Teng Xiao
commited on
Commit
•
9484d16
1
Parent(s):
9c6c800
TX
Browse files- README.md +60 -0
- all_results.json +9 -0
- config.json +28 -0
- generation_config.json +6 -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 +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2063 -0
- train_results.json +9 -0
- trainer_state.json +1455 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: princeton-nlp/Llama-3-Base-8B-SFT
|
3 |
+
tags:
|
4 |
+
- alignment_handbook-handbook
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
8 |
+
model-index:
|
9 |
+
- name: Llama-8b-MI01
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Llama-8b-MI01
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [princeton-nlp/Llama-3-Base-8B-SFT](https://huggingface.co/princeton-nlp/Llama-3-Base-8B-SFT) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-07
|
38 |
+
- train_batch_size: 2
|
39 |
+
- eval_batch_size: 4
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: multi-GPU
|
42 |
+
- num_devices: 4
|
43 |
+
- gradient_accumulation_steps: 16
|
44 |
+
- total_train_batch_size: 128
|
45 |
+
- total_eval_batch_size: 16
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 1
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.40.2
|
58 |
+
- Pytorch 2.1.2+cu121
|
59 |
+
- Datasets 2.14.6
|
60 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.998691442030882,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 1.7629729861733299,
|
5 |
+
"train_runtime": 8203.4319,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 7.452,
|
8 |
+
"train_steps_per_second": 0.058
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "princeton-nlp/Llama-3-Base-8B-SFT",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128001,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 500000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.40.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 128256
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 128000,
|
4 |
+
"eos_token_id": 128001,
|
5 |
+
"transformers_version": "4.40.2"
|
6 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6b8a40d200fde1daaa2637622ab17968450fe8d172e8da98093f7d08b5ffe33
|
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:e8774c46cc7e50baf36c30c49cfaf56bffb0a6b1038b7563674e3feb7aedec40
|
3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:116b00d7eda9aa48d5ed63d2881e1c292448a7a7641b3f87b949a78cebac3202
|
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:dba9f39c83fd1a739bc2aaf1b00f6bfa07b4a2a094bb6a3bdc3e99d285704df2
|
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 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|end_of_text|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end_of_text|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
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": "<|end_of_text|>",
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 2048,
|
2061 |
+
"pad_token": "<|end_of_text|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.998691442030882,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 1.7629729861733299,
|
5 |
+
"train_runtime": 8203.4319,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 7.452,
|
8 |
+
"train_steps_per_second": 0.058
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1455 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.998691442030882,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 477,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.010468463752944255,
|
13 |
+
"grad_norm": 1.1784705641049245,
|
14 |
+
"learning_rate": 5.208333333333333e-08,
|
15 |
+
"logits/chosen": -1.4463237524032593,
|
16 |
+
"logits/rejected": -1.4477096796035767,
|
17 |
+
"logps/chosen": -7.9823808670043945,
|
18 |
+
"logps/rejected": -8.155555725097656,
|
19 |
+
"loss": 1.798,
|
20 |
+
"rewards/accuracies": 0.5,
|
21 |
+
"rewards/chosen": -7.9823808670043945,
|
22 |
+
"rewards/margins": 0.1731749176979065,
|
23 |
+
"rewards/rejected": -8.155555725097656,
|
24 |
+
"step": 5
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.02093692750588851,
|
28 |
+
"grad_norm": 0.9602764459933493,
|
29 |
+
"learning_rate": 1.0416666666666667e-07,
|
30 |
+
"logits/chosen": -1.4451031684875488,
|
31 |
+
"logits/rejected": -1.436326265335083,
|
32 |
+
"logps/chosen": -8.046354293823242,
|
33 |
+
"logps/rejected": -7.959715843200684,
|
34 |
+
"loss": 1.7982,
|
35 |
+
"rewards/accuracies": 0.4937500059604645,
|
36 |
+
"rewards/chosen": -8.046354293823242,
|
37 |
+
"rewards/margins": -0.0866377204656601,
|
38 |
+
"rewards/rejected": -7.959715843200684,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.031405391258832765,
|
43 |
+
"grad_norm": 1.689559474976433,
|
44 |
+
"learning_rate": 1.5624999999999999e-07,
|
45 |
+
"logits/chosen": -1.448919415473938,
|
46 |
+
"logits/rejected": -1.444911003112793,
|
47 |
+
"logps/chosen": -7.851029872894287,
|
48 |
+
"logps/rejected": -7.866568565368652,
|
49 |
+
"loss": 1.789,
|
50 |
+
"rewards/accuracies": 0.5,
|
51 |
+
"rewards/chosen": -7.851029872894287,
|
52 |
+
"rewards/margins": 0.015538657084107399,
|
53 |
+
"rewards/rejected": -7.866568565368652,
|
54 |
+
"step": 15
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.04187385501177702,
|
58 |
+
"grad_norm": 1.4544738071780356,
|
59 |
+
"learning_rate": 2.0833333333333333e-07,
|
60 |
+
"logits/chosen": -1.4363288879394531,
|
61 |
+
"logits/rejected": -1.4409823417663574,
|
62 |
+
"logps/chosen": -8.180266380310059,
|
63 |
+
"logps/rejected": -8.204001426696777,
|
64 |
+
"loss": 1.8048,
|
65 |
+
"rewards/accuracies": 0.5,
|
66 |
+
"rewards/chosen": -8.180266380310059,
|
67 |
+
"rewards/margins": 0.023736288771033287,
|
68 |
+
"rewards/rejected": -8.204001426696777,
|
69 |
+
"step": 20
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.05234231876472128,
|
73 |
+
"grad_norm": 1.304458351649718,
|
74 |
+
"learning_rate": 2.604166666666667e-07,
|
75 |
+
"logits/chosen": -1.475970983505249,
|
76 |
+
"logits/rejected": -1.4659450054168701,
|
77 |
+
"logps/chosen": -8.084822654724121,
|
78 |
+
"logps/rejected": -7.987278938293457,
|
79 |
+
"loss": 1.8124,
|
80 |
+
"rewards/accuracies": 0.4375,
|
81 |
+
"rewards/chosen": -8.084822654724121,
|
82 |
+
"rewards/margins": -0.09754323959350586,
|
83 |
+
"rewards/rejected": -7.987278938293457,
|
84 |
+
"step": 25
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.06281078251766553,
|
88 |
+
"grad_norm": 1.2140086077938599,
|
89 |
+
"learning_rate": 3.1249999999999997e-07,
|
90 |
+
"logits/chosen": -1.4456737041473389,
|
91 |
+
"logits/rejected": -1.4336217641830444,
|
92 |
+
"logps/chosen": -7.773144721984863,
|
93 |
+
"logps/rejected": -7.694056510925293,
|
94 |
+
"loss": 1.8017,
|
95 |
+
"rewards/accuracies": 0.46875,
|
96 |
+
"rewards/chosen": -7.773144721984863,
|
97 |
+
"rewards/margins": -0.0790884867310524,
|
98 |
+
"rewards/rejected": -7.694056510925293,
|
99 |
+
"step": 30
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.07327924627060979,
|
103 |
+
"grad_norm": 0.9984160768782803,
|
104 |
+
"learning_rate": 3.645833333333333e-07,
|
105 |
+
"logits/chosen": -1.4582607746124268,
|
106 |
+
"logits/rejected": -1.4302797317504883,
|
107 |
+
"logps/chosen": -7.980234622955322,
|
108 |
+
"logps/rejected": -7.845289707183838,
|
109 |
+
"loss": 1.7982,
|
110 |
+
"rewards/accuracies": 0.4937500059604645,
|
111 |
+
"rewards/chosen": -7.980234622955322,
|
112 |
+
"rewards/margins": -0.13494457304477692,
|
113 |
+
"rewards/rejected": -7.845289707183838,
|
114 |
+
"step": 35
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.08374771002355404,
|
118 |
+
"grad_norm": 0.8920926404480951,
|
119 |
+
"learning_rate": 4.1666666666666667e-07,
|
120 |
+
"logits/chosen": -1.454561471939087,
|
121 |
+
"logits/rejected": -1.4629584550857544,
|
122 |
+
"logps/chosen": -7.85833740234375,
|
123 |
+
"logps/rejected": -8.055027961730957,
|
124 |
+
"loss": 1.8008,
|
125 |
+
"rewards/accuracies": 0.48124998807907104,
|
126 |
+
"rewards/chosen": -7.85833740234375,
|
127 |
+
"rewards/margins": 0.19669005274772644,
|
128 |
+
"rewards/rejected": -8.055027961730957,
|
129 |
+
"step": 40
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.0942161737764983,
|
133 |
+
"grad_norm": 1.0898338388611548,
|
134 |
+
"learning_rate": 4.6874999999999996e-07,
|
135 |
+
"logits/chosen": -1.4877290725708008,
|
136 |
+
"logits/rejected": -1.485259771347046,
|
137 |
+
"logps/chosen": -7.855520725250244,
|
138 |
+
"logps/rejected": -7.64023494720459,
|
139 |
+
"loss": 1.7987,
|
140 |
+
"rewards/accuracies": 0.4625000059604645,
|
141 |
+
"rewards/chosen": -7.855520725250244,
|
142 |
+
"rewards/margins": -0.21528606116771698,
|
143 |
+
"rewards/rejected": -7.64023494720459,
|
144 |
+
"step": 45
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.10468463752944256,
|
148 |
+
"grad_norm": 1.166801443928394,
|
149 |
+
"learning_rate": 4.999731868769026e-07,
|
150 |
+
"logits/chosen": -1.477698564529419,
|
151 |
+
"logits/rejected": -1.4901760816574097,
|
152 |
+
"logps/chosen": -8.011387825012207,
|
153 |
+
"logps/rejected": -8.05154037475586,
|
154 |
+
"loss": 1.8065,
|
155 |
+
"rewards/accuracies": 0.518750011920929,
|
156 |
+
"rewards/chosen": -8.011387825012207,
|
157 |
+
"rewards/margins": 0.040151696652173996,
|
158 |
+
"rewards/rejected": -8.05154037475586,
|
159 |
+
"step": 50
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.11515310128238682,
|
163 |
+
"grad_norm": 0.9751544943818836,
|
164 |
+
"learning_rate": 4.996716052911017e-07,
|
165 |
+
"logits/chosen": -1.48259699344635,
|
166 |
+
"logits/rejected": -1.4775769710540771,
|
167 |
+
"logps/chosen": -7.901836395263672,
|
168 |
+
"logps/rejected": -7.928590297698975,
|
169 |
+
"loss": 1.8086,
|
170 |
+
"rewards/accuracies": 0.4312500059604645,
|
171 |
+
"rewards/chosen": -7.901836395263672,
|
172 |
+
"rewards/margins": 0.0267526563256979,
|
173 |
+
"rewards/rejected": -7.928590297698975,
|
174 |
+
"step": 55
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.12562156503533106,
|
178 |
+
"grad_norm": 1.453860208239476,
|
179 |
+
"learning_rate": 4.990353313429303e-07,
|
180 |
+
"logits/chosen": -1.4845072031021118,
|
181 |
+
"logits/rejected": -1.495591402053833,
|
182 |
+
"logps/chosen": -7.9037041664123535,
|
183 |
+
"logps/rejected": -8.206459045410156,
|
184 |
+
"loss": 1.7865,
|
185 |
+
"rewards/accuracies": 0.606249988079071,
|
186 |
+
"rewards/chosen": -7.9037041664123535,
|
187 |
+
"rewards/margins": 0.30275601148605347,
|
188 |
+
"rewards/rejected": -8.206459045410156,
|
189 |
+
"step": 60
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.1360900287882753,
|
193 |
+
"grad_norm": 1.734106310553517,
|
194 |
+
"learning_rate": 4.980652179769217e-07,
|
195 |
+
"logits/chosen": -1.4411917924880981,
|
196 |
+
"logits/rejected": -1.4547481536865234,
|
197 |
+
"logps/chosen": -7.689724922180176,
|
198 |
+
"logps/rejected": -8.240130424499512,
|
199 |
+
"loss": 1.7898,
|
200 |
+
"rewards/accuracies": 0.59375,
|
201 |
+
"rewards/chosen": -7.689724922180176,
|
202 |
+
"rewards/margins": 0.5504060387611389,
|
203 |
+
"rewards/rejected": -8.240130424499512,
|
204 |
+
"step": 65
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.14655849254121958,
|
208 |
+
"grad_norm": 1.8736880005786551,
|
209 |
+
"learning_rate": 4.967625656594781e-07,
|
210 |
+
"logits/chosen": -1.430119514465332,
|
211 |
+
"logits/rejected": -1.420650839805603,
|
212 |
+
"logps/chosen": -7.873298645019531,
|
213 |
+
"logps/rejected": -7.9891533851623535,
|
214 |
+
"loss": 1.7922,
|
215 |
+
"rewards/accuracies": 0.518750011920929,
|
216 |
+
"rewards/chosen": -7.873298645019531,
|
217 |
+
"rewards/margins": 0.11585396528244019,
|
218 |
+
"rewards/rejected": -7.9891533851623535,
|
219 |
+
"step": 70
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.15702695629416383,
|
223 |
+
"grad_norm": 1.3664496432393678,
|
224 |
+
"learning_rate": 4.951291206355559e-07,
|
225 |
+
"logits/chosen": -1.4261605739593506,
|
226 |
+
"logits/rejected": -1.4281210899353027,
|
227 |
+
"logps/chosen": -7.770443916320801,
|
228 |
+
"logps/rejected": -7.860281467437744,
|
229 |
+
"loss": 1.7858,
|
230 |
+
"rewards/accuracies": 0.4749999940395355,
|
231 |
+
"rewards/chosen": -7.770443916320801,
|
232 |
+
"rewards/margins": 0.08983758091926575,
|
233 |
+
"rewards/rejected": -7.860281467437744,
|
234 |
+
"step": 75
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.16749542004710807,
|
238 |
+
"grad_norm": 1.6834122106300342,
|
239 |
+
"learning_rate": 4.93167072587771e-07,
|
240 |
+
"logits/chosen": -1.4214476346969604,
|
241 |
+
"logits/rejected": -1.4338067770004272,
|
242 |
+
"logps/chosen": -7.932246208190918,
|
243 |
+
"logps/rejected": -8.00547981262207,
|
244 |
+
"loss": 1.7858,
|
245 |
+
"rewards/accuracies": 0.45625001192092896,
|
246 |
+
"rewards/chosen": -7.932246208190918,
|
247 |
+
"rewards/margins": 0.07323212176561356,
|
248 |
+
"rewards/rejected": -8.00547981262207,
|
249 |
+
"step": 80
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.17796388380005235,
|
253 |
+
"grad_norm": 1.2997280215141844,
|
254 |
+
"learning_rate": 4.908790517010636e-07,
|
255 |
+
"logits/chosen": -1.435379981994629,
|
256 |
+
"logits/rejected": -1.4292837381362915,
|
257 |
+
"logps/chosen": -8.106579780578613,
|
258 |
+
"logps/rejected": -8.394915580749512,
|
259 |
+
"loss": 1.7975,
|
260 |
+
"rewards/accuracies": 0.5,
|
261 |
+
"rewards/chosen": -8.106579780578613,
|
262 |
+
"rewards/margins": 0.2883368134498596,
|
263 |
+
"rewards/rejected": -8.394915580749512,
|
264 |
+
"step": 85
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.1884323475529966,
|
268 |
+
"grad_norm": 1.4395629403420762,
|
269 |
+
"learning_rate": 4.882681251368548e-07,
|
270 |
+
"logits/chosen": -1.405975341796875,
|
271 |
+
"logits/rejected": -1.4189186096191406,
|
272 |
+
"logps/chosen": -8.203514099121094,
|
273 |
+
"logps/rejected": -8.477225303649902,
|
274 |
+
"loss": 1.7939,
|
275 |
+
"rewards/accuracies": 0.5562499761581421,
|
276 |
+
"rewards/chosen": -8.203514099121094,
|
277 |
+
"rewards/margins": 0.27371111512184143,
|
278 |
+
"rewards/rejected": -8.477225303649902,
|
279 |
+
"step": 90
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.19890081130594087,
|
283 |
+
"grad_norm": 1.4670380498675017,
|
284 |
+
"learning_rate": 4.853377929214243e-07,
|
285 |
+
"logits/chosen": -1.4155464172363281,
|
286 |
+
"logits/rejected": -1.408503532409668,
|
287 |
+
"logps/chosen": -8.385589599609375,
|
288 |
+
"logps/rejected": -8.298436164855957,
|
289 |
+
"loss": 1.7993,
|
290 |
+
"rewards/accuracies": 0.4375,
|
291 |
+
"rewards/chosen": -8.385589599609375,
|
292 |
+
"rewards/margins": -0.08715416491031647,
|
293 |
+
"rewards/rejected": -8.298436164855957,
|
294 |
+
"step": 95
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.2093692750588851,
|
298 |
+
"grad_norm": 1.8173814697081554,
|
299 |
+
"learning_rate": 4.820919832540181e-07,
|
300 |
+
"logits/chosen": -1.4453513622283936,
|
301 |
+
"logits/rejected": -1.4449245929718018,
|
302 |
+
"logps/chosen": -8.229129791259766,
|
303 |
+
"logps/rejected": -8.375448226928711,
|
304 |
+
"loss": 1.7935,
|
305 |
+
"rewards/accuracies": 0.512499988079071,
|
306 |
+
"rewards/chosen": -8.229129791259766,
|
307 |
+
"rewards/margins": 0.1463182270526886,
|
308 |
+
"rewards/rejected": -8.375448226928711,
|
309 |
+
"step": 100
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.21983773881182936,
|
313 |
+
"grad_norm": 1.5123285049323918,
|
314 |
+
"learning_rate": 4.785350472409791e-07,
|
315 |
+
"logits/chosen": -1.417307734489441,
|
316 |
+
"logits/rejected": -1.4141901731491089,
|
317 |
+
"logps/chosen": -7.822029113769531,
|
318 |
+
"logps/rejected": -8.184598922729492,
|
319 |
+
"loss": 1.7821,
|
320 |
+
"rewards/accuracies": 0.5874999761581421,
|
321 |
+
"rewards/chosen": -7.822029113769531,
|
322 |
+
"rewards/margins": 0.3625703752040863,
|
323 |
+
"rewards/rejected": -8.184598922729492,
|
324 |
+
"step": 105
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.23030620256477363,
|
328 |
+
"grad_norm": 1.6377413056182937,
|
329 |
+
"learning_rate": 4.7467175306295647e-07,
|
330 |
+
"logits/chosen": -1.4389078617095947,
|
331 |
+
"logits/rejected": -1.4492288827896118,
|
332 |
+
"logps/chosen": -8.023492813110352,
|
333 |
+
"logps/rejected": -8.443803787231445,
|
334 |
+
"loss": 1.7872,
|
335 |
+
"rewards/accuracies": 0.612500011920929,
|
336 |
+
"rewards/chosen": -8.023492813110352,
|
337 |
+
"rewards/margins": 0.4203101694583893,
|
338 |
+
"rewards/rejected": -8.443803787231445,
|
339 |
+
"step": 110
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.24077466631771788,
|
343 |
+
"grad_norm": 98.6962749407612,
|
344 |
+
"learning_rate": 4.70507279583015e-07,
|
345 |
+
"logits/chosen": -1.370867133140564,
|
346 |
+
"logits/rejected": -1.3796217441558838,
|
347 |
+
"logps/chosen": -7.94110107421875,
|
348 |
+
"logps/rejected": -8.37704086303711,
|
349 |
+
"loss": 1.7801,
|
350 |
+
"rewards/accuracies": 0.5874999761581421,
|
351 |
+
"rewards/chosen": -7.94110107421875,
|
352 |
+
"rewards/margins": 0.4359405040740967,
|
353 |
+
"rewards/rejected": -8.37704086303711,
|
354 |
+
"step": 115
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.2512431300706621,
|
358 |
+
"grad_norm": 1.8443926963030073,
|
359 |
+
"learning_rate": 4.6604720940421207e-07,
|
360 |
+
"logits/chosen": -1.3745276927947998,
|
361 |
+
"logits/rejected": -1.3777697086334229,
|
362 |
+
"logps/chosen": -8.194904327392578,
|
363 |
+
"logps/rejected": -8.444576263427734,
|
364 |
+
"loss": 1.7749,
|
365 |
+
"rewards/accuracies": 0.518750011920929,
|
366 |
+
"rewards/chosen": -8.194904327392578,
|
367 |
+
"rewards/margins": 0.24967141449451447,
|
368 |
+
"rewards/rejected": -8.444576263427734,
|
369 |
+
"step": 120
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.26171159382360637,
|
373 |
+
"grad_norm": 2.195114945918261,
|
374 |
+
"learning_rate": 4.612975213859487e-07,
|
375 |
+
"logits/chosen": -1.4081896543502808,
|
376 |
+
"logits/rejected": -1.4049599170684814,
|
377 |
+
"logps/chosen": -8.501805305480957,
|
378 |
+
"logps/rejected": -8.36412525177002,
|
379 |
+
"loss": 1.7924,
|
380 |
+
"rewards/accuracies": 0.4625000059604645,
|
381 |
+
"rewards/chosen": -8.501805305480957,
|
382 |
+
"rewards/margins": -0.13768072426319122,
|
383 |
+
"rewards/rejected": -8.36412525177002,
|
384 |
+
"step": 125
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.2721800575765506,
|
388 |
+
"grad_norm": 2.0830951299288785,
|
389 |
+
"learning_rate": 4.5626458262912735e-07,
|
390 |
+
"logits/chosen": -1.3827464580535889,
|
391 |
+
"logits/rejected": -1.396815299987793,
|
392 |
+
"logps/chosen": -8.410286903381348,
|
393 |
+
"logps/rejected": -8.63615608215332,
|
394 |
+
"loss": 1.7843,
|
395 |
+
"rewards/accuracies": 0.5249999761581421,
|
396 |
+
"rewards/chosen": -8.410286903381348,
|
397 |
+
"rewards/margins": 0.225869819521904,
|
398 |
+
"rewards/rejected": -8.63615608215332,
|
399 |
+
"step": 130
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.2826485213294949,
|
403 |
+
"grad_norm": 2.8119817250060923,
|
404 |
+
"learning_rate": 4.5095513994085974e-07,
|
405 |
+
"logits/chosen": -1.4122145175933838,
|
406 |
+
"logits/rejected": -1.4246305227279663,
|
407 |
+
"logps/chosen": -8.588987350463867,
|
408 |
+
"logps/rejected": -9.209198951721191,
|
409 |
+
"loss": 1.7873,
|
410 |
+
"rewards/accuracies": 0.5687500238418579,
|
411 |
+
"rewards/chosen": -8.588987350463867,
|
412 |
+
"rewards/margins": 0.6202121376991272,
|
413 |
+
"rewards/rejected": -9.209198951721191,
|
414 |
+
"step": 135
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.29311698508243916,
|
418 |
+
"grad_norm": 2.927322308508806,
|
419 |
+
"learning_rate": 4.453763107901675e-07,
|
420 |
+
"logits/chosen": -1.435681700706482,
|
421 |
+
"logits/rejected": -1.439152479171753,
|
422 |
+
"logps/chosen": -8.261212348937988,
|
423 |
+
"logps/rejected": -8.506053924560547,
|
424 |
+
"loss": 1.7771,
|
425 |
+
"rewards/accuracies": 0.5562499761581421,
|
426 |
+
"rewards/chosen": -8.261212348937988,
|
427 |
+
"rewards/margins": 0.2448415756225586,
|
428 |
+
"rewards/rejected": -8.506053924560547,
|
429 |
+
"step": 140
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.3035854488353834,
|
433 |
+
"grad_norm": 1.7606419766373003,
|
434 |
+
"learning_rate": 4.395355737667985e-07,
|
435 |
+
"logits/chosen": -1.4473952054977417,
|
436 |
+
"logits/rejected": -1.4762256145477295,
|
437 |
+
"logps/chosen": -8.1802396774292,
|
438 |
+
"logps/rejected": -8.576211929321289,
|
439 |
+
"loss": 1.7748,
|
440 |
+
"rewards/accuracies": 0.606249988079071,
|
441 |
+
"rewards/chosen": -8.1802396774292,
|
442 |
+
"rewards/margins": 0.3959727883338928,
|
443 |
+
"rewards/rejected": -8.576211929321289,
|
444 |
+
"step": 145
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.31405391258832765,
|
448 |
+
"grad_norm": 2.502338791234934,
|
449 |
+
"learning_rate": 4.3344075855595097e-07,
|
450 |
+
"logits/chosen": -1.4698665142059326,
|
451 |
+
"logits/rejected": -1.475287914276123,
|
452 |
+
"logps/chosen": -8.098420143127441,
|
453 |
+
"logps/rejected": -8.450376510620117,
|
454 |
+
"loss": 1.7739,
|
455 |
+
"rewards/accuracies": 0.518750011920929,
|
456 |
+
"rewards/chosen": -8.098420143127441,
|
457 |
+
"rewards/margins": 0.3519565463066101,
|
458 |
+
"rewards/rejected": -8.450376510620117,
|
459 |
+
"step": 150
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.3245223763412719,
|
463 |
+
"grad_norm": 2.2537748410992924,
|
464 |
+
"learning_rate": 4.271000354423425e-07,
|
465 |
+
"logits/chosen": -1.459938645362854,
|
466 |
+
"logits/rejected": -1.4374125003814697,
|
467 |
+
"logps/chosen": -8.157195091247559,
|
468 |
+
"logps/rejected": -8.490175247192383,
|
469 |
+
"loss": 1.7767,
|
470 |
+
"rewards/accuracies": 0.550000011920929,
|
471 |
+
"rewards/chosen": -8.157195091247559,
|
472 |
+
"rewards/margins": 0.3329797685146332,
|
473 |
+
"rewards/rejected": -8.490175247192383,
|
474 |
+
"step": 155
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.33499084009421615,
|
478 |
+
"grad_norm": 2.9160012212300086,
|
479 |
+
"learning_rate": 4.2052190435769554e-07,
|
480 |
+
"logits/chosen": -1.447819471359253,
|
481 |
+
"logits/rejected": -1.4601446390151978,
|
482 |
+
"logps/chosen": -8.642538070678711,
|
483 |
+
"logps/rejected": -8.85395336151123,
|
484 |
+
"loss": 1.7908,
|
485 |
+
"rewards/accuracies": 0.5625,
|
486 |
+
"rewards/chosen": -8.642538070678711,
|
487 |
+
"rewards/margins": 0.2114148586988449,
|
488 |
+
"rewards/rejected": -8.85395336151123,
|
489 |
+
"step": 160
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.34545930384716045,
|
493 |
+
"grad_norm": 2.332693331124937,
|
494 |
+
"learning_rate": 4.137151834863213e-07,
|
495 |
+
"logits/chosen": -1.4943044185638428,
|
496 |
+
"logits/rejected": -1.4839502573013306,
|
497 |
+
"logps/chosen": -8.424747467041016,
|
498 |
+
"logps/rejected": -8.770976066589355,
|
499 |
+
"loss": 1.7765,
|
500 |
+
"rewards/accuracies": 0.5249999761581421,
|
501 |
+
"rewards/chosen": -8.424747467041016,
|
502 |
+
"rewards/margins": 0.3462288975715637,
|
503 |
+
"rewards/rejected": -8.770976066589355,
|
504 |
+
"step": 165
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.3559277676001047,
|
508 |
+
"grad_norm": 2.4152194824308517,
|
509 |
+
"learning_rate": 4.0668899744407567e-07,
|
510 |
+
"logits/chosen": -1.4917938709259033,
|
511 |
+
"logits/rejected": -1.4810343980789185,
|
512 |
+
"logps/chosen": -8.424253463745117,
|
513 |
+
"logps/rejected": -8.7727632522583,
|
514 |
+
"loss": 1.7856,
|
515 |
+
"rewards/accuracies": 0.5687500238418579,
|
516 |
+
"rewards/chosen": -8.424253463745117,
|
517 |
+
"rewards/margins": 0.34850937128067017,
|
518 |
+
"rewards/rejected": -8.7727632522583,
|
519 |
+
"step": 170
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.36639623135304894,
|
523 |
+
"grad_norm": 2.653215706659519,
|
524 |
+
"learning_rate": 3.994527650465352e-07,
|
525 |
+
"logits/chosen": -1.5167206525802612,
|
526 |
+
"logits/rejected": -1.5095903873443604,
|
527 |
+
"logps/chosen": -8.30429458618164,
|
528 |
+
"logps/rejected": -8.76606559753418,
|
529 |
+
"loss": 1.7754,
|
530 |
+
"rewards/accuracies": 0.5625,
|
531 |
+
"rewards/chosen": -8.30429458618164,
|
532 |
+
"rewards/margins": 0.46177130937576294,
|
533 |
+
"rewards/rejected": -8.76606559753418,
|
534 |
+
"step": 175
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.3768646951059932,
|
538 |
+
"grad_norm": 3.002251381640332,
|
539 |
+
"learning_rate": 3.920161866827889e-07,
|
540 |
+
"logits/chosen": -1.5167474746704102,
|
541 |
+
"logits/rejected": -1.524743914604187,
|
542 |
+
"logps/chosen": -8.360708236694336,
|
543 |
+
"logps/rejected": -8.7758207321167,
|
544 |
+
"loss": 1.7796,
|
545 |
+
"rewards/accuracies": 0.5375000238418579,
|
546 |
+
"rewards/chosen": -8.360708236694336,
|
547 |
+
"rewards/margins": 0.41511401534080505,
|
548 |
+
"rewards/rejected": -8.7758207321167,
|
549 |
+
"step": 180
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.38733315885893743,
|
553 |
+
"grad_norm": 2.621525982629558,
|
554 |
+
"learning_rate": 3.8438923131177237e-07,
|
555 |
+
"logits/chosen": -1.5086079835891724,
|
556 |
+
"logits/rejected": -1.5038981437683105,
|
557 |
+
"logps/chosen": -8.088265419006348,
|
558 |
+
"logps/rejected": -8.633108139038086,
|
559 |
+
"loss": 1.7613,
|
560 |
+
"rewards/accuracies": 0.574999988079071,
|
561 |
+
"rewards/chosen": -8.088265419006348,
|
562 |
+
"rewards/margins": 0.5448437929153442,
|
563 |
+
"rewards/rejected": -8.633108139038086,
|
564 |
+
"step": 185
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.39780162261188173,
|
568 |
+
"grad_norm": 2.7052866783401983,
|
569 |
+
"learning_rate": 3.765821230985757e-07,
|
570 |
+
"logits/chosen": -1.530807375907898,
|
571 |
+
"logits/rejected": -1.5209619998931885,
|
572 |
+
"logps/chosen": -8.019875526428223,
|
573 |
+
"logps/rejected": -8.384284973144531,
|
574 |
+
"loss": 1.7721,
|
575 |
+
"rewards/accuracies": 0.4937500059604645,
|
576 |
+
"rewards/chosen": -8.019875526428223,
|
577 |
+
"rewards/margins": 0.3644091784954071,
|
578 |
+
"rewards/rejected": -8.384284973144531,
|
579 |
+
"step": 190
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.408270086364826,
|
583 |
+
"grad_norm": 3.1926636795520884,
|
584 |
+
"learning_rate": 3.6860532770864005e-07,
|
585 |
+
"logits/chosen": -1.4885269403457642,
|
586 |
+
"logits/rejected": -1.483224630355835,
|
587 |
+
"logps/chosen": -8.213752746582031,
|
588 |
+
"logps/rejected": -8.523615837097168,
|
589 |
+
"loss": 1.7799,
|
590 |
+
"rewards/accuracies": 0.5375000238418579,
|
591 |
+
"rewards/chosen": -8.213752746582031,
|
592 |
+
"rewards/margins": 0.3098633289337158,
|
593 |
+
"rewards/rejected": -8.523615837097168,
|
594 |
+
"step": 195
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.4187385501177702,
|
598 |
+
"grad_norm": 2.929908108293166,
|
599 |
+
"learning_rate": 3.604695382782159e-07,
|
600 |
+
"logits/chosen": -1.5416061878204346,
|
601 |
+
"logits/rejected": -1.5284559726715088,
|
602 |
+
"logps/chosen": -8.0154447555542,
|
603 |
+
"logps/rejected": -8.428897857666016,
|
604 |
+
"loss": 1.7863,
|
605 |
+
"rewards/accuracies": 0.5062500238418579,
|
606 |
+
"rewards/chosen": -8.0154447555542,
|
607 |
+
"rewards/margins": 0.4134535789489746,
|
608 |
+
"rewards/rejected": -8.428897857666016,
|
609 |
+
"step": 200
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.42920701387071447,
|
613 |
+
"grad_norm": 3.9208987619596365,
|
614 |
+
"learning_rate": 3.5218566107988867e-07,
|
615 |
+
"logits/chosen": -1.5039266347885132,
|
616 |
+
"logits/rejected": -1.495948076248169,
|
617 |
+
"logps/chosen": -8.161928176879883,
|
618 |
+
"logps/rejected": -8.836877822875977,
|
619 |
+
"loss": 1.7649,
|
620 |
+
"rewards/accuracies": 0.5562499761581421,
|
621 |
+
"rewards/chosen": -8.161928176879883,
|
622 |
+
"rewards/margins": 0.6749483346939087,
|
623 |
+
"rewards/rejected": -8.836877822875977,
|
624 |
+
"step": 205
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.4396754776236587,
|
628 |
+
"grad_norm": 9.132837726981721,
|
629 |
+
"learning_rate": 3.4376480090239047e-07,
|
630 |
+
"logits/chosen": -1.4978554248809814,
|
631 |
+
"logits/rejected": -1.5001240968704224,
|
632 |
+
"logps/chosen": -8.470359802246094,
|
633 |
+
"logps/rejected": -8.813634872436523,
|
634 |
+
"loss": 1.7745,
|
635 |
+
"rewards/accuracies": 0.550000011920929,
|
636 |
+
"rewards/chosen": -8.470359802246094,
|
637 |
+
"rewards/margins": 0.34327542781829834,
|
638 |
+
"rewards/rejected": -8.813634872436523,
|
639 |
+
"step": 210
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.45014394137660296,
|
643 |
+
"grad_norm": 2.6786514985319276,
|
644 |
+
"learning_rate": 3.3521824616429284e-07,
|
645 |
+
"logits/chosen": -1.5123167037963867,
|
646 |
+
"logits/rejected": -1.5113458633422852,
|
647 |
+
"logps/chosen": -7.9097490310668945,
|
648 |
+
"logps/rejected": -8.861387252807617,
|
649 |
+
"loss": 1.761,
|
650 |
+
"rewards/accuracies": 0.637499988079071,
|
651 |
+
"rewards/chosen": -7.9097490310668945,
|
652 |
+
"rewards/margins": 0.9516386985778809,
|
653 |
+
"rewards/rejected": -8.861387252807617,
|
654 |
+
"step": 215
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.46061240512954726,
|
658 |
+
"grad_norm": 3.81508961382941,
|
659 |
+
"learning_rate": 3.265574537815398e-07,
|
660 |
+
"logits/chosen": -1.4957890510559082,
|
661 |
+
"logits/rejected": -1.503143072128296,
|
662 |
+
"logps/chosen": -7.837327480316162,
|
663 |
+
"logps/rejected": -8.386968612670898,
|
664 |
+
"loss": 1.7778,
|
665 |
+
"rewards/accuracies": 0.59375,
|
666 |
+
"rewards/chosen": -7.837327480316162,
|
667 |
+
"rewards/margins": 0.549641489982605,
|
668 |
+
"rewards/rejected": -8.386968612670898,
|
669 |
+
"step": 220
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.4710808688824915,
|
673 |
+
"grad_norm": 4.889361688771567,
|
674 |
+
"learning_rate": 3.1779403380910425e-07,
|
675 |
+
"logits/chosen": -1.530035376548767,
|
676 |
+
"logits/rejected": -1.5252281427383423,
|
677 |
+
"logps/chosen": -7.843958377838135,
|
678 |
+
"logps/rejected": -8.631728172302246,
|
679 |
+
"loss": 1.7605,
|
680 |
+
"rewards/accuracies": 0.625,
|
681 |
+
"rewards/chosen": -7.843958377838135,
|
682 |
+
"rewards/margins": 0.787769079208374,
|
683 |
+
"rewards/rejected": -8.631728172302246,
|
684 |
+
"step": 225
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.48154933263543576,
|
688 |
+
"grad_norm": 4.621367765160452,
|
689 |
+
"learning_rate": 3.0893973387735683e-07,
|
690 |
+
"logits/chosen": -1.5648292303085327,
|
691 |
+
"logits/rejected": -1.5472863912582397,
|
692 |
+
"logps/chosen": -8.125567436218262,
|
693 |
+
"logps/rejected": -9.158833503723145,
|
694 |
+
"loss": 1.7587,
|
695 |
+
"rewards/accuracies": 0.581250011920929,
|
696 |
+
"rewards/chosen": -8.125567436218262,
|
697 |
+
"rewards/margins": 1.033265471458435,
|
698 |
+
"rewards/rejected": -9.158833503723145,
|
699 |
+
"step": 230
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.49201779638838,
|
703 |
+
"grad_norm": 4.510315294900107,
|
704 |
+
"learning_rate": 3.000064234440111e-07,
|
705 |
+
"logits/chosen": -1.6225063800811768,
|
706 |
+
"logits/rejected": -1.597538948059082,
|
707 |
+
"logps/chosen": -8.116875648498535,
|
708 |
+
"logps/rejected": -9.23936939239502,
|
709 |
+
"loss": 1.7614,
|
710 |
+
"rewards/accuracies": 0.6312500238418579,
|
711 |
+
"rewards/chosen": -8.116875648498535,
|
712 |
+
"rewards/margins": 1.1224939823150635,
|
713 |
+
"rewards/rejected": -9.23936939239502,
|
714 |
+
"step": 235
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.5024862601413242,
|
718 |
+
"grad_norm": 7.892385115240221,
|
719 |
+
"learning_rate": 2.910060778827554e-07,
|
720 |
+
"logits/chosen": -1.5823067426681519,
|
721 |
+
"logits/rejected": -1.574851155281067,
|
722 |
+
"logps/chosen": -8.326906204223633,
|
723 |
+
"logps/rejected": -9.232850074768066,
|
724 |
+
"loss": 1.7551,
|
725 |
+
"rewards/accuracies": 0.6187499761581421,
|
726 |
+
"rewards/chosen": -8.326906204223633,
|
727 |
+
"rewards/margins": 0.9059435129165649,
|
728 |
+
"rewards/rejected": -9.232850074768066,
|
729 |
+
"step": 240
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.5129547238942685,
|
733 |
+
"grad_norm": 7.898664476513504,
|
734 |
+
"learning_rate": 2.8195076242990116e-07,
|
735 |
+
"logits/chosen": -1.5616357326507568,
|
736 |
+
"logits/rejected": -1.5433732271194458,
|
737 |
+
"logps/chosen": -9.017087936401367,
|
738 |
+
"logps/rejected": -9.785380363464355,
|
739 |
+
"loss": 1.7399,
|
740 |
+
"rewards/accuracies": 0.543749988079071,
|
741 |
+
"rewards/chosen": -9.017087936401367,
|
742 |
+
"rewards/margins": 0.7682939767837524,
|
743 |
+
"rewards/rejected": -9.785380363464355,
|
744 |
+
"step": 245
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.5234231876472127,
|
748 |
+
"grad_norm": 7.533973692196864,
|
749 |
+
"learning_rate": 2.7285261601056697e-07,
|
750 |
+
"logits/chosen": -1.5792642831802368,
|
751 |
+
"logits/rejected": -1.5693460702896118,
|
752 |
+
"logps/chosen": -7.595057010650635,
|
753 |
+
"logps/rejected": -8.57075309753418,
|
754 |
+
"loss": 1.7492,
|
755 |
+
"rewards/accuracies": 0.625,
|
756 |
+
"rewards/chosen": -7.595057010650635,
|
757 |
+
"rewards/margins": 0.9756966829299927,
|
758 |
+
"rewards/rejected": -8.57075309753418,
|
759 |
+
"step": 250
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.533891651400157,
|
763 |
+
"grad_norm": 10.624973349509592,
|
764 |
+
"learning_rate": 2.6372383496608186e-07,
|
765 |
+
"logits/chosen": -1.5440006256103516,
|
766 |
+
"logits/rejected": -1.5143473148345947,
|
767 |
+
"logps/chosen": -8.250520706176758,
|
768 |
+
"logps/rejected": -9.301929473876953,
|
769 |
+
"loss": 1.7613,
|
770 |
+
"rewards/accuracies": 0.6000000238418579,
|
771 |
+
"rewards/chosen": -8.250520706176758,
|
772 |
+
"rewards/margins": 1.0514087677001953,
|
773 |
+
"rewards/rejected": -9.301929473876953,
|
774 |
+
"step": 255
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.5443601151531012,
|
778 |
+
"grad_norm": 6.827054099571504,
|
779 |
+
"learning_rate": 2.5457665670441937e-07,
|
780 |
+
"logits/chosen": -1.4768860340118408,
|
781 |
+
"logits/rejected": -1.4396953582763672,
|
782 |
+
"logps/chosen": -7.612262725830078,
|
783 |
+
"logps/rejected": -9.350198745727539,
|
784 |
+
"loss": 1.7355,
|
785 |
+
"rewards/accuracies": 0.6187499761581421,
|
786 |
+
"rewards/chosen": -7.612262725830078,
|
787 |
+
"rewards/margins": 1.7379356622695923,
|
788 |
+
"rewards/rejected": -9.350198745727539,
|
789 |
+
"step": 260
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.5548285789060455,
|
793 |
+
"grad_norm": 8.933359425352409,
|
794 |
+
"learning_rate": 2.454233432955807e-07,
|
795 |
+
"logits/chosen": -1.4639561176300049,
|
796 |
+
"logits/rejected": -1.453298807144165,
|
797 |
+
"logps/chosen": -8.868209838867188,
|
798 |
+
"logps/rejected": -9.566887855529785,
|
799 |
+
"loss": 1.7463,
|
800 |
+
"rewards/accuracies": 0.5874999761581421,
|
801 |
+
"rewards/chosen": -8.868209838867188,
|
802 |
+
"rewards/margins": 0.698679506778717,
|
803 |
+
"rewards/rejected": -9.566887855529785,
|
804 |
+
"step": 265
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.5652970426589898,
|
808 |
+
"grad_norm": 7.0066263897371535,
|
809 |
+
"learning_rate": 2.3627616503391812e-07,
|
810 |
+
"logits/chosen": -1.4920735359191895,
|
811 |
+
"logits/rejected": -1.4540319442749023,
|
812 |
+
"logps/chosen": -8.762821197509766,
|
813 |
+
"logps/rejected": -9.565961837768555,
|
814 |
+
"loss": 1.7653,
|
815 |
+
"rewards/accuracies": 0.5874999761581421,
|
816 |
+
"rewards/chosen": -8.762821197509766,
|
817 |
+
"rewards/margins": 0.8031412363052368,
|
818 |
+
"rewards/rejected": -9.565961837768555,
|
819 |
+
"step": 270
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.575765506411934,
|
823 |
+
"grad_norm": 6.881020189800575,
|
824 |
+
"learning_rate": 2.2714738398943308e-07,
|
825 |
+
"logits/chosen": -1.5479252338409424,
|
826 |
+
"logits/rejected": -1.5279855728149414,
|
827 |
+
"logps/chosen": -7.815232753753662,
|
828 |
+
"logps/rejected": -9.187639236450195,
|
829 |
+
"loss": 1.7328,
|
830 |
+
"rewards/accuracies": 0.606249988079071,
|
831 |
+
"rewards/chosen": -7.815232753753662,
|
832 |
+
"rewards/margins": 1.3724067211151123,
|
833 |
+
"rewards/rejected": -9.187639236450195,
|
834 |
+
"step": 275
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.5862339701648783,
|
838 |
+
"grad_norm": 7.517058454845967,
|
839 |
+
"learning_rate": 2.1804923757009882e-07,
|
840 |
+
"logits/chosen": -1.5499231815338135,
|
841 |
+
"logits/rejected": -1.5244100093841553,
|
842 |
+
"logps/chosen": -8.39962100982666,
|
843 |
+
"logps/rejected": -10.24171257019043,
|
844 |
+
"loss": 1.7267,
|
845 |
+
"rewards/accuracies": 0.637499988079071,
|
846 |
+
"rewards/chosen": -8.39962100982666,
|
847 |
+
"rewards/margins": 1.842092514038086,
|
848 |
+
"rewards/rejected": -10.24171257019043,
|
849 |
+
"step": 280
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.5967024339178225,
|
853 |
+
"grad_norm": 8.013738309459756,
|
854 |
+
"learning_rate": 2.089939221172446e-07,
|
855 |
+
"logits/chosen": -1.5420681238174438,
|
856 |
+
"logits/rejected": -1.5153690576553345,
|
857 |
+
"logps/chosen": -8.524008750915527,
|
858 |
+
"logps/rejected": -9.523444175720215,
|
859 |
+
"loss": 1.7487,
|
860 |
+
"rewards/accuracies": 0.550000011920929,
|
861 |
+
"rewards/chosen": -8.524008750915527,
|
862 |
+
"rewards/margins": 0.999435305595398,
|
863 |
+
"rewards/rejected": -9.523444175720215,
|
864 |
+
"step": 285
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.6071708976707668,
|
868 |
+
"grad_norm": 6.486821674482447,
|
869 |
+
"learning_rate": 1.9999357655598891e-07,
|
870 |
+
"logits/chosen": -1.6035845279693604,
|
871 |
+
"logits/rejected": -1.5711686611175537,
|
872 |
+
"logps/chosen": -8.237485885620117,
|
873 |
+
"logps/rejected": -9.552020072937012,
|
874 |
+
"loss": 1.735,
|
875 |
+
"rewards/accuracies": 0.6499999761581421,
|
876 |
+
"rewards/chosen": -8.237485885620117,
|
877 |
+
"rewards/margins": 1.3145345449447632,
|
878 |
+
"rewards/rejected": -9.552020072937012,
|
879 |
+
"step": 290
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.6176393614237111,
|
883 |
+
"grad_norm": 8.83521561541266,
|
884 |
+
"learning_rate": 1.9106026612264315e-07,
|
885 |
+
"logits/chosen": -1.6141548156738281,
|
886 |
+
"logits/rejected": -1.594178557395935,
|
887 |
+
"logps/chosen": -7.968149662017822,
|
888 |
+
"logps/rejected": -8.619260787963867,
|
889 |
+
"loss": 1.7566,
|
890 |
+
"rewards/accuracies": 0.550000011920929,
|
891 |
+
"rewards/chosen": -7.968149662017822,
|
892 |
+
"rewards/margins": 0.6511108875274658,
|
893 |
+
"rewards/rejected": -8.619260787963867,
|
894 |
+
"step": 295
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.6281078251766553,
|
898 |
+
"grad_norm": 6.975353142841212,
|
899 |
+
"learning_rate": 1.8220596619089573e-07,
|
900 |
+
"logits/chosen": -1.5654271841049194,
|
901 |
+
"logits/rejected": -1.546992301940918,
|
902 |
+
"logps/chosen": -8.48424243927002,
|
903 |
+
"logps/rejected": -9.418001174926758,
|
904 |
+
"loss": 1.7583,
|
905 |
+
"rewards/accuracies": 0.5687500238418579,
|
906 |
+
"rewards/chosen": -8.48424243927002,
|
907 |
+
"rewards/margins": 0.9337590336799622,
|
908 |
+
"rewards/rejected": -9.418001174926758,
|
909 |
+
"step": 300
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.6385762889295996,
|
913 |
+
"grad_norm": 5.4690365037746815,
|
914 |
+
"learning_rate": 1.7344254621846017e-07,
|
915 |
+
"logits/chosen": -1.5813648700714111,
|
916 |
+
"logits/rejected": -1.5758841037750244,
|
917 |
+
"logps/chosen": -8.727537155151367,
|
918 |
+
"logps/rejected": -9.66854190826416,
|
919 |
+
"loss": 1.732,
|
920 |
+
"rewards/accuracies": 0.550000011920929,
|
921 |
+
"rewards/chosen": -8.727537155151367,
|
922 |
+
"rewards/margins": 0.9410043954849243,
|
923 |
+
"rewards/rejected": -9.66854190826416,
|
924 |
+
"step": 305
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.6490447526825438,
|
928 |
+
"grad_norm": 5.361180962867588,
|
929 |
+
"learning_rate": 1.647817538357072e-07,
|
930 |
+
"logits/chosen": -1.6157958507537842,
|
931 |
+
"logits/rejected": -1.6046196222305298,
|
932 |
+
"logps/chosen": -8.187897682189941,
|
933 |
+
"logps/rejected": -8.897558212280273,
|
934 |
+
"loss": 1.7699,
|
935 |
+
"rewards/accuracies": 0.5625,
|
936 |
+
"rewards/chosen": -8.187897682189941,
|
937 |
+
"rewards/margins": 0.7096610069274902,
|
938 |
+
"rewards/rejected": -8.897558212280273,
|
939 |
+
"step": 310
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.6595132164354881,
|
943 |
+
"grad_norm": 5.449920555042311,
|
944 |
+
"learning_rate": 1.562351990976095e-07,
|
945 |
+
"logits/chosen": -1.6411434412002563,
|
946 |
+
"logits/rejected": -1.62042236328125,
|
947 |
+
"logps/chosen": -7.746342658996582,
|
948 |
+
"logps/rejected": -8.609481811523438,
|
949 |
+
"loss": 1.7396,
|
950 |
+
"rewards/accuracies": 0.5562499761581421,
|
951 |
+
"rewards/chosen": -7.746342658996582,
|
952 |
+
"rewards/margins": 0.8631397485733032,
|
953 |
+
"rewards/rejected": -8.609481811523438,
|
954 |
+
"step": 315
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.6699816801884323,
|
958 |
+
"grad_norm": 6.360997845008894,
|
959 |
+
"learning_rate": 1.478143389201113e-07,
|
960 |
+
"logits/chosen": -1.6342664957046509,
|
961 |
+
"logits/rejected": -1.598560094833374,
|
962 |
+
"logps/chosen": -8.291830062866211,
|
963 |
+
"logps/rejected": -9.186594009399414,
|
964 |
+
"loss": 1.7428,
|
965 |
+
"rewards/accuracies": 0.5562499761581421,
|
966 |
+
"rewards/chosen": -8.291830062866211,
|
967 |
+
"rewards/margins": 0.8947637677192688,
|
968 |
+
"rewards/rejected": -9.186594009399414,
|
969 |
+
"step": 320
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.6804501439413766,
|
973 |
+
"grad_norm": 7.837240923658896,
|
974 |
+
"learning_rate": 1.3953046172178413e-07,
|
975 |
+
"logits/chosen": -1.6066200733184814,
|
976 |
+
"logits/rejected": -1.5687167644500732,
|
977 |
+
"logps/chosen": -8.601926803588867,
|
978 |
+
"logps/rejected": -9.912989616394043,
|
979 |
+
"loss": 1.7306,
|
980 |
+
"rewards/accuracies": 0.5874999761581421,
|
981 |
+
"rewards/chosen": -8.601926803588867,
|
982 |
+
"rewards/margins": 1.3110629320144653,
|
983 |
+
"rewards/rejected": -9.912989616394043,
|
984 |
+
"step": 325
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.6909186076943209,
|
988 |
+
"grad_norm": 5.555679671882387,
|
989 |
+
"learning_rate": 1.3139467229135998e-07,
|
990 |
+
"logits/chosen": -1.6012904644012451,
|
991 |
+
"logits/rejected": -1.5771445035934448,
|
992 |
+
"logps/chosen": -8.177051544189453,
|
993 |
+
"logps/rejected": -8.873910903930664,
|
994 |
+
"loss": 1.7496,
|
995 |
+
"rewards/accuracies": 0.581250011920929,
|
996 |
+
"rewards/chosen": -8.177051544189453,
|
997 |
+
"rewards/margins": 0.6968590021133423,
|
998 |
+
"rewards/rejected": -8.873910903930664,
|
999 |
+
"step": 330
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.7013870714472651,
|
1003 |
+
"grad_norm": 5.848948219669636,
|
1004 |
+
"learning_rate": 1.2341787690142435e-07,
|
1005 |
+
"logits/chosen": -1.6410300731658936,
|
1006 |
+
"logits/rejected": -1.5906805992126465,
|
1007 |
+
"logps/chosen": -7.888881683349609,
|
1008 |
+
"logps/rejected": -8.846321105957031,
|
1009 |
+
"loss": 1.7444,
|
1010 |
+
"rewards/accuracies": 0.550000011920929,
|
1011 |
+
"rewards/chosen": -7.888881683349609,
|
1012 |
+
"rewards/margins": 0.9574400782585144,
|
1013 |
+
"rewards/rejected": -8.846321105957031,
|
1014 |
+
"step": 335
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.7118555352002094,
|
1018 |
+
"grad_norm": 5.607244300528084,
|
1019 |
+
"learning_rate": 1.1561076868822755e-07,
|
1020 |
+
"logits/chosen": -1.6162534952163696,
|
1021 |
+
"logits/rejected": -1.590820074081421,
|
1022 |
+
"logps/chosen": -8.39061450958252,
|
1023 |
+
"logps/rejected": -9.30118465423584,
|
1024 |
+
"loss": 1.7583,
|
1025 |
+
"rewards/accuracies": 0.6000000238418579,
|
1026 |
+
"rewards/chosen": -8.39061450958252,
|
1027 |
+
"rewards/margins": 0.9105701446533203,
|
1028 |
+
"rewards/rejected": -9.30118465423584,
|
1029 |
+
"step": 340
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.7223239989531536,
|
1033 |
+
"grad_norm": 7.279367786185165,
|
1034 |
+
"learning_rate": 1.0798381331721107e-07,
|
1035 |
+
"logits/chosen": -1.6430072784423828,
|
1036 |
+
"logits/rejected": -1.6136901378631592,
|
1037 |
+
"logps/chosen": -8.215340614318848,
|
1038 |
+
"logps/rejected": -9.647343635559082,
|
1039 |
+
"loss": 1.7453,
|
1040 |
+
"rewards/accuracies": 0.5687500238418579,
|
1041 |
+
"rewards/chosen": -8.215340614318848,
|
1042 |
+
"rewards/margins": 1.4320037364959717,
|
1043 |
+
"rewards/rejected": -9.647343635559082,
|
1044 |
+
"step": 345
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.7327924627060979,
|
1048 |
+
"grad_norm": 7.386464884448549,
|
1049 |
+
"learning_rate": 1.0054723495346482e-07,
|
1050 |
+
"logits/chosen": -1.5686066150665283,
|
1051 |
+
"logits/rejected": -1.5304858684539795,
|
1052 |
+
"logps/chosen": -8.146261215209961,
|
1053 |
+
"logps/rejected": -9.257192611694336,
|
1054 |
+
"loss": 1.7426,
|
1055 |
+
"rewards/accuracies": 0.5562499761581421,
|
1056 |
+
"rewards/chosen": -8.146261215209961,
|
1057 |
+
"rewards/margins": 1.1109315156936646,
|
1058 |
+
"rewards/rejected": -9.257192611694336,
|
1059 |
+
"step": 350
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.7432609264590422,
|
1063 |
+
"grad_norm": 5.785018086716381,
|
1064 |
+
"learning_rate": 9.331100255592436e-08,
|
1065 |
+
"logits/chosen": -1.6148964166641235,
|
1066 |
+
"logits/rejected": -1.5602537393569946,
|
1067 |
+
"logps/chosen": -8.22186279296875,
|
1068 |
+
"logps/rejected": -9.004861831665039,
|
1069 |
+
"loss": 1.7401,
|
1070 |
+
"rewards/accuracies": 0.543749988079071,
|
1071 |
+
"rewards/chosen": -8.22186279296875,
|
1072 |
+
"rewards/margins": 0.7829989194869995,
|
1073 |
+
"rewards/rejected": -9.004861831665039,
|
1074 |
+
"step": 355
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.7537293902119864,
|
1078 |
+
"grad_norm": 6.331566938080069,
|
1079 |
+
"learning_rate": 8.628481651367875e-08,
|
1080 |
+
"logits/chosen": -1.6229692697525024,
|
1081 |
+
"logits/rejected": -1.5903146266937256,
|
1082 |
+
"logps/chosen": -7.560595512390137,
|
1083 |
+
"logps/rejected": -8.47083568572998,
|
1084 |
+
"loss": 1.7385,
|
1085 |
+
"rewards/accuracies": 0.5562499761581421,
|
1086 |
+
"rewards/chosen": -7.560595512390137,
|
1087 |
+
"rewards/margins": 0.9102400541305542,
|
1088 |
+
"rewards/rejected": -8.47083568572998,
|
1089 |
+
"step": 360
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.7641978539649307,
|
1093 |
+
"grad_norm": 6.319560115409626,
|
1094 |
+
"learning_rate": 7.947809564230445e-08,
|
1095 |
+
"logits/chosen": -1.6155359745025635,
|
1096 |
+
"logits/rejected": -1.5554075241088867,
|
1097 |
+
"logps/chosen": -7.953149318695068,
|
1098 |
+
"logps/rejected": -8.690530776977539,
|
1099 |
+
"loss": 1.7605,
|
1100 |
+
"rewards/accuracies": 0.606249988079071,
|
1101 |
+
"rewards/chosen": -7.953149318695068,
|
1102 |
+
"rewards/margins": 0.7373809814453125,
|
1103 |
+
"rewards/rejected": -8.690530776977539,
|
1104 |
+
"step": 365
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.7746663177178749,
|
1108 |
+
"grad_norm": 6.673242442518388,
|
1109 |
+
"learning_rate": 7.289996455765748e-08,
|
1110 |
+
"logits/chosen": -1.6045255661010742,
|
1111 |
+
"logits/rejected": -1.5444786548614502,
|
1112 |
+
"logps/chosen": -8.404296875,
|
1113 |
+
"logps/rejected": -9.452798843383789,
|
1114 |
+
"loss": 1.7498,
|
1115 |
+
"rewards/accuracies": 0.612500011920929,
|
1116 |
+
"rewards/chosen": -8.404296875,
|
1117 |
+
"rewards/margins": 1.04850172996521,
|
1118 |
+
"rewards/rejected": -9.452798843383789,
|
1119 |
+
"step": 370
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.7851347814708192,
|
1123 |
+
"grad_norm": 7.020475966648844,
|
1124 |
+
"learning_rate": 6.655924144404906e-08,
|
1125 |
+
"logits/chosen": -1.5848079919815063,
|
1126 |
+
"logits/rejected": -1.5374637842178345,
|
1127 |
+
"logps/chosen": -8.454399108886719,
|
1128 |
+
"logps/rejected": -9.83703899383545,
|
1129 |
+
"loss": 1.739,
|
1130 |
+
"rewards/accuracies": 0.59375,
|
1131 |
+
"rewards/chosen": -8.454399108886719,
|
1132 |
+
"rewards/margins": 1.3826408386230469,
|
1133 |
+
"rewards/rejected": -9.83703899383545,
|
1134 |
+
"step": 375
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.7956032452237635,
|
1138 |
+
"grad_norm": 6.653238331291029,
|
1139 |
+
"learning_rate": 6.046442623320145e-08,
|
1140 |
+
"logits/chosen": -1.5949599742889404,
|
1141 |
+
"logits/rejected": -1.5306172370910645,
|
1142 |
+
"logps/chosen": -8.711164474487305,
|
1143 |
+
"logps/rejected": -9.62182331085205,
|
1144 |
+
"loss": 1.7155,
|
1145 |
+
"rewards/accuracies": 0.574999988079071,
|
1146 |
+
"rewards/chosen": -8.711164474487305,
|
1147 |
+
"rewards/margins": 0.910659670829773,
|
1148 |
+
"rewards/rejected": -9.62182331085205,
|
1149 |
+
"step": 380
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.8060717089767077,
|
1153 |
+
"grad_norm": 7.782341216017442,
|
1154 |
+
"learning_rate": 5.4623689209832484e-08,
|
1155 |
+
"logits/chosen": -1.577016830444336,
|
1156 |
+
"logits/rejected": -1.5303077697753906,
|
1157 |
+
"logps/chosen": -8.757134437561035,
|
1158 |
+
"logps/rejected": -9.896451950073242,
|
1159 |
+
"loss": 1.7371,
|
1160 |
+
"rewards/accuracies": 0.5874999761581421,
|
1161 |
+
"rewards/chosen": -8.757134437561035,
|
1162 |
+
"rewards/margins": 1.1393181085586548,
|
1163 |
+
"rewards/rejected": -9.896451950073242,
|
1164 |
+
"step": 385
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.816540172729652,
|
1168 |
+
"grad_norm": 6.684411144542067,
|
1169 |
+
"learning_rate": 4.904486005914027e-08,
|
1170 |
+
"logits/chosen": -1.5992292165756226,
|
1171 |
+
"logits/rejected": -1.5533421039581299,
|
1172 |
+
"logps/chosen": -8.044672012329102,
|
1173 |
+
"logps/rejected": -9.49129581451416,
|
1174 |
+
"loss": 1.7299,
|
1175 |
+
"rewards/accuracies": 0.625,
|
1176 |
+
"rewards/chosen": -8.044672012329102,
|
1177 |
+
"rewards/margins": 1.446624517440796,
|
1178 |
+
"rewards/rejected": -9.49129581451416,
|
1179 |
+
"step": 390
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.8270086364825961,
|
1183 |
+
"grad_norm": 8.354771172189295,
|
1184 |
+
"learning_rate": 4.373541737087263e-08,
|
1185 |
+
"logits/chosen": -1.5767982006072998,
|
1186 |
+
"logits/rejected": -1.5374451875686646,
|
1187 |
+
"logps/chosen": -7.573851108551025,
|
1188 |
+
"logps/rejected": -8.567195892333984,
|
1189 |
+
"loss": 1.7336,
|
1190 |
+
"rewards/accuracies": 0.581250011920929,
|
1191 |
+
"rewards/chosen": -7.573851108551025,
|
1192 |
+
"rewards/margins": 0.9933451414108276,
|
1193 |
+
"rewards/rejected": -8.567195892333984,
|
1194 |
+
"step": 395
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.8374771002355405,
|
1198 |
+
"grad_norm": 7.4009477251723865,
|
1199 |
+
"learning_rate": 3.8702478614051345e-08,
|
1200 |
+
"logits/chosen": -1.5977306365966797,
|
1201 |
+
"logits/rejected": -1.5405915975570679,
|
1202 |
+
"logps/chosen": -7.894219875335693,
|
1203 |
+
"logps/rejected": -8.81593132019043,
|
1204 |
+
"loss": 1.7454,
|
1205 |
+
"rewards/accuracies": 0.581250011920929,
|
1206 |
+
"rewards/chosen": -7.894219875335693,
|
1207 |
+
"rewards/margins": 0.9217125177383423,
|
1208 |
+
"rewards/rejected": -8.81593132019043,
|
1209 |
+
"step": 400
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.8479455639884846,
|
1213 |
+
"grad_norm": 6.210047238602565,
|
1214 |
+
"learning_rate": 3.3952790595787986e-08,
|
1215 |
+
"logits/chosen": -1.60799241065979,
|
1216 |
+
"logits/rejected": -1.6026899814605713,
|
1217 |
+
"logps/chosen": -8.381356239318848,
|
1218 |
+
"logps/rejected": -9.069351196289062,
|
1219 |
+
"loss": 1.742,
|
1220 |
+
"rewards/accuracies": 0.6000000238418579,
|
1221 |
+
"rewards/chosen": -8.381356239318848,
|
1222 |
+
"rewards/margins": 0.6879969835281372,
|
1223 |
+
"rewards/rejected": -9.069351196289062,
|
1224 |
+
"step": 405
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.8584140277414289,
|
1228 |
+
"grad_norm": 6.765719877755184,
|
1229 |
+
"learning_rate": 2.9492720416985e-08,
|
1230 |
+
"logits/chosen": -1.6209001541137695,
|
1231 |
+
"logits/rejected": -1.5718666315078735,
|
1232 |
+
"logps/chosen": -7.976959228515625,
|
1233 |
+
"logps/rejected": -8.827299118041992,
|
1234 |
+
"loss": 1.7364,
|
1235 |
+
"rewards/accuracies": 0.606249988079071,
|
1236 |
+
"rewards/chosen": -7.976959228515625,
|
1237 |
+
"rewards/margins": 0.8503401875495911,
|
1238 |
+
"rewards/rejected": -8.827299118041992,
|
1239 |
+
"step": 410
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.8688824914943732,
|
1243 |
+
"grad_norm": 8.979600106055784,
|
1244 |
+
"learning_rate": 2.5328246937043525e-08,
|
1245 |
+
"logits/chosen": -1.6459277868270874,
|
1246 |
+
"logits/rejected": -1.6195147037506104,
|
1247 |
+
"logps/chosen": -7.984838008880615,
|
1248 |
+
"logps/rejected": -9.079233169555664,
|
1249 |
+
"loss": 1.7264,
|
1250 |
+
"rewards/accuracies": 0.59375,
|
1251 |
+
"rewards/chosen": -7.984838008880615,
|
1252 |
+
"rewards/margins": 1.094395637512207,
|
1253 |
+
"rewards/rejected": -9.079233169555664,
|
1254 |
+
"step": 415
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.8793509552473174,
|
1258 |
+
"grad_norm": 6.181198265400907,
|
1259 |
+
"learning_rate": 2.1464952759020856e-08,
|
1260 |
+
"logits/chosen": -1.6045997142791748,
|
1261 |
+
"logits/rejected": -1.5594054460525513,
|
1262 |
+
"logps/chosen": -7.9123215675354,
|
1263 |
+
"logps/rejected": -8.782036781311035,
|
1264 |
+
"loss": 1.7493,
|
1265 |
+
"rewards/accuracies": 0.581250011920929,
|
1266 |
+
"rewards/chosen": -7.9123215675354,
|
1267 |
+
"rewards/margins": 0.8697155117988586,
|
1268 |
+
"rewards/rejected": -8.782036781311035,
|
1269 |
+
"step": 420
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.8898194190002617,
|
1273 |
+
"grad_norm": 7.693545140925747,
|
1274 |
+
"learning_rate": 1.7908016745981856e-08,
|
1275 |
+
"logits/chosen": -1.615017294883728,
|
1276 |
+
"logits/rejected": -1.5611761808395386,
|
1277 |
+
"logps/chosen": -8.289026260375977,
|
1278 |
+
"logps/rejected": -9.341882705688477,
|
1279 |
+
"loss": 1.733,
|
1280 |
+
"rewards/accuracies": 0.581250011920929,
|
1281 |
+
"rewards/chosen": -8.289026260375977,
|
1282 |
+
"rewards/margins": 1.0528560876846313,
|
1283 |
+
"rewards/rejected": -9.341882705688477,
|
1284 |
+
"step": 425
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.9002878827532059,
|
1288 |
+
"grad_norm": 6.582142344582445,
|
1289 |
+
"learning_rate": 1.4662207078575684e-08,
|
1290 |
+
"logits/chosen": -1.5919125080108643,
|
1291 |
+
"logits/rejected": -1.5359071493148804,
|
1292 |
+
"logps/chosen": -7.956709861755371,
|
1293 |
+
"logps/rejected": -9.315800666809082,
|
1294 |
+
"loss": 1.7211,
|
1295 |
+
"rewards/accuracies": 0.574999988079071,
|
1296 |
+
"rewards/chosen": -7.956709861755371,
|
1297 |
+
"rewards/margins": 1.3590909242630005,
|
1298 |
+
"rewards/rejected": -9.315800666809082,
|
1299 |
+
"step": 430
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.9107563465061502,
|
1303 |
+
"grad_norm": 8.523918422589938,
|
1304 |
+
"learning_rate": 1.1731874863145142e-08,
|
1305 |
+
"logits/chosen": -1.599135398864746,
|
1306 |
+
"logits/rejected": -1.5693204402923584,
|
1307 |
+
"logps/chosen": -8.411205291748047,
|
1308 |
+
"logps/rejected": -9.192506790161133,
|
1309 |
+
"loss": 1.7356,
|
1310 |
+
"rewards/accuracies": 0.5687500238418579,
|
1311 |
+
"rewards/chosen": -8.411205291748047,
|
1312 |
+
"rewards/margins": 0.781301736831665,
|
1313 |
+
"rewards/rejected": -9.192506790161133,
|
1314 |
+
"step": 435
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.9212248102590945,
|
1318 |
+
"grad_norm": 7.451771387036121,
|
1319 |
+
"learning_rate": 9.12094829893642e-09,
|
1320 |
+
"logits/chosen": -1.607877492904663,
|
1321 |
+
"logits/rejected": -1.5552005767822266,
|
1322 |
+
"logps/chosen": -8.183059692382812,
|
1323 |
+
"logps/rejected": -9.428353309631348,
|
1324 |
+
"loss": 1.7353,
|
1325 |
+
"rewards/accuracies": 0.5375000238418579,
|
1326 |
+
"rewards/chosen": -8.183059692382812,
|
1327 |
+
"rewards/margins": 1.2452945709228516,
|
1328 |
+
"rewards/rejected": -9.428353309631348,
|
1329 |
+
"step": 440
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.9316932740120387,
|
1333 |
+
"grad_norm": 9.436081897769167,
|
1334 |
+
"learning_rate": 6.832927412229017e-09,
|
1335 |
+
"logits/chosen": -1.6107797622680664,
|
1336 |
+
"logits/rejected": -1.5790627002716064,
|
1337 |
+
"logps/chosen": -8.090998649597168,
|
1338 |
+
"logps/rejected": -9.029291152954102,
|
1339 |
+
"loss": 1.7392,
|
1340 |
+
"rewards/accuracies": 0.606249988079071,
|
1341 |
+
"rewards/chosen": -8.090998649597168,
|
1342 |
+
"rewards/margins": 0.9382919073104858,
|
1343 |
+
"rewards/rejected": -9.029291152954102,
|
1344 |
+
"step": 445
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.942161737764983,
|
1348 |
+
"grad_norm": 8.582428584508216,
|
1349 |
+
"learning_rate": 4.8708793644441086e-09,
|
1350 |
+
"logits/chosen": -1.5821881294250488,
|
1351 |
+
"logits/rejected": -1.5397818088531494,
|
1352 |
+
"logps/chosen": -8.387347221374512,
|
1353 |
+
"logps/rejected": -9.367807388305664,
|
1354 |
+
"loss": 1.746,
|
1355 |
+
"rewards/accuracies": 0.5874999761581421,
|
1356 |
+
"rewards/chosen": -8.387347221374512,
|
1357 |
+
"rewards/margins": 0.9804602861404419,
|
1358 |
+
"rewards/rejected": -9.367807388305664,
|
1359 |
+
"step": 450
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.9526302015179272,
|
1363 |
+
"grad_norm": 6.129069741713946,
|
1364 |
+
"learning_rate": 3.2374343405217884e-09,
|
1365 |
+
"logits/chosen": -1.6205213069915771,
|
1366 |
+
"logits/rejected": -1.573266625404358,
|
1367 |
+
"logps/chosen": -8.136959075927734,
|
1368 |
+
"logps/rejected": -9.380440711975098,
|
1369 |
+
"loss": 1.7286,
|
1370 |
+
"rewards/accuracies": 0.6625000238418579,
|
1371 |
+
"rewards/chosen": -8.136959075927734,
|
1372 |
+
"rewards/margins": 1.243481993675232,
|
1373 |
+
"rewards/rejected": -9.380440711975098,
|
1374 |
+
"step": 455
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.9630986652708715,
|
1378 |
+
"grad_norm": 7.975954172184094,
|
1379 |
+
"learning_rate": 1.9347820230782295e-09,
|
1380 |
+
"logits/chosen": -1.6145153045654297,
|
1381 |
+
"logits/rejected": -1.5640535354614258,
|
1382 |
+
"logps/chosen": -8.394238471984863,
|
1383 |
+
"logps/rejected": -9.535688400268555,
|
1384 |
+
"loss": 1.727,
|
1385 |
+
"rewards/accuracies": 0.637499988079071,
|
1386 |
+
"rewards/chosen": -8.394238471984863,
|
1387 |
+
"rewards/margins": 1.14145028591156,
|
1388 |
+
"rewards/rejected": -9.535688400268555,
|
1389 |
+
"step": 460
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.9735671290238157,
|
1393 |
+
"grad_norm": 5.8616098100207195,
|
1394 |
+
"learning_rate": 9.64668657069706e-10,
|
1395 |
+
"logits/chosen": -1.639035940170288,
|
1396 |
+
"logits/rejected": -1.5807130336761475,
|
1397 |
+
"logps/chosen": -8.210695266723633,
|
1398 |
+
"logps/rejected": -9.582908630371094,
|
1399 |
+
"loss": 1.7511,
|
1400 |
+
"rewards/accuracies": 0.612500011920929,
|
1401 |
+
"rewards/chosen": -8.210695266723633,
|
1402 |
+
"rewards/margins": 1.372214674949646,
|
1403 |
+
"rewards/rejected": -9.582908630371094,
|
1404 |
+
"step": 465
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.98403559277676,
|
1408 |
+
"grad_norm": 6.126688648522468,
|
1409 |
+
"learning_rate": 3.2839470889836627e-10,
|
1410 |
+
"logits/chosen": -1.6169319152832031,
|
1411 |
+
"logits/rejected": -1.5936636924743652,
|
1412 |
+
"logps/chosen": -8.055643081665039,
|
1413 |
+
"logps/rejected": -8.981685638427734,
|
1414 |
+
"loss": 1.739,
|
1415 |
+
"rewards/accuracies": 0.550000011920929,
|
1416 |
+
"rewards/chosen": -8.055643081665039,
|
1417 |
+
"rewards/margins": 0.9260419011116028,
|
1418 |
+
"rewards/rejected": -8.981685638427734,
|
1419 |
+
"step": 470
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.9945040565297043,
|
1423 |
+
"grad_norm": 7.844036990048118,
|
1424 |
+
"learning_rate": 2.6813123097352287e-11,
|
1425 |
+
"logits/chosen": -1.6366430521011353,
|
1426 |
+
"logits/rejected": -1.5729566812515259,
|
1427 |
+
"logps/chosen": -8.483617782592773,
|
1428 |
+
"logps/rejected": -9.541167259216309,
|
1429 |
+
"loss": 1.7467,
|
1430 |
+
"rewards/accuracies": 0.59375,
|
1431 |
+
"rewards/chosen": -8.483617782592773,
|
1432 |
+
"rewards/margins": 1.0575507879257202,
|
1433 |
+
"rewards/rejected": -9.541167259216309,
|
1434 |
+
"step": 475
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.998691442030882,
|
1438 |
+
"step": 477,
|
1439 |
+
"total_flos": 0.0,
|
1440 |
+
"train_loss": 1.7629729861733299,
|
1441 |
+
"train_runtime": 8203.4319,
|
1442 |
+
"train_samples_per_second": 7.452,
|
1443 |
+
"train_steps_per_second": 0.058
|
1444 |
+
}
|
1445 |
+
],
|
1446 |
+
"logging_steps": 5,
|
1447 |
+
"max_steps": 477,
|
1448 |
+
"num_input_tokens_seen": 0,
|
1449 |
+
"num_train_epochs": 1,
|
1450 |
+
"save_steps": 1000000,
|
1451 |
+
"total_flos": 0.0,
|
1452 |
+
"train_batch_size": 2,
|
1453 |
+
"trial_name": null,
|
1454 |
+
"trial_params": null
|
1455 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52878a460b123ec0b0ddf547ab8d51501e0f9f7009fb1e44ebccff32a9a8c0c9
|
3 |
+
size 7160
|