0.33261579275131226,
|
| 1264 |
+
"logps/rejected": -0.3417048752307892,
|
| 1265 |
+
"loss": 111.2202,
|
| 1266 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 1267 |
+
"rewards/chosen": -0.831539511680603,
|
| 1268 |
+
"rewards/margins": 0.022722622379660606,
|
| 1269 |
+
"rewards/rejected": -0.8542621731758118,
|
| 1270 |
+
"step": 410
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.88698904621961,
|
| 1274 |
+
"grad_norm": 2850565.0664724754,
|
| 1275 |
+
"learning_rate": 3.734784976300165e-08,
|
| 1276 |
+
"logits/chosen": -1.0673637390136719,
|
| 1277 |
+
"logits/rejected": -1.040725827217102,
|
| 1278 |
+
"logps/chosen": -0.34171849489212036,
|
| 1279 |
+
"logps/rejected": -0.348112016916275,
|
| 1280 |
+
"loss": 191.3689,
|
| 1281 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 1282 |
+
"rewards/chosen": -0.8542962074279785,
|
| 1283 |
+
"rewards/margins": 0.015983855351805687,
|
| 1284 |
+
"rewards/rejected": -0.8702800869941711,
|
| 1285 |
+
"step": 415
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.897675661234304,
|
| 1289 |
+
"grad_norm": 507688.39572092163,
|
| 1290 |
+
"learning_rate": 3.058153372200695e-08,
|
| 1291 |
+
"logits/chosen": -1.1354072093963623,
|
| 1292 |
+
"logits/rejected": -1.1297013759613037,
|
| 1293 |
+
"logps/chosen": -0.3288155198097229,
|
| 1294 |
+
"logps/rejected": -0.3461647629737854,
|
| 1295 |
+
"loss": 112.2704,
|
| 1296 |
+
"rewards/accuracies": 0.4375,
|
| 1297 |
+
"rewards/chosen": -0.8220387697219849,
|
| 1298 |
+
"rewards/margins": 0.04337311536073685,
|
| 1299 |
+
"rewards/rejected": -0.8654119372367859,
|
| 1300 |
+
"step": 420
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.9083622762489981,
|
| 1304 |
+
"grad_norm": 7451525102.30645,
|
| 1305 |
+
"learning_rate": 2.4471741852423233e-08,
|
| 1306 |
+
"logits/chosen": -1.0978658199310303,
|
| 1307 |
+
"logits/rejected": -1.0448986291885376,
|
| 1308 |
+
"logps/chosen": -0.3529340624809265,
|
| 1309 |
+
"logps/rejected": -0.35007423162460327,
|
| 1310 |
+
"loss": 3170.9543,
|
| 1311 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1312 |
+
"rewards/chosen": -0.8823351860046387,
|
| 1313 |
+
"rewards/margins": -0.007149559445679188,
|
| 1314 |
+
"rewards/rejected": -0.8751856088638306,
|
| 1315 |
+
"step": 425
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.9190488912636923,
|
| 1319 |
+
"grad_norm": 10934704.996058388,
|
| 1320 |
+
"learning_rate": 1.9027019250647036e-08,
|
| 1321 |
+
"logits/chosen": -1.1120647192001343,
|
| 1322 |
+
"logits/rejected": -1.0629384517669678,
|
| 1323 |
+
"logps/chosen": -0.30386024713516235,
|
| 1324 |
+
"logps/rejected": -0.31913992762565613,
|
| 1325 |
+
"loss": 237.2099,
|
| 1326 |
+
"rewards/accuracies": 0.5625,
|
| 1327 |
+
"rewards/chosen": -0.759650707244873,
|
| 1328 |
+
"rewards/margins": 0.03819913789629936,
|
| 1329 |
+
"rewards/rejected": -0.7978497743606567,
|
| 1330 |
+
"step": 430
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.9297355062783863,
|
| 1334 |
+
"grad_norm": 1059239098.6557789,
|
| 1335 |
+
"learning_rate": 1.4254980853566246e-08,
|
| 1336 |
+
"logits/chosen": -1.1208689212799072,
|
| 1337 |
+
"logits/rejected": -1.076522946357727,
|
| 1338 |
+
"logps/chosen": -0.3260021507740021,
|
| 1339 |
+
"logps/rejected": -0.32419848442077637,
|
| 1340 |
+
"loss": 252.7438,
|
| 1341 |
+
"rewards/accuracies": 0.5,
|
| 1342 |
+
"rewards/chosen": -0.8150054216384888,
|
| 1343 |
+
"rewards/margins": -0.004509164486080408,
|
| 1344 |
+
"rewards/rejected": -0.8104962110519409,
|
| 1345 |
+
"step": 435
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 0.9404221212930804,
|
| 1349 |
+
"grad_norm": 3163894.8555042273,
|
| 1350 |
+
"learning_rate": 1.016230078838226e-08,
|
| 1351 |
+
"logits/chosen": -1.1477479934692383,
|
| 1352 |
+
"logits/rejected": -1.1257246732711792,
|
| 1353 |
+
"logps/chosen": -0.3194740116596222,
|
| 1354 |
+
"logps/rejected": -0.3639461398124695,
|
| 1355 |
+
"loss": 283.9071,
|
| 1356 |
+
"rewards/accuracies": 0.574999988079071,
|
| 1357 |
+
"rewards/chosen": -0.7986849546432495,
|
| 1358 |
+
"rewards/margins": 0.11118029057979584,
|
| 1359 |
+
"rewards/rejected": -0.9098652601242065,
|
| 1360 |
+
"step": 440
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.9511087363077745,
|
| 1364 |
+
"grad_norm": 313415.0194399257,
|
| 1365 |
+
"learning_rate": 6.754703038239329e-09,
|
| 1366 |
+
"logits/chosen": -1.1323530673980713,
|
| 1367 |
+
"logits/rejected": -1.0702521800994873,
|
| 1368 |
+
"logps/chosen": -0.323483407497406,
|
| 1369 |
+
"logps/rejected": -0.3070305287837982,
|
| 1370 |
+
"loss": 142.406,
|
| 1371 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 1372 |
+
"rewards/chosen": -0.8087084889411926,
|
| 1373 |
+
"rewards/margins": -0.041132211685180664,
|
| 1374 |
+
"rewards/rejected": -0.7675763368606567,
|
| 1375 |
+
"step": 445
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.9617953513224686,
|
| 1379 |
+
"grad_norm": 312608.20391974325,
|
| 1380 |
+
"learning_rate": 4.036953436716895e-09,
|
| 1381 |
+
"logits/chosen": -1.0631930828094482,
|
| 1382 |
+
"logits/rejected": -1.0676857233047485,
|
| 1383 |
+
"logps/chosen": -0.34714624285697937,
|
| 1384 |
+
"logps/rejected": -0.3853607773780823,
|
| 1385 |
+
"loss": 98.3866,
|
| 1386 |
+
"rewards/accuracies": 0.5,
|
| 1387 |
+
"rewards/chosen": -0.8678655624389648,
|
| 1388 |
+
"rewards/margins": 0.09553632885217667,
|
| 1389 |
+
"rewards/rejected": -0.9634019136428833,
|
| 1390 |
+
"step": 450
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 0.9724819663371627,
|
| 1394 |
+
"grad_norm": 98094.25868242758,
|
| 1395 |
+
"learning_rate": 2.0128530023804656e-09,
|
| 1396 |
+
"logits/chosen": -1.1627556085586548,
|
| 1397 |
+
"logits/rejected": -1.131043791770935,
|
| 1398 |
+
"logps/chosen": -0.34627044200897217,
|
| 1399 |
+
"logps/rejected": -0.32559770345687866,
|
| 1400 |
+
"loss": 136.3491,
|
| 1401 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 1402 |
+
"rewards/chosen": -0.8656761050224304,
|
| 1403 |
+
"rewards/margins": -0.05168183892965317,
|
| 1404 |
+
"rewards/rejected": -0.813994288444519,
|
| 1405 |
+
"step": 455
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.9831685813518568,
|
| 1409 |
+
"grad_norm": 25583015.430213835,
|
| 1410 |
+
"learning_rate": 6.852326227130833e-10,
|
| 1411 |
+
"logits/chosen": -1.1027119159698486,
|
| 1412 |
+
"logits/rejected": -1.1237401962280273,
|
| 1413 |
+
"logps/chosen": -0.33976924419403076,
|
| 1414 |
+
"logps/rejected": -0.3329155147075653,
|
| 1415 |
+
"loss": 116.0967,
|
| 1416 |
+
"rewards/accuracies": 0.4375,
|
| 1417 |
+
"rewards/chosen": -0.8494230508804321,
|
| 1418 |
+
"rewards/margins": -0.01713428646326065,
|
| 1419 |
+
"rewards/rejected": -0.8322887420654297,
|
| 1420 |
+
"step": 460
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.9938551963665508,
|
| 1424 |
+
"grad_norm": 351352.5694241463,
|
| 1425 |
+
"learning_rate": 5.594909486328348e-11,
|
| 1426 |
+
"logits/chosen": -1.212425947189331,
|
| 1427 |
+
"logits/rejected": -1.1084251403808594,
|
| 1428 |
+
"logps/chosen": -0.3214932084083557,
|
| 1429 |
+
"logps/rejected": -0.3376317620277405,
|
| 1430 |
+
"loss": 2736.6258,
|
| 1431 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 1432 |
+
"rewards/chosen": -0.8037330508232117,
|
| 1433 |
+
"rewards/margins": 0.04034631699323654,
|
| 1434 |
+
"rewards/rejected": -0.844079315662384,
|
| 1435 |
+
"step": 465
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.9981298423724285,
|
| 1439 |
+
"step": 467,
|
| 1440 |
+
"total_flos": 0.0,
|
| 1441 |
+
"train_loss": 444.38003229635433,
|
| 1442 |
+
"train_runtime": 7255.1322,
|
| 1443 |
+
"train_samples_per_second": 8.253,
|
| 1444 |
+
"train_steps_per_second": 0.064
|
| 1445 |
+
}
|
| 1446 |
+
],
|
| 1447 |
+
"logging_steps": 5,
|
| 1448 |
+
"max_steps": 467,
|
| 1449 |
+
"num_input_tokens_seen": 0,
|
| 1450 |
+
"num_train_epochs": 1,
|
| 1451 |
+
"save_steps": 1000000,
|
| 1452 |
+
"stateful_callbacks": {
|
| 1453 |
+
"TrainerControl": {
|
| 1454 |
+
"args": {
|
| 1455 |
+
"should_epoch_stop": false,
|
| 1456 |
+
"should_evaluate": false,
|
| 1457 |
+
"should_log": false,
|
| 1458 |
+
"should_save": false,
|
| 1459 |
+
"should_training_stop": false
|
| 1460 |
+
},
|
| 1461 |
+
"attributes": {}
|
| 1462 |
+
}
|
| 1463 |
+
},
|
| 1464 |
+
"total_flos": 0.0,
|
| 1465 |
+
"train_batch_size": 2,
|
| 1466 |
+
"trial_name": null,
|
| 1467 |
+
"trial_params": null
|
| 1468 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60725d6b75d3e4a13fc20b5f5f266b1766b735faed8c0d5158a1d2ad97643af7
|
| 3 |
+
size 6840
|