Upload folder using huggingface_hub
Browse files- README.md +44 -0
- checkpoint-11153/config.json +28 -0
- checkpoint-11153/generation_config.json +6 -0
- checkpoint-11153/latest +1 -0
- checkpoint-11153/model-00001-of-00004.safetensors +3 -0
- checkpoint-11153/model-00002-of-00004.safetensors +3 -0
- checkpoint-11153/model-00003-of-00004.safetensors +3 -0
- checkpoint-11153/model-00004-of-00004.safetensors +3 -0
- checkpoint-11153/model.safetensors.index.json +298 -0
- checkpoint-11153/rng_state_0.pth +3 -0
- checkpoint-11153/rng_state_1.pth +3 -0
- checkpoint-11153/rng_state_2.pth +3 -0
- checkpoint-11153/rng_state_3.pth +3 -0
- checkpoint-11153/rng_state_4.pth +3 -0
- checkpoint-11153/rng_state_5.pth +3 -0
- checkpoint-11153/rng_state_6.pth +3 -0
- checkpoint-11153/rng_state_7.pth +3 -0
- checkpoint-11153/scheduler.pt +3 -0
- checkpoint-11153/special_tokens_map.json +13 -0
- checkpoint-11153/tokenizer.json +0 -0
- checkpoint-11153/tokenizer_config.json +2119 -0
- checkpoint-11153/trainer_state.json +3143 -0
- checkpoint-11153/training_args.bin +3 -0
- checkpoint-11153/zero_to_fp32.py +604 -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 +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2119 -0
- training_args.bin +3 -0
- training_params.json +47 -0
README.md
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation-inference
|
5 |
+
- text-generation
|
6 |
+
library_name: transformers
|
7 |
+
widget:
|
8 |
+
- messages:
|
9 |
+
- role: user
|
10 |
+
content: What is your favorite condiment?
|
11 |
+
license: other
|
12 |
+
---
|
13 |
+
|
14 |
+
# Model Trained Using AutoTrain
|
15 |
+
|
16 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
17 |
+
|
18 |
+
# Usage
|
19 |
+
|
20 |
+
```python
|
21 |
+
|
22 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
23 |
+
|
24 |
+
model_path = "PATH_TO_THIS_REPO"
|
25 |
+
|
26 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
27 |
+
model = AutoModelForCausalLM.from_pretrained(
|
28 |
+
model_path,
|
29 |
+
device_map="auto",
|
30 |
+
torch_dtype='auto'
|
31 |
+
).eval()
|
32 |
+
|
33 |
+
# Prompt content: "hi"
|
34 |
+
messages = [
|
35 |
+
{"role": "user", "content": "hi"}
|
36 |
+
]
|
37 |
+
|
38 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
39 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
40 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
41 |
+
|
42 |
+
# Model response: "Hello! How can I assist you today?"
|
43 |
+
print(response)
|
44 |
+
```
|
checkpoint-11153/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 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": "4.40.0",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 128264
|
28 |
+
}
|
checkpoint-11153/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": "4.40.0"
|
6 |
+
}
|
checkpoint-11153/latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step11153
|
checkpoint-11153/model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4dc60ba1d2073bdd95a0f469265587e9711e0e35b5569da784f287cd6ab0356
|
3 |
+
size 4976764208
|
checkpoint-11153/model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cb22b1acddca151372ab19dda1bc7dfed4848c70e15bf93e20fc7c02b4fdb98
|
3 |
+
size 4999802720
|
checkpoint-11153/model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5136aa7410834a6af82d77dbbb7b3e854b09b750e55406a7c6b3ced0e24b4afb
|
3 |
+
size 4915916176
|
checkpoint-11153/model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8708006d0d25d48da829f87f16dd42ba10f7286b63ab292b7546c45be3ff2059
|
3 |
+
size 1168204344
|
checkpoint-11153/model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 16060653568
|
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 |
+
}
|
checkpoint-11153/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:575119a228f98110923ffa2dedcb50e3317251b26054355d015e0b2240d566f2
|
3 |
+
size 15984
|
checkpoint-11153/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0728b56dab7abb5ef8a0d4bae3519c5767c97467bdd886d26bf19cc8599d0312
|
3 |
+
size 15984
|
checkpoint-11153/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4e481d4ef1546694da7337f6bb6c658b866dcb79b85deeb477da0d27ebe851e
|
3 |
+
size 15984
|
checkpoint-11153/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:353c60be37ea56fc992fca446598ceca5d1fd002aa3bd6dbb9ad740e6f47ebb3
|
3 |
+
size 15984
|
checkpoint-11153/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9107fe964ba7205e354084b85210e5a5ea1c98cfd4d38adb9cd3926945dcae4
|
3 |
+
size 15984
|
checkpoint-11153/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69d1bb1abee38b92e53f3f23549b642ce0f1edcdccf7b6129847ac61636e96d5
|
3 |
+
size 15984
|
checkpoint-11153/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afd5516048e20f36959601574e29e40106085a7d3cdc7bf425ce5e84633490e6
|
3 |
+
size 15984
|
checkpoint-11153/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e2c46927fc06939b4c976a01e4b95dec1f8b98ceaea86d31a5d756fc30ff006
|
3 |
+
size 15984
|
checkpoint-11153/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d960e8208aff0ce325af0e98a7691007c04a2bd8d6ea631be6bf97d32f9ca866
|
3 |
+
size 1064
|
checkpoint-11153/special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>user",
|
4 |
+
"<|im_start|>assistant",
|
5 |
+
"<|im_start|>system",
|
6 |
+
"<|im_end|>",
|
7 |
+
"<s>",
|
8 |
+
"<pad>"
|
9 |
+
],
|
10 |
+
"bos_token": "<s>",
|
11 |
+
"eos_token": "<|im_end|>",
|
12 |
+
"pad_token": "<pad>"
|
13 |
+
}
|
checkpoint-11153/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-11153/tokenizer_config.json
ADDED
@@ -0,0 +1,2119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"128256": {
|
2052 |
+
"content": "<s>",
|
2053 |
+
"lstrip": false,
|
2054 |
+
"normalized": false,
|
2055 |
+
"rstrip": false,
|
2056 |
+
"single_word": false,
|
2057 |
+
"special": true
|
2058 |
+
},
|
2059 |
+
"128257": {
|
2060 |
+
"content": "<|im_end|>",
|
2061 |
+
"lstrip": false,
|
2062 |
+
"normalized": false,
|
2063 |
+
"rstrip": false,
|
2064 |
+
"single_word": false,
|
2065 |
+
"special": true
|
2066 |
+
},
|
2067 |
+
"128258": {
|
2068 |
+
"content": "<pad>",
|
2069 |
+
"lstrip": false,
|
2070 |
+
"normalized": false,
|
2071 |
+
"rstrip": false,
|
2072 |
+
"single_word": false,
|
2073 |
+
"special": true
|
2074 |
+
},
|
2075 |
+
"128259": {
|
2076 |
+
"content": "<|im_start|>user",
|
2077 |
+
"lstrip": false,
|
2078 |
+
"normalized": false,
|
2079 |
+
"rstrip": false,
|
2080 |
+
"single_word": false,
|
2081 |
+
"special": true
|
2082 |
+
},
|
2083 |
+
"128260": {
|
2084 |
+
"content": "<|im_start|>assistant",
|
2085 |
+
"lstrip": false,
|
2086 |
+
"normalized": false,
|
2087 |
+
"rstrip": false,
|
2088 |
+
"single_word": false,
|
2089 |
+
"special": true
|
2090 |
+
},
|
2091 |
+
"128261": {
|
2092 |
+
"content": "<|im_start|>system",
|
2093 |
+
"lstrip": false,
|
2094 |
+
"normalized": false,
|
2095 |
+
"rstrip": false,
|
2096 |
+
"single_word": false,
|
2097 |
+
"special": true
|
2098 |
+
}
|
2099 |
+
},
|
2100 |
+
"additional_special_tokens": [
|
2101 |
+
"<|im_start|>user",
|
2102 |
+
"<|im_start|>assistant",
|
2103 |
+
"<|im_start|>system",
|
2104 |
+
"<|im_end|>",
|
2105 |
+
"<s>",
|
2106 |
+
"<pad>"
|
2107 |
+
],
|
2108 |
+
"bos_token": "<s>",
|
2109 |
+
"chat_template": "{% for message in messages %}\n{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% if loop.last and add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}{% endfor %}",
|
2110 |
+
"clean_up_tokenization_spaces": true,
|
2111 |
+
"eos_token": "<|im_end|>",
|
2112 |
+
"model_input_names": [
|
2113 |
+
"input_ids",
|
2114 |
+
"attention_mask"
|
2115 |
+
],
|
2116 |
+
"model_max_length": 8192,
|
2117 |
+
"pad_token": "<pad>",
|
2118 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2119 |
+
}
|
checkpoint-11153/trainer_state.json
ADDED
@@ -0,0 +1,3143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 11153,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0022415493589168834,
|
13 |
+
"grad_norm": 15.685082226240027,
|
14 |
+
"learning_rate": 4.480286738351255e-07,
|
15 |
+
"loss": 1.726,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.004483098717833767,
|
20 |
+
"grad_norm": 4.767375275306418,
|
21 |
+
"learning_rate": 8.96057347670251e-07,
|
22 |
+
"loss": 1.4821,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.00672464807675065,
|
27 |
+
"grad_norm": 2.7898427654813496,
|
28 |
+
"learning_rate": 1.3440860215053765e-06,
|
29 |
+
"loss": 1.3178,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.008966197435667534,
|
34 |
+
"grad_norm": 2.450767559139303,
|
35 |
+
"learning_rate": 1.792114695340502e-06,
|
36 |
+
"loss": 1.2526,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.011207746794584417,
|
41 |
+
"grad_norm": 2.1230121564392475,
|
42 |
+
"learning_rate": 2.2401433691756277e-06,
|
43 |
+
"loss": 1.2204,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0134492961535013,
|
48 |
+
"grad_norm": 2.5183780437270205,
|
49 |
+
"learning_rate": 2.688172043010753e-06,
|
50 |
+
"loss": 1.1894,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.015690845512418183,
|
55 |
+
"grad_norm": 2.1917851710152974,
|
56 |
+
"learning_rate": 3.1362007168458786e-06,
|
57 |
+
"loss": 1.1946,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.017932394871335067,
|
62 |
+
"grad_norm": 2.2162729922708118,
|
63 |
+
"learning_rate": 3.584229390681004e-06,
|
64 |
+
"loss": 1.1389,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.02017394423025195,
|
69 |
+
"grad_norm": 2.3941641310533925,
|
70 |
+
"learning_rate": 4.032258064516129e-06,
|
71 |
+
"loss": 1.1478,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.022415493589168833,
|
76 |
+
"grad_norm": 3.072121988145324,
|
77 |
+
"learning_rate": 4.480286738351255e-06,
|
78 |
+
"loss": 1.1468,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.024657042948085718,
|
83 |
+
"grad_norm": 2.219661451743802,
|
84 |
+
"learning_rate": 4.928315412186381e-06,
|
85 |
+
"loss": 1.1425,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.0268985923070026,
|
90 |
+
"grad_norm": 2.4345631665676533,
|
91 |
+
"learning_rate": 5.376344086021506e-06,
|
92 |
+
"loss": 1.1095,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.029140141665919484,
|
97 |
+
"grad_norm": 2.047942477418226,
|
98 |
+
"learning_rate": 5.824372759856631e-06,
|
99 |
+
"loss": 1.1204,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.031381691024836365,
|
104 |
+
"grad_norm": 2.175499992275822,
|
105 |
+
"learning_rate": 6.272401433691757e-06,
|
106 |
+
"loss": 1.1202,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.03362324038375325,
|
111 |
+
"grad_norm": 2.25503906485662,
|
112 |
+
"learning_rate": 6.720430107526882e-06,
|
113 |
+
"loss": 1.1022,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.035864789742670135,
|
118 |
+
"grad_norm": 2.108460216356371,
|
119 |
+
"learning_rate": 7.168458781362008e-06,
|
120 |
+
"loss": 1.0877,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.03810633910158702,
|
125 |
+
"grad_norm": 2.240064238054789,
|
126 |
+
"learning_rate": 7.616487455197133e-06,
|
127 |
+
"loss": 1.1007,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.0403478884605039,
|
132 |
+
"grad_norm": 2.4263093751968734,
|
133 |
+
"learning_rate": 8.064516129032258e-06,
|
134 |
+
"loss": 1.0936,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.04258943781942078,
|
139 |
+
"grad_norm": 2.387017798068924,
|
140 |
+
"learning_rate": 8.512544802867385e-06,
|
141 |
+
"loss": 1.0761,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.04483098717833767,
|
146 |
+
"grad_norm": 2.1179318054101564,
|
147 |
+
"learning_rate": 8.96057347670251e-06,
|
148 |
+
"loss": 1.0771,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.04707253653725455,
|
153 |
+
"grad_norm": 1.9922816447378509,
|
154 |
+
"learning_rate": 9.408602150537635e-06,
|
155 |
+
"loss": 1.0864,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.049314085896171436,
|
160 |
+
"grad_norm": 2.030735040176059,
|
161 |
+
"learning_rate": 9.856630824372761e-06,
|
162 |
+
"loss": 1.0932,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.051555635255088314,
|
167 |
+
"grad_norm": 1.9365105060421755,
|
168 |
+
"learning_rate": 1.0304659498207886e-05,
|
169 |
+
"loss": 1.0992,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.0537971846140052,
|
174 |
+
"grad_norm": 2.1272853307800044,
|
175 |
+
"learning_rate": 1.0752688172043012e-05,
|
176 |
+
"loss": 1.0712,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.056038733972922083,
|
181 |
+
"grad_norm": 2.1859906837121907,
|
182 |
+
"learning_rate": 1.1200716845878136e-05,
|
183 |
+
"loss": 1.0748,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.05828028333183897,
|
188 |
+
"grad_norm": 2.079572861691428,
|
189 |
+
"learning_rate": 1.1648745519713262e-05,
|
190 |
+
"loss": 1.0771,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.06052183269075585,
|
195 |
+
"grad_norm": 1.9857796074700236,
|
196 |
+
"learning_rate": 1.2096774193548388e-05,
|
197 |
+
"loss": 1.0541,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.06276338204967273,
|
202 |
+
"grad_norm": 2.0507709686842315,
|
203 |
+
"learning_rate": 1.2544802867383515e-05,
|
204 |
+
"loss": 1.0751,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.06500493140858962,
|
209 |
+
"grad_norm": 1.952012882655032,
|
210 |
+
"learning_rate": 1.299283154121864e-05,
|
211 |
+
"loss": 1.0628,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.0672464807675065,
|
216 |
+
"grad_norm": 2.1878324461110856,
|
217 |
+
"learning_rate": 1.3440860215053763e-05,
|
218 |
+
"loss": 1.0584,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.06948803012642338,
|
223 |
+
"grad_norm": 2.054184787294387,
|
224 |
+
"learning_rate": 1.388888888888889e-05,
|
225 |
+
"loss": 1.0871,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.07172957948534027,
|
230 |
+
"grad_norm": 2.125679946407211,
|
231 |
+
"learning_rate": 1.4336917562724016e-05,
|
232 |
+
"loss": 1.0784,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.07397112884425715,
|
237 |
+
"grad_norm": 2.1121699070033872,
|
238 |
+
"learning_rate": 1.4784946236559142e-05,
|
239 |
+
"loss": 1.0598,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.07621267820317404,
|
244 |
+
"grad_norm": 2.0730206555235906,
|
245 |
+
"learning_rate": 1.5232974910394266e-05,
|
246 |
+
"loss": 1.0786,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.07845422756209092,
|
251 |
+
"grad_norm": 2.027127840079525,
|
252 |
+
"learning_rate": 1.5681003584229394e-05,
|
253 |
+
"loss": 1.0634,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.0806957769210078,
|
258 |
+
"grad_norm": 2.023384971151795,
|
259 |
+
"learning_rate": 1.6129032258064517e-05,
|
260 |
+
"loss": 1.0764,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.08293732627992469,
|
265 |
+
"grad_norm": 2.0055801278407075,
|
266 |
+
"learning_rate": 1.6577060931899643e-05,
|
267 |
+
"loss": 1.0673,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.08517887563884156,
|
272 |
+
"grad_norm": 1.9506409683212098,
|
273 |
+
"learning_rate": 1.702508960573477e-05,
|
274 |
+
"loss": 1.0742,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.08742042499775846,
|
279 |
+
"grad_norm": 2.1771441973840733,
|
280 |
+
"learning_rate": 1.7473118279569895e-05,
|
281 |
+
"loss": 1.0761,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.08966197435667533,
|
286 |
+
"grad_norm": 2.011510686003709,
|
287 |
+
"learning_rate": 1.792114695340502e-05,
|
288 |
+
"loss": 1.0706,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.09190352371559221,
|
293 |
+
"grad_norm": 1.8219073311702734,
|
294 |
+
"learning_rate": 1.8369175627240144e-05,
|
295 |
+
"loss": 1.0867,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.0941450730745091,
|
300 |
+
"grad_norm": 2.084440231532221,
|
301 |
+
"learning_rate": 1.881720430107527e-05,
|
302 |
+
"loss": 1.1018,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.09638662243342598,
|
307 |
+
"grad_norm": 1.998527691194371,
|
308 |
+
"learning_rate": 1.9265232974910396e-05,
|
309 |
+
"loss": 1.0858,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.09862817179234287,
|
314 |
+
"grad_norm": 2.0128555781491784,
|
315 |
+
"learning_rate": 1.9713261648745522e-05,
|
316 |
+
"loss": 1.0525,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.10086972115125975,
|
321 |
+
"grad_norm": 2.080552489821866,
|
322 |
+
"learning_rate": 1.9982066354488394e-05,
|
323 |
+
"loss": 1.0685,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.10311127051017663,
|
328 |
+
"grad_norm": 2.093067690460913,
|
329 |
+
"learning_rate": 1.9932250672511707e-05,
|
330 |
+
"loss": 1.0376,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.10535281986909352,
|
335 |
+
"grad_norm": 1.9149860215931092,
|
336 |
+
"learning_rate": 1.9882434990535024e-05,
|
337 |
+
"loss": 1.0782,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.1075943692280104,
|
342 |
+
"grad_norm": 1.88017980052791,
|
343 |
+
"learning_rate": 1.9832619308558337e-05,
|
344 |
+
"loss": 1.0766,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.10983591858692729,
|
349 |
+
"grad_norm": 1.91492994234324,
|
350 |
+
"learning_rate": 1.978280362658165e-05,
|
351 |
+
"loss": 1.0922,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.11207746794584417,
|
356 |
+
"grad_norm": 2.0110976065228345,
|
357 |
+
"learning_rate": 1.9732987944604963e-05,
|
358 |
+
"loss": 1.0442,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.11431901730476104,
|
363 |
+
"grad_norm": 1.963223650876964,
|
364 |
+
"learning_rate": 1.9683172262628276e-05,
|
365 |
+
"loss": 1.0587,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.11656056666367794,
|
370 |
+
"grad_norm": 2.134419169579966,
|
371 |
+
"learning_rate": 1.963335658065159e-05,
|
372 |
+
"loss": 1.0926,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.11880211602259481,
|
377 |
+
"grad_norm": 1.9854410848170396,
|
378 |
+
"learning_rate": 1.9583540898674905e-05,
|
379 |
+
"loss": 1.0642,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.1210436653815117,
|
384 |
+
"grad_norm": 2.1190303504427717,
|
385 |
+
"learning_rate": 1.953372521669822e-05,
|
386 |
+
"loss": 1.0963,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.12328521474042858,
|
391 |
+
"grad_norm": 2.0917025707015915,
|
392 |
+
"learning_rate": 1.948390953472153e-05,
|
393 |
+
"loss": 1.0652,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.12552676409934546,
|
398 |
+
"grad_norm": 2.0833056932137466,
|
399 |
+
"learning_rate": 1.9434093852744848e-05,
|
400 |
+
"loss": 1.0774,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.12776831345826234,
|
405 |
+
"grad_norm": 1.923749930785264,
|
406 |
+
"learning_rate": 1.938427817076816e-05,
|
407 |
+
"loss": 1.066,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.13000986281717924,
|
412 |
+
"grad_norm": 1.917103256862209,
|
413 |
+
"learning_rate": 1.9334462488791474e-05,
|
414 |
+
"loss": 1.052,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.13225141217609612,
|
419 |
+
"grad_norm": 2.2817156042334896,
|
420 |
+
"learning_rate": 1.9284646806814787e-05,
|
421 |
+
"loss": 1.053,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.134492961535013,
|
426 |
+
"grad_norm": 1.8228317130823313,
|
427 |
+
"learning_rate": 1.92348311248381e-05,
|
428 |
+
"loss": 1.0346,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.13673451089392988,
|
433 |
+
"grad_norm": 1.8523579647705695,
|
434 |
+
"learning_rate": 1.9185015442861413e-05,
|
435 |
+
"loss": 1.0457,
|
436 |
+
"step": 1525
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.13897606025284676,
|
440 |
+
"grad_norm": 1.8768486959088566,
|
441 |
+
"learning_rate": 1.913519976088473e-05,
|
442 |
+
"loss": 1.0348,
|
443 |
+
"step": 1550
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.14121760961176366,
|
447 |
+
"grad_norm": 1.9857424877457883,
|
448 |
+
"learning_rate": 1.9085384078908043e-05,
|
449 |
+
"loss": 1.0439,
|
450 |
+
"step": 1575
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.14345915897068054,
|
454 |
+
"grad_norm": 2.531831058245927,
|
455 |
+
"learning_rate": 1.9035568396931356e-05,
|
456 |
+
"loss": 1.045,
|
457 |
+
"step": 1600
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.14570070832959742,
|
461 |
+
"grad_norm": 2.5223998582597855,
|
462 |
+
"learning_rate": 1.898575271495467e-05,
|
463 |
+
"loss": 1.0355,
|
464 |
+
"step": 1625
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.1479422576885143,
|
468 |
+
"grad_norm": 2.9220932656370366,
|
469 |
+
"learning_rate": 1.893593703297798e-05,
|
470 |
+
"loss": 1.0657,
|
471 |
+
"step": 1650
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.15018380704743117,
|
475 |
+
"grad_norm": 1.883244384210707,
|
476 |
+
"learning_rate": 1.8886121351001298e-05,
|
477 |
+
"loss": 1.0285,
|
478 |
+
"step": 1675
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.15242535640634808,
|
482 |
+
"grad_norm": 2.0400410969199445,
|
483 |
+
"learning_rate": 1.883630566902461e-05,
|
484 |
+
"loss": 1.0292,
|
485 |
+
"step": 1700
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.15466690576526496,
|
489 |
+
"grad_norm": 1.7753007869372996,
|
490 |
+
"learning_rate": 1.8786489987047924e-05,
|
491 |
+
"loss": 1.0508,
|
492 |
+
"step": 1725
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.15690845512418183,
|
496 |
+
"grad_norm": 1.6604310223265337,
|
497 |
+
"learning_rate": 1.8736674305071237e-05,
|
498 |
+
"loss": 1.0183,
|
499 |
+
"step": 1750
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.1591500044830987,
|
503 |
+
"grad_norm": 1.9310548345394576,
|
504 |
+
"learning_rate": 1.8686858623094554e-05,
|
505 |
+
"loss": 1.0438,
|
506 |
+
"step": 1775
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.1613915538420156,
|
510 |
+
"grad_norm": 1.8571948617085183,
|
511 |
+
"learning_rate": 1.8637042941117863e-05,
|
512 |
+
"loss": 1.0299,
|
513 |
+
"step": 1800
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.1636331032009325,
|
517 |
+
"grad_norm": 2.0999139482201037,
|
518 |
+
"learning_rate": 1.858722725914118e-05,
|
519 |
+
"loss": 1.0357,
|
520 |
+
"step": 1825
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.16587465255984937,
|
524 |
+
"grad_norm": 1.8302941023869517,
|
525 |
+
"learning_rate": 1.8537411577164493e-05,
|
526 |
+
"loss": 1.0394,
|
527 |
+
"step": 1850
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.16811620191876625,
|
531 |
+
"grad_norm": 1.7860535462449534,
|
532 |
+
"learning_rate": 1.8487595895187806e-05,
|
533 |
+
"loss": 1.0026,
|
534 |
+
"step": 1875
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.17035775127768313,
|
538 |
+
"grad_norm": 1.8983118114362876,
|
539 |
+
"learning_rate": 1.8437780213211122e-05,
|
540 |
+
"loss": 1.0178,
|
541 |
+
"step": 1900
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.1725993006366,
|
545 |
+
"grad_norm": 2.205679465328378,
|
546 |
+
"learning_rate": 1.8387964531234435e-05,
|
547 |
+
"loss": 1.0327,
|
548 |
+
"step": 1925
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.1748408499955169,
|
552 |
+
"grad_norm": 2.134664272100197,
|
553 |
+
"learning_rate": 1.8338148849257748e-05,
|
554 |
+
"loss": 1.029,
|
555 |
+
"step": 1950
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.1770823993544338,
|
559 |
+
"grad_norm": 1.9531002021208808,
|
560 |
+
"learning_rate": 1.828833316728106e-05,
|
561 |
+
"loss": 1.0521,
|
562 |
+
"step": 1975
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.17932394871335067,
|
566 |
+
"grad_norm": 1.9511745913401646,
|
567 |
+
"learning_rate": 1.8238517485304374e-05,
|
568 |
+
"loss": 1.0387,
|
569 |
+
"step": 2000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.18156549807226754,
|
573 |
+
"grad_norm": 1.7617448914936356,
|
574 |
+
"learning_rate": 1.8188701803327687e-05,
|
575 |
+
"loss": 1.0312,
|
576 |
+
"step": 2025
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.18380704743118442,
|
580 |
+
"grad_norm": 1.8660119308426493,
|
581 |
+
"learning_rate": 1.8138886121351004e-05,
|
582 |
+
"loss": 1.001,
|
583 |
+
"step": 2050
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.18604859679010133,
|
587 |
+
"grad_norm": 11.361341672786956,
|
588 |
+
"learning_rate": 1.8089070439374317e-05,
|
589 |
+
"loss": 1.0323,
|
590 |
+
"step": 2075
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.1882901461490182,
|
594 |
+
"grad_norm": 1.9440541229934303,
|
595 |
+
"learning_rate": 1.803925475739763e-05,
|
596 |
+
"loss": 1.0292,
|
597 |
+
"step": 2100
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.19053169550793508,
|
601 |
+
"grad_norm": 1.6998031346610352,
|
602 |
+
"learning_rate": 1.7989439075420946e-05,
|
603 |
+
"loss": 1.0125,
|
604 |
+
"step": 2125
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.19277324486685196,
|
608 |
+
"grad_norm": 2.1474706821772123,
|
609 |
+
"learning_rate": 1.793962339344426e-05,
|
610 |
+
"loss": 0.9816,
|
611 |
+
"step": 2150
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.19501479422576884,
|
615 |
+
"grad_norm": 1.7163947976457987,
|
616 |
+
"learning_rate": 1.788980771146757e-05,
|
617 |
+
"loss": 1.0192,
|
618 |
+
"step": 2175
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.19725634358468574,
|
622 |
+
"grad_norm": 1.8892267392764226,
|
623 |
+
"learning_rate": 1.7839992029490885e-05,
|
624 |
+
"loss": 1.0056,
|
625 |
+
"step": 2200
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.19949789294360262,
|
629 |
+
"grad_norm": 2.0524457692263076,
|
630 |
+
"learning_rate": 1.77901763475142e-05,
|
631 |
+
"loss": 1.0103,
|
632 |
+
"step": 2225
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.2017394423025195,
|
636 |
+
"grad_norm": 1.8606062165245123,
|
637 |
+
"learning_rate": 1.774036066553751e-05,
|
638 |
+
"loss": 1.0093,
|
639 |
+
"step": 2250
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.20398099166143638,
|
643 |
+
"grad_norm": 1.6620327251666154,
|
644 |
+
"learning_rate": 1.7690544983560828e-05,
|
645 |
+
"loss": 1.0018,
|
646 |
+
"step": 2275
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.20622254102035326,
|
650 |
+
"grad_norm": 1.8581969734354233,
|
651 |
+
"learning_rate": 1.764072930158414e-05,
|
652 |
+
"loss": 0.9882,
|
653 |
+
"step": 2300
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.20846409037927016,
|
657 |
+
"grad_norm": 1.9329085125000098,
|
658 |
+
"learning_rate": 1.7590913619607454e-05,
|
659 |
+
"loss": 1.0029,
|
660 |
+
"step": 2325
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.21070563973818704,
|
664 |
+
"grad_norm": 1.9189341443783814,
|
665 |
+
"learning_rate": 1.7541097937630767e-05,
|
666 |
+
"loss": 0.9814,
|
667 |
+
"step": 2350
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.21294718909710392,
|
671 |
+
"grad_norm": 1.8381222846173,
|
672 |
+
"learning_rate": 1.749128225565408e-05,
|
673 |
+
"loss": 0.9953,
|
674 |
+
"step": 2375
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.2151887384560208,
|
678 |
+
"grad_norm": 1.8899248374704989,
|
679 |
+
"learning_rate": 1.7441466573677396e-05,
|
680 |
+
"loss": 0.9823,
|
681 |
+
"step": 2400
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.21743028781493767,
|
685 |
+
"grad_norm": 1.7449302218389742,
|
686 |
+
"learning_rate": 1.739165089170071e-05,
|
687 |
+
"loss": 0.9797,
|
688 |
+
"step": 2425
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.21967183717385458,
|
692 |
+
"grad_norm": 1.8919151945987245,
|
693 |
+
"learning_rate": 1.7341835209724022e-05,
|
694 |
+
"loss": 1.0136,
|
695 |
+
"step": 2450
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.22191338653277146,
|
699 |
+
"grad_norm": 1.7269209983774687,
|
700 |
+
"learning_rate": 1.7292019527747335e-05,
|
701 |
+
"loss": 0.9936,
|
702 |
+
"step": 2475
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.22415493589168833,
|
706 |
+
"grad_norm": 2.0801589205177073,
|
707 |
+
"learning_rate": 1.7242203845770652e-05,
|
708 |
+
"loss": 0.9806,
|
709 |
+
"step": 2500
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.2263964852506052,
|
713 |
+
"grad_norm": 1.9132953909491215,
|
714 |
+
"learning_rate": 1.719238816379396e-05,
|
715 |
+
"loss": 0.9773,
|
716 |
+
"step": 2525
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.2286380346095221,
|
720 |
+
"grad_norm": 2.121494652645993,
|
721 |
+
"learning_rate": 1.7142572481817278e-05,
|
722 |
+
"loss": 0.9913,
|
723 |
+
"step": 2550
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.230879583968439,
|
727 |
+
"grad_norm": 1.984427309513833,
|
728 |
+
"learning_rate": 1.709275679984059e-05,
|
729 |
+
"loss": 0.9777,
|
730 |
+
"step": 2575
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.23312113332735587,
|
734 |
+
"grad_norm": 1.8076604331872659,
|
735 |
+
"learning_rate": 1.7042941117863904e-05,
|
736 |
+
"loss": 0.9916,
|
737 |
+
"step": 2600
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.23536268268627275,
|
741 |
+
"grad_norm": 1.729667080715962,
|
742 |
+
"learning_rate": 1.699312543588722e-05,
|
743 |
+
"loss": 0.959,
|
744 |
+
"step": 2625
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.23760423204518963,
|
748 |
+
"grad_norm": 1.6461940121533178,
|
749 |
+
"learning_rate": 1.6943309753910533e-05,
|
750 |
+
"loss": 0.9356,
|
751 |
+
"step": 2650
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.2398457814041065,
|
755 |
+
"grad_norm": 1.7818239495803552,
|
756 |
+
"learning_rate": 1.6893494071933847e-05,
|
757 |
+
"loss": 0.9836,
|
758 |
+
"step": 2675
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.2420873307630234,
|
762 |
+
"grad_norm": 1.7098481517946613,
|
763 |
+
"learning_rate": 1.684367838995716e-05,
|
764 |
+
"loss": 0.9626,
|
765 |
+
"step": 2700
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.2443288801219403,
|
769 |
+
"grad_norm": 1.865561495461263,
|
770 |
+
"learning_rate": 1.6793862707980473e-05,
|
771 |
+
"loss": 0.9773,
|
772 |
+
"step": 2725
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.24657042948085717,
|
776 |
+
"grad_norm": 1.7896064708721888,
|
777 |
+
"learning_rate": 1.6744047026003786e-05,
|
778 |
+
"loss": 0.9819,
|
779 |
+
"step": 2750
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.24881197883977405,
|
783 |
+
"grad_norm": 1.7260499292304918,
|
784 |
+
"learning_rate": 1.6694231344027102e-05,
|
785 |
+
"loss": 0.9752,
|
786 |
+
"step": 2775
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.2510535281986909,
|
790 |
+
"grad_norm": 1.826190790491217,
|
791 |
+
"learning_rate": 1.6644415662050415e-05,
|
792 |
+
"loss": 0.9346,
|
793 |
+
"step": 2800
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.25329507755760783,
|
797 |
+
"grad_norm": 1.7454817242814047,
|
798 |
+
"learning_rate": 1.6594599980073728e-05,
|
799 |
+
"loss": 0.9609,
|
800 |
+
"step": 2825
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.2555366269165247,
|
804 |
+
"grad_norm": 1.7578596385064043,
|
805 |
+
"learning_rate": 1.6544784298097045e-05,
|
806 |
+
"loss": 0.9556,
|
807 |
+
"step": 2850
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.2577781762754416,
|
811 |
+
"grad_norm": 1.7683018696985564,
|
812 |
+
"learning_rate": 1.6494968616120358e-05,
|
813 |
+
"loss": 0.9484,
|
814 |
+
"step": 2875
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.2600197256343585,
|
818 |
+
"grad_norm": 1.7223372499585023,
|
819 |
+
"learning_rate": 1.6445152934143667e-05,
|
820 |
+
"loss": 0.968,
|
821 |
+
"step": 2900
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.26226127499327534,
|
825 |
+
"grad_norm": 1.808053969311946,
|
826 |
+
"learning_rate": 1.6395337252166984e-05,
|
827 |
+
"loss": 0.9536,
|
828 |
+
"step": 2925
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.26450282435219225,
|
832 |
+
"grad_norm": 1.9043794632911786,
|
833 |
+
"learning_rate": 1.6345521570190297e-05,
|
834 |
+
"loss": 0.9442,
|
835 |
+
"step": 2950
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.2667443737111091,
|
839 |
+
"grad_norm": 1.7895687686236537,
|
840 |
+
"learning_rate": 1.629570588821361e-05,
|
841 |
+
"loss": 0.9466,
|
842 |
+
"step": 2975
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.268985923070026,
|
846 |
+
"grad_norm": 1.934781759123613,
|
847 |
+
"learning_rate": 1.6245890206236926e-05,
|
848 |
+
"loss": 0.9807,
|
849 |
+
"step": 3000
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.2712274724289429,
|
853 |
+
"grad_norm": 1.632988026978096,
|
854 |
+
"learning_rate": 1.619607452426024e-05,
|
855 |
+
"loss": 0.9594,
|
856 |
+
"step": 3025
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.27346902178785976,
|
860 |
+
"grad_norm": 2.027393243768135,
|
861 |
+
"learning_rate": 1.6146258842283552e-05,
|
862 |
+
"loss": 0.9531,
|
863 |
+
"step": 3050
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.27571057114677666,
|
867 |
+
"grad_norm": 1.8992087782858946,
|
868 |
+
"learning_rate": 1.6096443160306865e-05,
|
869 |
+
"loss": 0.9437,
|
870 |
+
"step": 3075
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.2779521205056935,
|
874 |
+
"grad_norm": 1.7343465694135203,
|
875 |
+
"learning_rate": 1.6046627478330178e-05,
|
876 |
+
"loss": 0.9626,
|
877 |
+
"step": 3100
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.2801936698646104,
|
881 |
+
"grad_norm": 1.7072938434556733,
|
882 |
+
"learning_rate": 1.5996811796353495e-05,
|
883 |
+
"loss": 0.9453,
|
884 |
+
"step": 3125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.2824352192235273,
|
888 |
+
"grad_norm": 1.8218156899532207,
|
889 |
+
"learning_rate": 1.5946996114376808e-05,
|
890 |
+
"loss": 0.9304,
|
891 |
+
"step": 3150
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.2846767685824442,
|
895 |
+
"grad_norm": 1.6937676571633637,
|
896 |
+
"learning_rate": 1.589718043240012e-05,
|
897 |
+
"loss": 0.9447,
|
898 |
+
"step": 3175
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.2869183179413611,
|
902 |
+
"grad_norm": 1.644893250819176,
|
903 |
+
"learning_rate": 1.5847364750423434e-05,
|
904 |
+
"loss": 0.9503,
|
905 |
+
"step": 3200
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.28915986730027793,
|
909 |
+
"grad_norm": 1.8909556942793773,
|
910 |
+
"learning_rate": 1.579754906844675e-05,
|
911 |
+
"loss": 0.949,
|
912 |
+
"step": 3225
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.29140141665919483,
|
916 |
+
"grad_norm": 1.8529318404284596,
|
917 |
+
"learning_rate": 1.574773338647006e-05,
|
918 |
+
"loss": 0.9152,
|
919 |
+
"step": 3250
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.29364296601811174,
|
923 |
+
"grad_norm": 1.7004297471160559,
|
924 |
+
"learning_rate": 1.5697917704493376e-05,
|
925 |
+
"loss": 0.9112,
|
926 |
+
"step": 3275
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.2958845153770286,
|
930 |
+
"grad_norm": 1.9502983060858345,
|
931 |
+
"learning_rate": 1.564810202251669e-05,
|
932 |
+
"loss": 0.9569,
|
933 |
+
"step": 3300
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.2981260647359455,
|
937 |
+
"grad_norm": 1.7459285738352261,
|
938 |
+
"learning_rate": 1.5598286340540002e-05,
|
939 |
+
"loss": 0.9441,
|
940 |
+
"step": 3325
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.30036761409486235,
|
944 |
+
"grad_norm": 1.6839416479204592,
|
945 |
+
"learning_rate": 1.554847065856332e-05,
|
946 |
+
"loss": 0.9343,
|
947 |
+
"step": 3350
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.30260916345377925,
|
951 |
+
"grad_norm": 1.7972168152482286,
|
952 |
+
"learning_rate": 1.5498654976586632e-05,
|
953 |
+
"loss": 0.93,
|
954 |
+
"step": 3375
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.30485071281269616,
|
958 |
+
"grad_norm": 1.7165679877234483,
|
959 |
+
"learning_rate": 1.5448839294609945e-05,
|
960 |
+
"loss": 0.9024,
|
961 |
+
"step": 3400
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.307092262171613,
|
965 |
+
"grad_norm": 1.8154734324573523,
|
966 |
+
"learning_rate": 1.5399023612633258e-05,
|
967 |
+
"loss": 0.9301,
|
968 |
+
"step": 3425
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.3093338115305299,
|
972 |
+
"grad_norm": 1.6952336101878391,
|
973 |
+
"learning_rate": 1.534920793065657e-05,
|
974 |
+
"loss": 0.9204,
|
975 |
+
"step": 3450
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.31157536088944676,
|
979 |
+
"grad_norm": 1.7430417778073755,
|
980 |
+
"learning_rate": 1.5299392248679884e-05,
|
981 |
+
"loss": 0.9325,
|
982 |
+
"step": 3475
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.31381691024836367,
|
986 |
+
"grad_norm": 1.8264268621395723,
|
987 |
+
"learning_rate": 1.5249576566703199e-05,
|
988 |
+
"loss": 0.9388,
|
989 |
+
"step": 3500
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.3160584596072806,
|
993 |
+
"grad_norm": 1.7279147424934178,
|
994 |
+
"learning_rate": 1.5199760884726513e-05,
|
995 |
+
"loss": 0.9532,
|
996 |
+
"step": 3525
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.3183000089661974,
|
1000 |
+
"grad_norm": 1.7829003359104079,
|
1001 |
+
"learning_rate": 1.5149945202749826e-05,
|
1002 |
+
"loss": 0.9156,
|
1003 |
+
"step": 3550
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.32054155832511433,
|
1007 |
+
"grad_norm": 1.8115804249304372,
|
1008 |
+
"learning_rate": 1.5100129520773141e-05,
|
1009 |
+
"loss": 0.9126,
|
1010 |
+
"step": 3575
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.3227831076840312,
|
1014 |
+
"grad_norm": 1.8101472164090928,
|
1015 |
+
"learning_rate": 1.5050313838796456e-05,
|
1016 |
+
"loss": 0.9276,
|
1017 |
+
"step": 3600
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.3250246570429481,
|
1021 |
+
"grad_norm": 1.9070110243849654,
|
1022 |
+
"learning_rate": 1.5000498156819767e-05,
|
1023 |
+
"loss": 0.9128,
|
1024 |
+
"step": 3625
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.327266206401865,
|
1028 |
+
"grad_norm": 1.9072311557403854,
|
1029 |
+
"learning_rate": 1.4950682474843082e-05,
|
1030 |
+
"loss": 0.9184,
|
1031 |
+
"step": 3650
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.32950775576078184,
|
1035 |
+
"grad_norm": 1.61923199587523,
|
1036 |
+
"learning_rate": 1.4900866792866395e-05,
|
1037 |
+
"loss": 0.911,
|
1038 |
+
"step": 3675
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.33174930511969875,
|
1042 |
+
"grad_norm": 1.8120353797625837,
|
1043 |
+
"learning_rate": 1.485105111088971e-05,
|
1044 |
+
"loss": 0.915,
|
1045 |
+
"step": 3700
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.3339908544786156,
|
1049 |
+
"grad_norm": 1.7354507845151927,
|
1050 |
+
"learning_rate": 1.4801235428913023e-05,
|
1051 |
+
"loss": 0.9115,
|
1052 |
+
"step": 3725
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.3362324038375325,
|
1056 |
+
"grad_norm": 1.7796643660754665,
|
1057 |
+
"learning_rate": 1.4751419746936338e-05,
|
1058 |
+
"loss": 0.9145,
|
1059 |
+
"step": 3750
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.3384739531964494,
|
1063 |
+
"grad_norm": 1.855968151723882,
|
1064 |
+
"learning_rate": 1.4701604064959652e-05,
|
1065 |
+
"loss": 0.9056,
|
1066 |
+
"step": 3775
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.34071550255536626,
|
1070 |
+
"grad_norm": 1.9082686727020328,
|
1071 |
+
"learning_rate": 1.4651788382982964e-05,
|
1072 |
+
"loss": 0.9304,
|
1073 |
+
"step": 3800
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.34295705191428316,
|
1077 |
+
"grad_norm": 1.8449390404041304,
|
1078 |
+
"learning_rate": 1.4601972701006277e-05,
|
1079 |
+
"loss": 0.8985,
|
1080 |
+
"step": 3825
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.3451986012732,
|
1084 |
+
"grad_norm": 1.7578794796486368,
|
1085 |
+
"learning_rate": 1.4552157019029591e-05,
|
1086 |
+
"loss": 0.8969,
|
1087 |
+
"step": 3850
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.3474401506321169,
|
1091 |
+
"grad_norm": 1.8367706573696312,
|
1092 |
+
"learning_rate": 1.4502341337052906e-05,
|
1093 |
+
"loss": 0.915,
|
1094 |
+
"step": 3875
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.3496816999910338,
|
1098 |
+
"grad_norm": 1.8822503403709299,
|
1099 |
+
"learning_rate": 1.4452525655076219e-05,
|
1100 |
+
"loss": 0.914,
|
1101 |
+
"step": 3900
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.3519232493499507,
|
1105 |
+
"grad_norm": 1.7324094016304221,
|
1106 |
+
"learning_rate": 1.4402709973099534e-05,
|
1107 |
+
"loss": 0.9103,
|
1108 |
+
"step": 3925
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.3541647987088676,
|
1112 |
+
"grad_norm": 1.924493271883657,
|
1113 |
+
"learning_rate": 1.4352894291122847e-05,
|
1114 |
+
"loss": 0.8822,
|
1115 |
+
"step": 3950
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.35640634806778443,
|
1119 |
+
"grad_norm": 1.7603655512407765,
|
1120 |
+
"learning_rate": 1.430307860914616e-05,
|
1121 |
+
"loss": 0.9047,
|
1122 |
+
"step": 3975
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.35864789742670133,
|
1126 |
+
"grad_norm": 1.728593406803126,
|
1127 |
+
"learning_rate": 1.4253262927169473e-05,
|
1128 |
+
"loss": 0.9034,
|
1129 |
+
"step": 4000
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.36088944678561824,
|
1133 |
+
"grad_norm": 1.7079384156065074,
|
1134 |
+
"learning_rate": 1.4203447245192788e-05,
|
1135 |
+
"loss": 0.9108,
|
1136 |
+
"step": 4025
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.3631309961445351,
|
1140 |
+
"grad_norm": 1.8124067484354314,
|
1141 |
+
"learning_rate": 1.41536315632161e-05,
|
1142 |
+
"loss": 0.8731,
|
1143 |
+
"step": 4050
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.365372545503452,
|
1147 |
+
"grad_norm": 1.6392410836376878,
|
1148 |
+
"learning_rate": 1.4103815881239415e-05,
|
1149 |
+
"loss": 0.8961,
|
1150 |
+
"step": 4075
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.36761409486236885,
|
1154 |
+
"grad_norm": 1.8375262874030192,
|
1155 |
+
"learning_rate": 1.405400019926273e-05,
|
1156 |
+
"loss": 0.9039,
|
1157 |
+
"step": 4100
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.36985564422128575,
|
1161 |
+
"grad_norm": 1.7237334097670618,
|
1162 |
+
"learning_rate": 1.4004184517286043e-05,
|
1163 |
+
"loss": 0.9017,
|
1164 |
+
"step": 4125
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.37209719358020266,
|
1168 |
+
"grad_norm": 1.7732172478528363,
|
1169 |
+
"learning_rate": 1.3954368835309358e-05,
|
1170 |
+
"loss": 0.8707,
|
1171 |
+
"step": 4150
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.3743387429391195,
|
1175 |
+
"grad_norm": 1.798174483175535,
|
1176 |
+
"learning_rate": 1.390455315333267e-05,
|
1177 |
+
"loss": 0.8951,
|
1178 |
+
"step": 4175
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.3765802922980364,
|
1182 |
+
"grad_norm": 1.6403444255783957,
|
1183 |
+
"learning_rate": 1.3854737471355984e-05,
|
1184 |
+
"loss": 0.8867,
|
1185 |
+
"step": 4200
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.37882184165695326,
|
1189 |
+
"grad_norm": 1.630947223766077,
|
1190 |
+
"learning_rate": 1.3804921789379297e-05,
|
1191 |
+
"loss": 0.8633,
|
1192 |
+
"step": 4225
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.38106339101587017,
|
1196 |
+
"grad_norm": 1.7170897564750465,
|
1197 |
+
"learning_rate": 1.3755106107402612e-05,
|
1198 |
+
"loss": 0.8984,
|
1199 |
+
"step": 4250
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.3833049403747871,
|
1203 |
+
"grad_norm": 2.375355817440413,
|
1204 |
+
"learning_rate": 1.3705290425425925e-05,
|
1205 |
+
"loss": 0.9036,
|
1206 |
+
"step": 4275
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.3855464897337039,
|
1210 |
+
"grad_norm": 1.773676455707909,
|
1211 |
+
"learning_rate": 1.365547474344924e-05,
|
1212 |
+
"loss": 0.8859,
|
1213 |
+
"step": 4300
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.38778803909262083,
|
1217 |
+
"grad_norm": 2.2923198536180385,
|
1218 |
+
"learning_rate": 1.3605659061472554e-05,
|
1219 |
+
"loss": 0.8914,
|
1220 |
+
"step": 4325
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.3900295884515377,
|
1224 |
+
"grad_norm": 1.5848618729646098,
|
1225 |
+
"learning_rate": 1.3555843379495866e-05,
|
1226 |
+
"loss": 0.8832,
|
1227 |
+
"step": 4350
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.3922711378104546,
|
1231 |
+
"grad_norm": 1.8306249640013397,
|
1232 |
+
"learning_rate": 1.350602769751918e-05,
|
1233 |
+
"loss": 0.8689,
|
1234 |
+
"step": 4375
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.3945126871693715,
|
1238 |
+
"grad_norm": 1.7205681208039685,
|
1239 |
+
"learning_rate": 1.3456212015542493e-05,
|
1240 |
+
"loss": 0.8886,
|
1241 |
+
"step": 4400
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.39675423652828834,
|
1245 |
+
"grad_norm": 1.7563808610676828,
|
1246 |
+
"learning_rate": 1.3406396333565808e-05,
|
1247 |
+
"loss": 0.8957,
|
1248 |
+
"step": 4425
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.39899578588720525,
|
1252 |
+
"grad_norm": 1.762473526098044,
|
1253 |
+
"learning_rate": 1.3356580651589121e-05,
|
1254 |
+
"loss": 0.886,
|
1255 |
+
"step": 4450
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.4012373352461221,
|
1259 |
+
"grad_norm": 1.5235508352345122,
|
1260 |
+
"learning_rate": 1.3306764969612436e-05,
|
1261 |
+
"loss": 0.9023,
|
1262 |
+
"step": 4475
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.403478884605039,
|
1266 |
+
"grad_norm": 1.6080245871591732,
|
1267 |
+
"learning_rate": 1.325694928763575e-05,
|
1268 |
+
"loss": 0.8742,
|
1269 |
+
"step": 4500
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.4057204339639559,
|
1273 |
+
"grad_norm": 1.6042016149275076,
|
1274 |
+
"learning_rate": 1.3207133605659062e-05,
|
1275 |
+
"loss": 0.8861,
|
1276 |
+
"step": 4525
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.40796198332287276,
|
1280 |
+
"grad_norm": 1.833739247341173,
|
1281 |
+
"learning_rate": 1.3157317923682375e-05,
|
1282 |
+
"loss": 0.8808,
|
1283 |
+
"step": 4550
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.41020353268178966,
|
1287 |
+
"grad_norm": 1.6633181057260342,
|
1288 |
+
"learning_rate": 1.310750224170569e-05,
|
1289 |
+
"loss": 0.8519,
|
1290 |
+
"step": 4575
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.4124450820407065,
|
1294 |
+
"grad_norm": 1.77817726319169,
|
1295 |
+
"learning_rate": 1.3057686559729004e-05,
|
1296 |
+
"loss": 0.8623,
|
1297 |
+
"step": 4600
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.4146866313996234,
|
1301 |
+
"grad_norm": 1.9820958145272036,
|
1302 |
+
"learning_rate": 1.3007870877752317e-05,
|
1303 |
+
"loss": 0.8659,
|
1304 |
+
"step": 4625
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.4169281807585403,
|
1308 |
+
"grad_norm": 1.6475751439718662,
|
1309 |
+
"learning_rate": 1.2958055195775632e-05,
|
1310 |
+
"loss": 0.8863,
|
1311 |
+
"step": 4650
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.4191697301174572,
|
1315 |
+
"grad_norm": 1.6563594872670169,
|
1316 |
+
"learning_rate": 1.2908239513798945e-05,
|
1317 |
+
"loss": 0.852,
|
1318 |
+
"step": 4675
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.4214112794763741,
|
1322 |
+
"grad_norm": 1.7048605228423215,
|
1323 |
+
"learning_rate": 1.2858423831822258e-05,
|
1324 |
+
"loss": 0.8649,
|
1325 |
+
"step": 4700
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.42365282883529093,
|
1329 |
+
"grad_norm": 1.625027526065513,
|
1330 |
+
"learning_rate": 1.2808608149845571e-05,
|
1331 |
+
"loss": 0.8658,
|
1332 |
+
"step": 4725
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.42589437819420783,
|
1336 |
+
"grad_norm": 1.918671896492615,
|
1337 |
+
"learning_rate": 1.2758792467868886e-05,
|
1338 |
+
"loss": 0.8478,
|
1339 |
+
"step": 4750
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.42813592755312474,
|
1343 |
+
"grad_norm": 1.7529097573536403,
|
1344 |
+
"learning_rate": 1.2708976785892199e-05,
|
1345 |
+
"loss": 0.8863,
|
1346 |
+
"step": 4775
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.4303774769120416,
|
1350 |
+
"grad_norm": 1.7580856057956353,
|
1351 |
+
"learning_rate": 1.2659161103915514e-05,
|
1352 |
+
"loss": 0.8543,
|
1353 |
+
"step": 4800
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.4326190262709585,
|
1357 |
+
"grad_norm": 1.7264754733728158,
|
1358 |
+
"learning_rate": 1.2609345421938828e-05,
|
1359 |
+
"loss": 0.88,
|
1360 |
+
"step": 4825
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.43486057562987535,
|
1364 |
+
"grad_norm": 1.6664400318355115,
|
1365 |
+
"learning_rate": 1.2559529739962142e-05,
|
1366 |
+
"loss": 0.865,
|
1367 |
+
"step": 4850
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.43710212498879225,
|
1371 |
+
"grad_norm": 1.5810013518562152,
|
1372 |
+
"learning_rate": 1.2509714057985456e-05,
|
1373 |
+
"loss": 0.8644,
|
1374 |
+
"step": 4875
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.43934367434770916,
|
1378 |
+
"grad_norm": 1.7637476166127988,
|
1379 |
+
"learning_rate": 1.2459898376008768e-05,
|
1380 |
+
"loss": 0.845,
|
1381 |
+
"step": 4900
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.441585223706626,
|
1385 |
+
"grad_norm": 1.7932279049924675,
|
1386 |
+
"learning_rate": 1.2410082694032082e-05,
|
1387 |
+
"loss": 0.8651,
|
1388 |
+
"step": 4925
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.4438267730655429,
|
1392 |
+
"grad_norm": 1.829561755443512,
|
1393 |
+
"learning_rate": 1.2360267012055395e-05,
|
1394 |
+
"loss": 0.8504,
|
1395 |
+
"step": 4950
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.44606832242445976,
|
1399 |
+
"grad_norm": 1.6188361315894273,
|
1400 |
+
"learning_rate": 1.231045133007871e-05,
|
1401 |
+
"loss": 0.8161,
|
1402 |
+
"step": 4975
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.44830987178337667,
|
1406 |
+
"grad_norm": 1.7056183046742297,
|
1407 |
+
"learning_rate": 1.2260635648102023e-05,
|
1408 |
+
"loss": 0.8591,
|
1409 |
+
"step": 5000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.4505514211422936,
|
1413 |
+
"grad_norm": 1.8841012895490568,
|
1414 |
+
"learning_rate": 1.2210819966125338e-05,
|
1415 |
+
"loss": 0.861,
|
1416 |
+
"step": 5025
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.4527929705012104,
|
1420 |
+
"grad_norm": 1.6238068299735378,
|
1421 |
+
"learning_rate": 1.2161004284148653e-05,
|
1422 |
+
"loss": 0.8575,
|
1423 |
+
"step": 5050
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.45503451986012733,
|
1427 |
+
"grad_norm": 1.8397094786253432,
|
1428 |
+
"learning_rate": 1.2111188602171964e-05,
|
1429 |
+
"loss": 0.8822,
|
1430 |
+
"step": 5075
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.4572760692190442,
|
1434 |
+
"grad_norm": 1.864241679602278,
|
1435 |
+
"learning_rate": 1.2061372920195279e-05,
|
1436 |
+
"loss": 0.8706,
|
1437 |
+
"step": 5100
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.4595176185779611,
|
1441 |
+
"grad_norm": 1.961344695482636,
|
1442 |
+
"learning_rate": 1.2011557238218592e-05,
|
1443 |
+
"loss": 0.8465,
|
1444 |
+
"step": 5125
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.461759167936878,
|
1448 |
+
"grad_norm": 1.7654809958600572,
|
1449 |
+
"learning_rate": 1.1961741556241906e-05,
|
1450 |
+
"loss": 0.8744,
|
1451 |
+
"step": 5150
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.46400071729579484,
|
1455 |
+
"grad_norm": 1.7238964433167303,
|
1456 |
+
"learning_rate": 1.191192587426522e-05,
|
1457 |
+
"loss": 0.8475,
|
1458 |
+
"step": 5175
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.46624226665471175,
|
1462 |
+
"grad_norm": 1.7695094943018663,
|
1463 |
+
"learning_rate": 1.1862110192288534e-05,
|
1464 |
+
"loss": 0.8193,
|
1465 |
+
"step": 5200
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.4684838160136286,
|
1469 |
+
"grad_norm": 1.8313450949005072,
|
1470 |
+
"learning_rate": 1.1812294510311847e-05,
|
1471 |
+
"loss": 0.8543,
|
1472 |
+
"step": 5225
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.4707253653725455,
|
1476 |
+
"grad_norm": 1.7242055485237682,
|
1477 |
+
"learning_rate": 1.176247882833516e-05,
|
1478 |
+
"loss": 0.8524,
|
1479 |
+
"step": 5250
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.4729669147314624,
|
1483 |
+
"grad_norm": 1.685334541109067,
|
1484 |
+
"learning_rate": 1.1712663146358473e-05,
|
1485 |
+
"loss": 0.8437,
|
1486 |
+
"step": 5275
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.47520846409037926,
|
1490 |
+
"grad_norm": 1.7482758279879385,
|
1491 |
+
"learning_rate": 1.1662847464381788e-05,
|
1492 |
+
"loss": 0.8305,
|
1493 |
+
"step": 5300
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.47745001344929616,
|
1497 |
+
"grad_norm": 3.4351483388103388,
|
1498 |
+
"learning_rate": 1.1613031782405103e-05,
|
1499 |
+
"loss": 0.853,
|
1500 |
+
"step": 5325
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.479691562808213,
|
1504 |
+
"grad_norm": 1.6345096360692302,
|
1505 |
+
"learning_rate": 1.1563216100428416e-05,
|
1506 |
+
"loss": 0.8328,
|
1507 |
+
"step": 5350
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.4819331121671299,
|
1511 |
+
"grad_norm": 1.8613988702465172,
|
1512 |
+
"learning_rate": 1.151340041845173e-05,
|
1513 |
+
"loss": 0.8475,
|
1514 |
+
"step": 5375
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.4841746615260468,
|
1518 |
+
"grad_norm": 1.7381762438125414,
|
1519 |
+
"learning_rate": 1.1463584736475044e-05,
|
1520 |
+
"loss": 0.8366,
|
1521 |
+
"step": 5400
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.4864162108849637,
|
1525 |
+
"grad_norm": 1.9220405850041657,
|
1526 |
+
"learning_rate": 1.1413769054498357e-05,
|
1527 |
+
"loss": 0.832,
|
1528 |
+
"step": 5425
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.4886577602438806,
|
1532 |
+
"grad_norm": 1.7762301237994864,
|
1533 |
+
"learning_rate": 1.136395337252167e-05,
|
1534 |
+
"loss": 0.8288,
|
1535 |
+
"step": 5450
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.49089930960279743,
|
1539 |
+
"grad_norm": 1.6336059312280666,
|
1540 |
+
"learning_rate": 1.1314137690544984e-05,
|
1541 |
+
"loss": 0.8428,
|
1542 |
+
"step": 5475
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.49314085896171433,
|
1546 |
+
"grad_norm": 1.7113743327911453,
|
1547 |
+
"learning_rate": 1.1264322008568297e-05,
|
1548 |
+
"loss": 0.8245,
|
1549 |
+
"step": 5500
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.49538240832063124,
|
1553 |
+
"grad_norm": 1.6955896520800513,
|
1554 |
+
"learning_rate": 1.1214506326591612e-05,
|
1555 |
+
"loss": 0.854,
|
1556 |
+
"step": 5525
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.4976239576795481,
|
1560 |
+
"grad_norm": 1.745123834536872,
|
1561 |
+
"learning_rate": 1.1164690644614927e-05,
|
1562 |
+
"loss": 0.8407,
|
1563 |
+
"step": 5550
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.499865507038465,
|
1567 |
+
"grad_norm": 1.7031285490401316,
|
1568 |
+
"learning_rate": 1.111487496263824e-05,
|
1569 |
+
"loss": 0.8407,
|
1570 |
+
"step": 5575
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.5021070563973818,
|
1574 |
+
"grad_norm": 1.6770089078383563,
|
1575 |
+
"learning_rate": 1.1065059280661555e-05,
|
1576 |
+
"loss": 0.8201,
|
1577 |
+
"step": 5600
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.5043486057562988,
|
1581 |
+
"grad_norm": 1.7307655888153608,
|
1582 |
+
"learning_rate": 1.1015243598684866e-05,
|
1583 |
+
"loss": 0.8338,
|
1584 |
+
"step": 5625
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.5065901551152157,
|
1588 |
+
"grad_norm": 1.8528909963261024,
|
1589 |
+
"learning_rate": 1.096542791670818e-05,
|
1590 |
+
"loss": 0.8307,
|
1591 |
+
"step": 5650
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.5088317044741325,
|
1595 |
+
"grad_norm": 1.8698755576150798,
|
1596 |
+
"learning_rate": 1.0915612234731494e-05,
|
1597 |
+
"loss": 0.8448,
|
1598 |
+
"step": 5675
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.5110732538330494,
|
1602 |
+
"grad_norm": 1.80016651013364,
|
1603 |
+
"learning_rate": 1.0865796552754808e-05,
|
1604 |
+
"loss": 0.8335,
|
1605 |
+
"step": 5700
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.5133148031919663,
|
1609 |
+
"grad_norm": 1.6573575321981893,
|
1610 |
+
"learning_rate": 1.0815980870778121e-05,
|
1611 |
+
"loss": 0.8406,
|
1612 |
+
"step": 5725
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.5155563525508832,
|
1616 |
+
"grad_norm": 1.8492211722078626,
|
1617 |
+
"learning_rate": 1.0766165188801436e-05,
|
1618 |
+
"loss": 0.8172,
|
1619 |
+
"step": 5750
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.5177979019098,
|
1623 |
+
"grad_norm": 1.6035391080567873,
|
1624 |
+
"learning_rate": 1.0716349506824751e-05,
|
1625 |
+
"loss": 0.8392,
|
1626 |
+
"step": 5775
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.520039451268717,
|
1630 |
+
"grad_norm": 1.8244861205863412,
|
1631 |
+
"learning_rate": 1.0666533824848062e-05,
|
1632 |
+
"loss": 0.8255,
|
1633 |
+
"step": 5800
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.5222810006276338,
|
1637 |
+
"grad_norm": 1.9845349836801902,
|
1638 |
+
"learning_rate": 1.0616718142871377e-05,
|
1639 |
+
"loss": 0.7773,
|
1640 |
+
"step": 5825
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.5245225499865507,
|
1644 |
+
"grad_norm": 1.6692235658845165,
|
1645 |
+
"learning_rate": 1.056690246089469e-05,
|
1646 |
+
"loss": 0.8204,
|
1647 |
+
"step": 5850
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.5267640993454676,
|
1651 |
+
"grad_norm": 1.77718790971494,
|
1652 |
+
"learning_rate": 1.0517086778918005e-05,
|
1653 |
+
"loss": 0.838,
|
1654 |
+
"step": 5875
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.5290056487043845,
|
1658 |
+
"grad_norm": 2.216535651554211,
|
1659 |
+
"learning_rate": 1.0467271096941318e-05,
|
1660 |
+
"loss": 0.8032,
|
1661 |
+
"step": 5900
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.5312471980633013,
|
1665 |
+
"grad_norm": 1.51672462878331,
|
1666 |
+
"learning_rate": 1.0417455414964633e-05,
|
1667 |
+
"loss": 0.8134,
|
1668 |
+
"step": 5925
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.5334887474222182,
|
1672 |
+
"grad_norm": 1.5842154935520327,
|
1673 |
+
"learning_rate": 1.0367639732987946e-05,
|
1674 |
+
"loss": 0.8156,
|
1675 |
+
"step": 5950
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.5357302967811352,
|
1679 |
+
"grad_norm": 1.8084527777329682,
|
1680 |
+
"learning_rate": 1.0317824051011259e-05,
|
1681 |
+
"loss": 0.8044,
|
1682 |
+
"step": 5975
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.537971846140052,
|
1686 |
+
"grad_norm": 1.8279664094537542,
|
1687 |
+
"learning_rate": 1.0268008369034572e-05,
|
1688 |
+
"loss": 0.8221,
|
1689 |
+
"step": 6000
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.5402133954989689,
|
1693 |
+
"grad_norm": 1.8246484550571145,
|
1694 |
+
"learning_rate": 1.0218192687057886e-05,
|
1695 |
+
"loss": 0.8113,
|
1696 |
+
"step": 6025
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.5424549448578858,
|
1700 |
+
"grad_norm": 1.9794225799144154,
|
1701 |
+
"learning_rate": 1.0168377005081201e-05,
|
1702 |
+
"loss": 0.8297,
|
1703 |
+
"step": 6050
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.5446964942168027,
|
1707 |
+
"grad_norm": 1.8107096798923765,
|
1708 |
+
"learning_rate": 1.0118561323104514e-05,
|
1709 |
+
"loss": 0.7963,
|
1710 |
+
"step": 6075
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.5469380435757195,
|
1714 |
+
"grad_norm": 1.7381439602233606,
|
1715 |
+
"learning_rate": 1.0068745641127829e-05,
|
1716 |
+
"loss": 0.8292,
|
1717 |
+
"step": 6100
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.5491795929346365,
|
1721 |
+
"grad_norm": 1.7511199022521768,
|
1722 |
+
"learning_rate": 1.0018929959151142e-05,
|
1723 |
+
"loss": 0.7881,
|
1724 |
+
"step": 6125
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.5514211422935533,
|
1728 |
+
"grad_norm": 1.8540296738093,
|
1729 |
+
"learning_rate": 9.969114277174455e-06,
|
1730 |
+
"loss": 0.819,
|
1731 |
+
"step": 6150
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.5536626916524702,
|
1735 |
+
"grad_norm": 1.604616094415389,
|
1736 |
+
"learning_rate": 9.91929859519777e-06,
|
1737 |
+
"loss": 0.8149,
|
1738 |
+
"step": 6175
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.555904241011387,
|
1742 |
+
"grad_norm": 1.7889735212307019,
|
1743 |
+
"learning_rate": 9.869482913221083e-06,
|
1744 |
+
"loss": 0.8174,
|
1745 |
+
"step": 6200
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.558145790370304,
|
1749 |
+
"grad_norm": 1.7124938531820217,
|
1750 |
+
"learning_rate": 9.819667231244396e-06,
|
1751 |
+
"loss": 0.8282,
|
1752 |
+
"step": 6225
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.5603873397292208,
|
1756 |
+
"grad_norm": 1.7697417082932925,
|
1757 |
+
"learning_rate": 9.76985154926771e-06,
|
1758 |
+
"loss": 0.8112,
|
1759 |
+
"step": 6250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.5626288890881377,
|
1763 |
+
"grad_norm": 1.7720332425978838,
|
1764 |
+
"learning_rate": 9.720035867291025e-06,
|
1765 |
+
"loss": 0.8256,
|
1766 |
+
"step": 6275
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.5648704384470546,
|
1770 |
+
"grad_norm": 1.7791860279019227,
|
1771 |
+
"learning_rate": 9.670220185314338e-06,
|
1772 |
+
"loss": 0.7993,
|
1773 |
+
"step": 6300
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.5671119878059715,
|
1777 |
+
"grad_norm": 1.8298443186416975,
|
1778 |
+
"learning_rate": 9.620404503337651e-06,
|
1779 |
+
"loss": 0.8074,
|
1780 |
+
"step": 6325
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 0.5693535371648883,
|
1784 |
+
"grad_norm": 1.740618137225464,
|
1785 |
+
"learning_rate": 9.570588821360966e-06,
|
1786 |
+
"loss": 0.7915,
|
1787 |
+
"step": 6350
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 0.5715950865238053,
|
1791 |
+
"grad_norm": 1.6575823203829687,
|
1792 |
+
"learning_rate": 9.520773139384279e-06,
|
1793 |
+
"loss": 0.8061,
|
1794 |
+
"step": 6375
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.5738366358827222,
|
1798 |
+
"grad_norm": 1.594956412545229,
|
1799 |
+
"learning_rate": 9.470957457407592e-06,
|
1800 |
+
"loss": 0.7835,
|
1801 |
+
"step": 6400
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.576078185241639,
|
1805 |
+
"grad_norm": 1.7061113242845711,
|
1806 |
+
"learning_rate": 9.421141775430907e-06,
|
1807 |
+
"loss": 0.7786,
|
1808 |
+
"step": 6425
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.5783197346005559,
|
1812 |
+
"grad_norm": 1.7037561820889011,
|
1813 |
+
"learning_rate": 9.37132609345422e-06,
|
1814 |
+
"loss": 0.7847,
|
1815 |
+
"step": 6450
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.5805612839594728,
|
1819 |
+
"grad_norm": 1.6215842870197699,
|
1820 |
+
"learning_rate": 9.321510411477533e-06,
|
1821 |
+
"loss": 0.8216,
|
1822 |
+
"step": 6475
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 0.5828028333183897,
|
1826 |
+
"grad_norm": 1.7215498826410882,
|
1827 |
+
"learning_rate": 9.271694729500848e-06,
|
1828 |
+
"loss": 0.7908,
|
1829 |
+
"step": 6500
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 0.5850443826773065,
|
1833 |
+
"grad_norm": 1.6190690905298566,
|
1834 |
+
"learning_rate": 9.221879047524162e-06,
|
1835 |
+
"loss": 0.7975,
|
1836 |
+
"step": 6525
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 0.5872859320362235,
|
1840 |
+
"grad_norm": 1.7359669159042928,
|
1841 |
+
"learning_rate": 9.172063365547475e-06,
|
1842 |
+
"loss": 0.8038,
|
1843 |
+
"step": 6550
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.5895274813951403,
|
1847 |
+
"grad_norm": 1.6569209888458083,
|
1848 |
+
"learning_rate": 9.122247683570788e-06,
|
1849 |
+
"loss": 0.7865,
|
1850 |
+
"step": 6575
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 0.5917690307540572,
|
1854 |
+
"grad_norm": 1.7468326887043915,
|
1855 |
+
"learning_rate": 9.072432001594103e-06,
|
1856 |
+
"loss": 0.7945,
|
1857 |
+
"step": 6600
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.5940105801129741,
|
1861 |
+
"grad_norm": 1.89027859669638,
|
1862 |
+
"learning_rate": 9.022616319617416e-06,
|
1863 |
+
"loss": 0.7945,
|
1864 |
+
"step": 6625
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 0.596252129471891,
|
1868 |
+
"grad_norm": 3.1956433500954846,
|
1869 |
+
"learning_rate": 8.972800637640729e-06,
|
1870 |
+
"loss": 0.7832,
|
1871 |
+
"step": 6650
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.5984936788308078,
|
1875 |
+
"grad_norm": 1.6708308695139495,
|
1876 |
+
"learning_rate": 8.922984955664044e-06,
|
1877 |
+
"loss": 0.7804,
|
1878 |
+
"step": 6675
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 0.6007352281897247,
|
1882 |
+
"grad_norm": 1.6619509622184405,
|
1883 |
+
"learning_rate": 8.873169273687357e-06,
|
1884 |
+
"loss": 0.7736,
|
1885 |
+
"step": 6700
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 0.6029767775486417,
|
1889 |
+
"grad_norm": 1.703044857731027,
|
1890 |
+
"learning_rate": 8.823353591710672e-06,
|
1891 |
+
"loss": 0.7803,
|
1892 |
+
"step": 6725
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 0.6052183269075585,
|
1896 |
+
"grad_norm": 1.690170724872845,
|
1897 |
+
"learning_rate": 8.773537909733985e-06,
|
1898 |
+
"loss": 0.7739,
|
1899 |
+
"step": 6750
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.6074598762664754,
|
1903 |
+
"grad_norm": 1.792403817902017,
|
1904 |
+
"learning_rate": 8.7237222277573e-06,
|
1905 |
+
"loss": 0.8006,
|
1906 |
+
"step": 6775
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 0.6097014256253923,
|
1910 |
+
"grad_norm": 1.6433093780482904,
|
1911 |
+
"learning_rate": 8.673906545780612e-06,
|
1912 |
+
"loss": 0.7867,
|
1913 |
+
"step": 6800
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 0.6119429749843092,
|
1917 |
+
"grad_norm": 1.790404324898307,
|
1918 |
+
"learning_rate": 8.624090863803927e-06,
|
1919 |
+
"loss": 0.7849,
|
1920 |
+
"step": 6825
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 0.614184524343226,
|
1924 |
+
"grad_norm": 1.6454337492340885,
|
1925 |
+
"learning_rate": 8.57427518182724e-06,
|
1926 |
+
"loss": 0.7879,
|
1927 |
+
"step": 6850
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 0.616426073702143,
|
1931 |
+
"grad_norm": 1.7355887161904928,
|
1932 |
+
"learning_rate": 8.524459499850553e-06,
|
1933 |
+
"loss": 0.7768,
|
1934 |
+
"step": 6875
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 0.6186676230610598,
|
1938 |
+
"grad_norm": 1.7882226224444007,
|
1939 |
+
"learning_rate": 8.474643817873868e-06,
|
1940 |
+
"loss": 0.7994,
|
1941 |
+
"step": 6900
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.6209091724199767,
|
1945 |
+
"grad_norm": 1.6311627761596097,
|
1946 |
+
"learning_rate": 8.424828135897181e-06,
|
1947 |
+
"loss": 0.778,
|
1948 |
+
"step": 6925
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 0.6231507217788935,
|
1952 |
+
"grad_norm": 1.8193761919911795,
|
1953 |
+
"learning_rate": 8.375012453920494e-06,
|
1954 |
+
"loss": 0.8019,
|
1955 |
+
"step": 6950
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 0.6253922711378105,
|
1959 |
+
"grad_norm": 1.837184984077742,
|
1960 |
+
"learning_rate": 8.325196771943809e-06,
|
1961 |
+
"loss": 0.788,
|
1962 |
+
"step": 6975
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 0.6276338204967273,
|
1966 |
+
"grad_norm": 1.7295194630868602,
|
1967 |
+
"learning_rate": 8.275381089967123e-06,
|
1968 |
+
"loss": 0.79,
|
1969 |
+
"step": 7000
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 0.6298753698556442,
|
1973 |
+
"grad_norm": 1.7138938284046155,
|
1974 |
+
"learning_rate": 8.225565407990437e-06,
|
1975 |
+
"loss": 0.8014,
|
1976 |
+
"step": 7025
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 0.6321169192145611,
|
1980 |
+
"grad_norm": 1.761547883189452,
|
1981 |
+
"learning_rate": 8.17574972601375e-06,
|
1982 |
+
"loss": 0.7667,
|
1983 |
+
"step": 7050
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.634358468573478,
|
1987 |
+
"grad_norm": 1.733008722282232,
|
1988 |
+
"learning_rate": 8.125934044037064e-06,
|
1989 |
+
"loss": 0.7932,
|
1990 |
+
"step": 7075
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 0.6366000179323948,
|
1994 |
+
"grad_norm": 4.166995261072046,
|
1995 |
+
"learning_rate": 8.076118362060377e-06,
|
1996 |
+
"loss": 0.8139,
|
1997 |
+
"step": 7100
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 0.6388415672913118,
|
2001 |
+
"grad_norm": 2.775575951767444,
|
2002 |
+
"learning_rate": 8.02630268008369e-06,
|
2003 |
+
"loss": 0.8398,
|
2004 |
+
"step": 7125
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 0.6410831166502287,
|
2008 |
+
"grad_norm": 1.866468516722052,
|
2009 |
+
"learning_rate": 7.976486998107005e-06,
|
2010 |
+
"loss": 0.7846,
|
2011 |
+
"step": 7150
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.6433246660091455,
|
2015 |
+
"grad_norm": 1.7569056138933221,
|
2016 |
+
"learning_rate": 7.926671316130318e-06,
|
2017 |
+
"loss": 0.7579,
|
2018 |
+
"step": 7175
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 0.6455662153680624,
|
2022 |
+
"grad_norm": 1.7346922018694015,
|
2023 |
+
"learning_rate": 7.876855634153631e-06,
|
2024 |
+
"loss": 0.7668,
|
2025 |
+
"step": 7200
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.6478077647269793,
|
2029 |
+
"grad_norm": 1.702125683289223,
|
2030 |
+
"learning_rate": 7.827039952176946e-06,
|
2031 |
+
"loss": 0.7696,
|
2032 |
+
"step": 7225
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 0.6500493140858962,
|
2036 |
+
"grad_norm": 1.7917713066235164,
|
2037 |
+
"learning_rate": 7.77722427020026e-06,
|
2038 |
+
"loss": 0.7664,
|
2039 |
+
"step": 7250
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 0.652290863444813,
|
2043 |
+
"grad_norm": 1.6937229241150964,
|
2044 |
+
"learning_rate": 7.727408588223574e-06,
|
2045 |
+
"loss": 0.7515,
|
2046 |
+
"step": 7275
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 0.65453241280373,
|
2050 |
+
"grad_norm": 1.7775884772395607,
|
2051 |
+
"learning_rate": 7.677592906246887e-06,
|
2052 |
+
"loss": 0.767,
|
2053 |
+
"step": 7300
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 0.6567739621626468,
|
2057 |
+
"grad_norm": 1.7226500388022883,
|
2058 |
+
"learning_rate": 7.6277772242702006e-06,
|
2059 |
+
"loss": 0.7676,
|
2060 |
+
"step": 7325
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 0.6590155115215637,
|
2064 |
+
"grad_norm": 1.738366084601186,
|
2065 |
+
"learning_rate": 7.577961542293515e-06,
|
2066 |
+
"loss": 0.7796,
|
2067 |
+
"step": 7350
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.6612570608804806,
|
2071 |
+
"grad_norm": 1.659677524471436,
|
2072 |
+
"learning_rate": 7.5281458603168275e-06,
|
2073 |
+
"loss": 0.7543,
|
2074 |
+
"step": 7375
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 0.6634986102393975,
|
2078 |
+
"grad_norm": 1.7220186075774808,
|
2079 |
+
"learning_rate": 7.478330178340142e-06,
|
2080 |
+
"loss": 0.7918,
|
2081 |
+
"step": 7400
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 0.6657401595983143,
|
2085 |
+
"grad_norm": 1.7274393080929407,
|
2086 |
+
"learning_rate": 7.428514496363456e-06,
|
2087 |
+
"loss": 0.7882,
|
2088 |
+
"step": 7425
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 0.6679817089572312,
|
2092 |
+
"grad_norm": 1.8016655237128902,
|
2093 |
+
"learning_rate": 7.37869881438677e-06,
|
2094 |
+
"loss": 0.7889,
|
2095 |
+
"step": 7450
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 0.6702232583161482,
|
2099 |
+
"grad_norm": 1.9514224447470465,
|
2100 |
+
"learning_rate": 7.328883132410083e-06,
|
2101 |
+
"loss": 0.7772,
|
2102 |
+
"step": 7475
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 0.672464807675065,
|
2106 |
+
"grad_norm": 1.6866541471123346,
|
2107 |
+
"learning_rate": 7.279067450433397e-06,
|
2108 |
+
"loss": 0.7537,
|
2109 |
+
"step": 7500
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.6747063570339819,
|
2113 |
+
"grad_norm": 1.5995131098013584,
|
2114 |
+
"learning_rate": 7.229251768456711e-06,
|
2115 |
+
"loss": 0.741,
|
2116 |
+
"step": 7525
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 0.6769479063928988,
|
2120 |
+
"grad_norm": 1.7025523689523283,
|
2121 |
+
"learning_rate": 7.179436086480025e-06,
|
2122 |
+
"loss": 0.7558,
|
2123 |
+
"step": 7550
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 0.6791894557518157,
|
2127 |
+
"grad_norm": 2.0095499267364745,
|
2128 |
+
"learning_rate": 7.129620404503338e-06,
|
2129 |
+
"loss": 0.757,
|
2130 |
+
"step": 7575
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 0.6814310051107325,
|
2134 |
+
"grad_norm": 1.7992263340730072,
|
2135 |
+
"learning_rate": 7.0798047225266516e-06,
|
2136 |
+
"loss": 0.7636,
|
2137 |
+
"step": 7600
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 0.6836725544696495,
|
2141 |
+
"grad_norm": 1.7559061906827926,
|
2142 |
+
"learning_rate": 7.029989040549966e-06,
|
2143 |
+
"loss": 0.778,
|
2144 |
+
"step": 7625
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 0.6859141038285663,
|
2148 |
+
"grad_norm": 1.956755336390013,
|
2149 |
+
"learning_rate": 6.980173358573279e-06,
|
2150 |
+
"loss": 0.7683,
|
2151 |
+
"step": 7650
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.6881556531874832,
|
2155 |
+
"grad_norm": 1.7448110825187608,
|
2156 |
+
"learning_rate": 6.930357676596593e-06,
|
2157 |
+
"loss": 0.7751,
|
2158 |
+
"step": 7675
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 0.6903972025464,
|
2162 |
+
"grad_norm": 1.6670481706384996,
|
2163 |
+
"learning_rate": 6.880541994619907e-06,
|
2164 |
+
"loss": 0.7628,
|
2165 |
+
"step": 7700
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 0.692638751905317,
|
2169 |
+
"grad_norm": 1.7735206213020065,
|
2170 |
+
"learning_rate": 6.830726312643221e-06,
|
2171 |
+
"loss": 0.7667,
|
2172 |
+
"step": 7725
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 0.6948803012642338,
|
2176 |
+
"grad_norm": 1.6570338157726383,
|
2177 |
+
"learning_rate": 6.780910630666534e-06,
|
2178 |
+
"loss": 0.7373,
|
2179 |
+
"step": 7750
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 0.6971218506231507,
|
2183 |
+
"grad_norm": 1.8540028960496349,
|
2184 |
+
"learning_rate": 6.731094948689848e-06,
|
2185 |
+
"loss": 0.7319,
|
2186 |
+
"step": 7775
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 0.6993633999820676,
|
2190 |
+
"grad_norm": 1.6857468789586427,
|
2191 |
+
"learning_rate": 6.681279266713162e-06,
|
2192 |
+
"loss": 0.7632,
|
2193 |
+
"step": 7800
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.7016049493409845,
|
2197 |
+
"grad_norm": 1.6890850810078746,
|
2198 |
+
"learning_rate": 6.6314635847364765e-06,
|
2199 |
+
"loss": 0.7749,
|
2200 |
+
"step": 7825
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 0.7038464986999013,
|
2204 |
+
"grad_norm": 1.924422917379529,
|
2205 |
+
"learning_rate": 6.581647902759789e-06,
|
2206 |
+
"loss": 0.7583,
|
2207 |
+
"step": 7850
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 0.7060880480588183,
|
2211 |
+
"grad_norm": 1.630090078651694,
|
2212 |
+
"learning_rate": 6.531832220783103e-06,
|
2213 |
+
"loss": 0.7631,
|
2214 |
+
"step": 7875
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.7083295974177352,
|
2218 |
+
"grad_norm": 2.0468696598695804,
|
2219 |
+
"learning_rate": 6.482016538806417e-06,
|
2220 |
+
"loss": 0.7353,
|
2221 |
+
"step": 7900
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 0.710571146776652,
|
2225 |
+
"grad_norm": 1.8259752815108847,
|
2226 |
+
"learning_rate": 6.43220085682973e-06,
|
2227 |
+
"loss": 0.7549,
|
2228 |
+
"step": 7925
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.7128126961355689,
|
2232 |
+
"grad_norm": 1.9661073390983392,
|
2233 |
+
"learning_rate": 6.382385174853044e-06,
|
2234 |
+
"loss": 0.7387,
|
2235 |
+
"step": 7950
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.7150542454944858,
|
2239 |
+
"grad_norm": 1.8203344976450027,
|
2240 |
+
"learning_rate": 6.332569492876358e-06,
|
2241 |
+
"loss": 0.7503,
|
2242 |
+
"step": 7975
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 0.7172957948534027,
|
2246 |
+
"grad_norm": 1.6706387021687052,
|
2247 |
+
"learning_rate": 6.282753810899672e-06,
|
2248 |
+
"loss": 0.7547,
|
2249 |
+
"step": 8000
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 0.7195373442123195,
|
2253 |
+
"grad_norm": 1.6604842538698719,
|
2254 |
+
"learning_rate": 6.232938128922985e-06,
|
2255 |
+
"loss": 0.7572,
|
2256 |
+
"step": 8025
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 0.7217788935712365,
|
2260 |
+
"grad_norm": 1.6447415350716448,
|
2261 |
+
"learning_rate": 6.183122446946299e-06,
|
2262 |
+
"loss": 0.7296,
|
2263 |
+
"step": 8050
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 0.7240204429301533,
|
2267 |
+
"grad_norm": 1.9020553686330788,
|
2268 |
+
"learning_rate": 6.133306764969613e-06,
|
2269 |
+
"loss": 0.7487,
|
2270 |
+
"step": 8075
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 0.7262619922890702,
|
2274 |
+
"grad_norm": 1.8432810146288983,
|
2275 |
+
"learning_rate": 6.083491082992926e-06,
|
2276 |
+
"loss": 0.7536,
|
2277 |
+
"step": 8100
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.7285035416479871,
|
2281 |
+
"grad_norm": 1.6720677963590904,
|
2282 |
+
"learning_rate": 6.0336754010162405e-06,
|
2283 |
+
"loss": 0.7503,
|
2284 |
+
"step": 8125
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 0.730745091006904,
|
2288 |
+
"grad_norm": 1.6924073549958094,
|
2289 |
+
"learning_rate": 5.983859719039554e-06,
|
2290 |
+
"loss": 0.7311,
|
2291 |
+
"step": 8150
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 0.7329866403658208,
|
2295 |
+
"grad_norm": 1.7039808290333063,
|
2296 |
+
"learning_rate": 5.934044037062868e-06,
|
2297 |
+
"loss": 0.7328,
|
2298 |
+
"step": 8175
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 0.7352281897247377,
|
2302 |
+
"grad_norm": 1.8427531227740936,
|
2303 |
+
"learning_rate": 5.884228355086181e-06,
|
2304 |
+
"loss": 0.7425,
|
2305 |
+
"step": 8200
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 0.7374697390836547,
|
2309 |
+
"grad_norm": 1.7942833275137888,
|
2310 |
+
"learning_rate": 5.834412673109495e-06,
|
2311 |
+
"loss": 0.7267,
|
2312 |
+
"step": 8225
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 0.7397112884425715,
|
2316 |
+
"grad_norm": 1.7022537282468946,
|
2317 |
+
"learning_rate": 5.784596991132809e-06,
|
2318 |
+
"loss": 0.7272,
|
2319 |
+
"step": 8250
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.7419528378014884,
|
2323 |
+
"grad_norm": 1.7117727723387872,
|
2324 |
+
"learning_rate": 5.734781309156123e-06,
|
2325 |
+
"loss": 0.7406,
|
2326 |
+
"step": 8275
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 0.7441943871604053,
|
2330 |
+
"grad_norm": 1.6662930795240602,
|
2331 |
+
"learning_rate": 5.684965627179436e-06,
|
2332 |
+
"loss": 0.7144,
|
2333 |
+
"step": 8300
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 0.7464359365193222,
|
2337 |
+
"grad_norm": 1.7271646882114742,
|
2338 |
+
"learning_rate": 5.63514994520275e-06,
|
2339 |
+
"loss": 0.7194,
|
2340 |
+
"step": 8325
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 0.748677485878239,
|
2344 |
+
"grad_norm": 1.7848763942941896,
|
2345 |
+
"learning_rate": 5.585334263226065e-06,
|
2346 |
+
"loss": 0.746,
|
2347 |
+
"step": 8350
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 0.750919035237156,
|
2351 |
+
"grad_norm": 1.8023379110361575,
|
2352 |
+
"learning_rate": 5.535518581249378e-06,
|
2353 |
+
"loss": 0.7626,
|
2354 |
+
"step": 8375
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 0.7531605845960728,
|
2358 |
+
"grad_norm": 1.912633778788871,
|
2359 |
+
"learning_rate": 5.4857028992726915e-06,
|
2360 |
+
"loss": 0.742,
|
2361 |
+
"step": 8400
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 0.7554021339549897,
|
2365 |
+
"grad_norm": 1.7489417073434457,
|
2366 |
+
"learning_rate": 5.4358872172960054e-06,
|
2367 |
+
"loss": 0.7235,
|
2368 |
+
"step": 8425
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 0.7576436833139065,
|
2372 |
+
"grad_norm": 1.8578170309164246,
|
2373 |
+
"learning_rate": 5.386071535319319e-06,
|
2374 |
+
"loss": 0.7406,
|
2375 |
+
"step": 8450
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 0.7598852326728235,
|
2379 |
+
"grad_norm": 1.6841301357346117,
|
2380 |
+
"learning_rate": 5.336255853342632e-06,
|
2381 |
+
"loss": 0.7265,
|
2382 |
+
"step": 8475
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 0.7621267820317403,
|
2386 |
+
"grad_norm": 1.67637322338657,
|
2387 |
+
"learning_rate": 5.286440171365946e-06,
|
2388 |
+
"loss": 0.7298,
|
2389 |
+
"step": 8500
|
2390 |
+
},
|
2391 |
+
{
|
2392 |
+
"epoch": 0.7643683313906572,
|
2393 |
+
"grad_norm": 2.75057542787619,
|
2394 |
+
"learning_rate": 5.23662448938926e-06,
|
2395 |
+
"loss": 0.7403,
|
2396 |
+
"step": 8525
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 0.7666098807495741,
|
2400 |
+
"grad_norm": 1.9562182621837296,
|
2401 |
+
"learning_rate": 5.186808807412575e-06,
|
2402 |
+
"loss": 0.7357,
|
2403 |
+
"step": 8550
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 0.768851430108491,
|
2407 |
+
"grad_norm": 1.6178018797694105,
|
2408 |
+
"learning_rate": 5.136993125435887e-06,
|
2409 |
+
"loss": 0.7204,
|
2410 |
+
"step": 8575
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 0.7710929794674078,
|
2414 |
+
"grad_norm": 1.7743524698802162,
|
2415 |
+
"learning_rate": 5.087177443459202e-06,
|
2416 |
+
"loss": 0.7184,
|
2417 |
+
"step": 8600
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 0.7733345288263248,
|
2421 |
+
"grad_norm": 1.7898971028849646,
|
2422 |
+
"learning_rate": 5.037361761482516e-06,
|
2423 |
+
"loss": 0.7175,
|
2424 |
+
"step": 8625
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 0.7755760781852417,
|
2428 |
+
"grad_norm": 1.6656106823591226,
|
2429 |
+
"learning_rate": 4.987546079505829e-06,
|
2430 |
+
"loss": 0.7321,
|
2431 |
+
"step": 8650
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 0.7778176275441585,
|
2435 |
+
"grad_norm": 1.7374976494979955,
|
2436 |
+
"learning_rate": 4.9377303975291425e-06,
|
2437 |
+
"loss": 0.7143,
|
2438 |
+
"step": 8675
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 0.7800591769030754,
|
2442 |
+
"grad_norm": 1.7005970489827344,
|
2443 |
+
"learning_rate": 4.8879147155524564e-06,
|
2444 |
+
"loss": 0.7192,
|
2445 |
+
"step": 8700
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 0.7823007262619923,
|
2449 |
+
"grad_norm": 1.9487288387163249,
|
2450 |
+
"learning_rate": 4.83809903357577e-06,
|
2451 |
+
"loss": 0.7316,
|
2452 |
+
"step": 8725
|
2453 |
+
},
|
2454 |
+
{
|
2455 |
+
"epoch": 0.7845422756209092,
|
2456 |
+
"grad_norm": 1.925164538441118,
|
2457 |
+
"learning_rate": 4.788283351599084e-06,
|
2458 |
+
"loss": 0.7168,
|
2459 |
+
"step": 8750
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 0.786783824979826,
|
2463 |
+
"grad_norm": 1.8020535072536237,
|
2464 |
+
"learning_rate": 4.738467669622397e-06,
|
2465 |
+
"loss": 0.717,
|
2466 |
+
"step": 8775
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 0.789025374338743,
|
2470 |
+
"grad_norm": 1.7020258141919171,
|
2471 |
+
"learning_rate": 4.688651987645711e-06,
|
2472 |
+
"loss": 0.705,
|
2473 |
+
"step": 8800
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 0.7912669236976598,
|
2477 |
+
"grad_norm": 1.7601750027580583,
|
2478 |
+
"learning_rate": 4.638836305669025e-06,
|
2479 |
+
"loss": 0.7182,
|
2480 |
+
"step": 8825
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 0.7935084730565767,
|
2484 |
+
"grad_norm": 1.846265294881566,
|
2485 |
+
"learning_rate": 4.589020623692339e-06,
|
2486 |
+
"loss": 0.7201,
|
2487 |
+
"step": 8850
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 0.7957500224154936,
|
2491 |
+
"grad_norm": 1.923703748637079,
|
2492 |
+
"learning_rate": 4.539204941715653e-06,
|
2493 |
+
"loss": 0.7197,
|
2494 |
+
"step": 8875
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 0.7979915717744105,
|
2498 |
+
"grad_norm": 1.8056553901529664,
|
2499 |
+
"learning_rate": 4.489389259738966e-06,
|
2500 |
+
"loss": 0.7285,
|
2501 |
+
"step": 8900
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 0.8002331211333273,
|
2505 |
+
"grad_norm": 1.795629570041314,
|
2506 |
+
"learning_rate": 4.43957357776228e-06,
|
2507 |
+
"loss": 0.7163,
|
2508 |
+
"step": 8925
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 0.8024746704922442,
|
2512 |
+
"grad_norm": 1.5666589265984843,
|
2513 |
+
"learning_rate": 4.3897578957855936e-06,
|
2514 |
+
"loss": 0.7275,
|
2515 |
+
"step": 8950
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 0.8047162198511612,
|
2519 |
+
"grad_norm": 1.6549818049918694,
|
2520 |
+
"learning_rate": 4.3399422138089074e-06,
|
2521 |
+
"loss": 0.7039,
|
2522 |
+
"step": 8975
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 0.806957769210078,
|
2526 |
+
"grad_norm": 1.7814051375647009,
|
2527 |
+
"learning_rate": 4.290126531832221e-06,
|
2528 |
+
"loss": 0.7227,
|
2529 |
+
"step": 9000
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.8091993185689949,
|
2533 |
+
"grad_norm": 1.7898138695626653,
|
2534 |
+
"learning_rate": 4.240310849855535e-06,
|
2535 |
+
"loss": 0.7079,
|
2536 |
+
"step": 9025
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 0.8114408679279118,
|
2540 |
+
"grad_norm": 1.515676572777515,
|
2541 |
+
"learning_rate": 4.190495167878848e-06,
|
2542 |
+
"loss": 0.7045,
|
2543 |
+
"step": 9050
|
2544 |
+
},
|
2545 |
+
{
|
2546 |
+
"epoch": 0.8136824172868287,
|
2547 |
+
"grad_norm": 1.898283603072741,
|
2548 |
+
"learning_rate": 4.140679485902162e-06,
|
2549 |
+
"loss": 0.7,
|
2550 |
+
"step": 9075
|
2551 |
+
},
|
2552 |
+
{
|
2553 |
+
"epoch": 0.8159239666457455,
|
2554 |
+
"grad_norm": 1.7281337925852416,
|
2555 |
+
"learning_rate": 4.090863803925476e-06,
|
2556 |
+
"loss": 0.7286,
|
2557 |
+
"step": 9100
|
2558 |
+
},
|
2559 |
+
{
|
2560 |
+
"epoch": 0.8181655160046625,
|
2561 |
+
"grad_norm": 1.8301510420483158,
|
2562 |
+
"learning_rate": 4.04104812194879e-06,
|
2563 |
+
"loss": 0.7238,
|
2564 |
+
"step": 9125
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 0.8204070653635793,
|
2568 |
+
"grad_norm": 1.784168091420267,
|
2569 |
+
"learning_rate": 3.991232439972104e-06,
|
2570 |
+
"loss": 0.7141,
|
2571 |
+
"step": 9150
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 0.8226486147224962,
|
2575 |
+
"grad_norm": 1.7711618071268116,
|
2576 |
+
"learning_rate": 3.941416757995417e-06,
|
2577 |
+
"loss": 0.705,
|
2578 |
+
"step": 9175
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 0.824890164081413,
|
2582 |
+
"grad_norm": 1.7943262394506765,
|
2583 |
+
"learning_rate": 3.8916010760187315e-06,
|
2584 |
+
"loss": 0.6912,
|
2585 |
+
"step": 9200
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 0.82713171344033,
|
2589 |
+
"grad_norm": 1.7222088978012928,
|
2590 |
+
"learning_rate": 3.8417853940420446e-06,
|
2591 |
+
"loss": 0.7113,
|
2592 |
+
"step": 9225
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 0.8293732627992468,
|
2596 |
+
"grad_norm": 1.7435568457969255,
|
2597 |
+
"learning_rate": 3.791969712065359e-06,
|
2598 |
+
"loss": 0.7057,
|
2599 |
+
"step": 9250
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 0.8316148121581637,
|
2603 |
+
"grad_norm": 1.6373991331602138,
|
2604 |
+
"learning_rate": 3.7421540300886723e-06,
|
2605 |
+
"loss": 0.7125,
|
2606 |
+
"step": 9275
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 0.8338563615170806,
|
2610 |
+
"grad_norm": 1.9154506347265303,
|
2611 |
+
"learning_rate": 3.692338348111986e-06,
|
2612 |
+
"loss": 0.7061,
|
2613 |
+
"step": 9300
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 0.8360979108759975,
|
2617 |
+
"grad_norm": 1.6555518537057525,
|
2618 |
+
"learning_rate": 3.6425226661352997e-06,
|
2619 |
+
"loss": 0.7067,
|
2620 |
+
"step": 9325
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 0.8383394602349143,
|
2624 |
+
"grad_norm": 1.6884565793905875,
|
2625 |
+
"learning_rate": 3.592706984158613e-06,
|
2626 |
+
"loss": 0.6977,
|
2627 |
+
"step": 9350
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 0.8405810095938313,
|
2631 |
+
"grad_norm": 1.840174884218591,
|
2632 |
+
"learning_rate": 3.5428913021819274e-06,
|
2633 |
+
"loss": 0.705,
|
2634 |
+
"step": 9375
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 0.8428225589527482,
|
2638 |
+
"grad_norm": 1.7593245437402398,
|
2639 |
+
"learning_rate": 3.493075620205241e-06,
|
2640 |
+
"loss": 0.7009,
|
2641 |
+
"step": 9400
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 0.845064108311665,
|
2645 |
+
"grad_norm": 1.758774652432913,
|
2646 |
+
"learning_rate": 3.4432599382285548e-06,
|
2647 |
+
"loss": 0.7098,
|
2648 |
+
"step": 9425
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 0.8473056576705819,
|
2652 |
+
"grad_norm": 2.005892733446428,
|
2653 |
+
"learning_rate": 3.3934442562518682e-06,
|
2654 |
+
"loss": 0.6976,
|
2655 |
+
"step": 9450
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 0.8495472070294988,
|
2659 |
+
"grad_norm": 1.9488435196357063,
|
2660 |
+
"learning_rate": 3.343628574275182e-06,
|
2661 |
+
"loss": 0.6847,
|
2662 |
+
"step": 9475
|
2663 |
+
},
|
2664 |
+
{
|
2665 |
+
"epoch": 0.8517887563884157,
|
2666 |
+
"grad_norm": 1.6521048790538413,
|
2667 |
+
"learning_rate": 3.2938128922984956e-06,
|
2668 |
+
"loss": 0.7175,
|
2669 |
+
"step": 9500
|
2670 |
+
},
|
2671 |
+
{
|
2672 |
+
"epoch": 0.8540303057473325,
|
2673 |
+
"grad_norm": 1.7212515172137823,
|
2674 |
+
"learning_rate": 3.24399721032181e-06,
|
2675 |
+
"loss": 0.6974,
|
2676 |
+
"step": 9525
|
2677 |
+
},
|
2678 |
+
{
|
2679 |
+
"epoch": 0.8562718551062495,
|
2680 |
+
"grad_norm": 1.7737509134642555,
|
2681 |
+
"learning_rate": 3.1941815283451233e-06,
|
2682 |
+
"loss": 0.708,
|
2683 |
+
"step": 9550
|
2684 |
+
},
|
2685 |
+
{
|
2686 |
+
"epoch": 0.8585134044651663,
|
2687 |
+
"grad_norm": 1.7653120750571727,
|
2688 |
+
"learning_rate": 3.1443658463684368e-06,
|
2689 |
+
"loss": 0.7159,
|
2690 |
+
"step": 9575
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 0.8607549538240832,
|
2694 |
+
"grad_norm": 1.734111952523256,
|
2695 |
+
"learning_rate": 3.0945501643917507e-06,
|
2696 |
+
"loss": 0.7077,
|
2697 |
+
"step": 9600
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 0.8629965031830001,
|
2701 |
+
"grad_norm": 1.7456697538522787,
|
2702 |
+
"learning_rate": 3.044734482415064e-06,
|
2703 |
+
"loss": 0.7087,
|
2704 |
+
"step": 9625
|
2705 |
+
},
|
2706 |
+
{
|
2707 |
+
"epoch": 0.865238052541917,
|
2708 |
+
"grad_norm": 1.7238213295739973,
|
2709 |
+
"learning_rate": 2.9949188004383784e-06,
|
2710 |
+
"loss": 0.7005,
|
2711 |
+
"step": 9650
|
2712 |
+
},
|
2713 |
+
{
|
2714 |
+
"epoch": 0.8674796019008338,
|
2715 |
+
"grad_norm": 1.8377474317274547,
|
2716 |
+
"learning_rate": 2.945103118461692e-06,
|
2717 |
+
"loss": 0.6944,
|
2718 |
+
"step": 9675
|
2719 |
+
},
|
2720 |
+
{
|
2721 |
+
"epoch": 0.8697211512597507,
|
2722 |
+
"grad_norm": 1.7142002887130772,
|
2723 |
+
"learning_rate": 2.8952874364850058e-06,
|
2724 |
+
"loss": 0.7053,
|
2725 |
+
"step": 9700
|
2726 |
+
},
|
2727 |
+
{
|
2728 |
+
"epoch": 0.8719627006186677,
|
2729 |
+
"grad_norm": 1.7300662647642029,
|
2730 |
+
"learning_rate": 2.8454717545083192e-06,
|
2731 |
+
"loss": 0.6977,
|
2732 |
+
"step": 9725
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 0.8742042499775845,
|
2736 |
+
"grad_norm": 1.7629299601559292,
|
2737 |
+
"learning_rate": 2.7956560725316335e-06,
|
2738 |
+
"loss": 0.7258,
|
2739 |
+
"step": 9750
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 0.8764457993365014,
|
2743 |
+
"grad_norm": 2.035565282704572,
|
2744 |
+
"learning_rate": 2.745840390554947e-06,
|
2745 |
+
"loss": 0.6958,
|
2746 |
+
"step": 9775
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 0.8786873486954183,
|
2750 |
+
"grad_norm": 1.9591996552629682,
|
2751 |
+
"learning_rate": 2.696024708578261e-06,
|
2752 |
+
"loss": 0.7007,
|
2753 |
+
"step": 9800
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 0.8809288980543352,
|
2757 |
+
"grad_norm": 1.7485828313310643,
|
2758 |
+
"learning_rate": 2.6462090266015743e-06,
|
2759 |
+
"loss": 0.7155,
|
2760 |
+
"step": 9825
|
2761 |
+
},
|
2762 |
+
{
|
2763 |
+
"epoch": 0.883170447413252,
|
2764 |
+
"grad_norm": 1.7931319821271166,
|
2765 |
+
"learning_rate": 2.596393344624888e-06,
|
2766 |
+
"loss": 0.6986,
|
2767 |
+
"step": 9850
|
2768 |
+
},
|
2769 |
+
{
|
2770 |
+
"epoch": 0.885411996772169,
|
2771 |
+
"grad_norm": 1.9307468792470688,
|
2772 |
+
"learning_rate": 2.546577662648202e-06,
|
2773 |
+
"loss": 0.6803,
|
2774 |
+
"step": 9875
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 0.8876535461310858,
|
2778 |
+
"grad_norm": 1.7491594363238476,
|
2779 |
+
"learning_rate": 2.4967619806715156e-06,
|
2780 |
+
"loss": 0.6906,
|
2781 |
+
"step": 9900
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 0.8898950954900027,
|
2785 |
+
"grad_norm": 1.6753791987181879,
|
2786 |
+
"learning_rate": 2.4469462986948294e-06,
|
2787 |
+
"loss": 0.6852,
|
2788 |
+
"step": 9925
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 0.8921366448489195,
|
2792 |
+
"grad_norm": 2.0182721863038804,
|
2793 |
+
"learning_rate": 2.397130616718143e-06,
|
2794 |
+
"loss": 0.6905,
|
2795 |
+
"step": 9950
|
2796 |
+
},
|
2797 |
+
{
|
2798 |
+
"epoch": 0.8943781942078365,
|
2799 |
+
"grad_norm": 1.8187532671275537,
|
2800 |
+
"learning_rate": 2.3473149347414568e-06,
|
2801 |
+
"loss": 0.699,
|
2802 |
+
"step": 9975
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 0.8966197435667533,
|
2806 |
+
"grad_norm": 1.6663248832177007,
|
2807 |
+
"learning_rate": 2.2974992527647707e-06,
|
2808 |
+
"loss": 0.7003,
|
2809 |
+
"step": 10000
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 0.8988612929256702,
|
2813 |
+
"grad_norm": 1.9202844832714863,
|
2814 |
+
"learning_rate": 2.247683570788084e-06,
|
2815 |
+
"loss": 0.6835,
|
2816 |
+
"step": 10025
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 0.9011028422845871,
|
2820 |
+
"grad_norm": 1.6853858508241173,
|
2821 |
+
"learning_rate": 2.197867888811398e-06,
|
2822 |
+
"loss": 0.6916,
|
2823 |
+
"step": 10050
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 0.903344391643504,
|
2827 |
+
"grad_norm": 1.9868266435863697,
|
2828 |
+
"learning_rate": 2.148052206834712e-06,
|
2829 |
+
"loss": 0.6844,
|
2830 |
+
"step": 10075
|
2831 |
+
},
|
2832 |
+
{
|
2833 |
+
"epoch": 0.9055859410024208,
|
2834 |
+
"grad_norm": 1.8849355749170535,
|
2835 |
+
"learning_rate": 2.0982365248580253e-06,
|
2836 |
+
"loss": 0.7072,
|
2837 |
+
"step": 10100
|
2838 |
+
},
|
2839 |
+
{
|
2840 |
+
"epoch": 0.9078274903613378,
|
2841 |
+
"grad_norm": 1.6731153407780723,
|
2842 |
+
"learning_rate": 2.0484208428813392e-06,
|
2843 |
+
"loss": 0.6607,
|
2844 |
+
"step": 10125
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 0.9100690397202547,
|
2848 |
+
"grad_norm": 1.5128757018080325,
|
2849 |
+
"learning_rate": 1.998605160904653e-06,
|
2850 |
+
"loss": 0.6918,
|
2851 |
+
"step": 10150
|
2852 |
+
},
|
2853 |
+
{
|
2854 |
+
"epoch": 0.9123105890791715,
|
2855 |
+
"grad_norm": 1.767646778725392,
|
2856 |
+
"learning_rate": 1.9487894789279666e-06,
|
2857 |
+
"loss": 0.6961,
|
2858 |
+
"step": 10175
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 0.9145521384380884,
|
2862 |
+
"grad_norm": 1.6315602541613066,
|
2863 |
+
"learning_rate": 1.8989737969512802e-06,
|
2864 |
+
"loss": 0.6693,
|
2865 |
+
"step": 10200
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 0.9167936877970053,
|
2869 |
+
"grad_norm": 1.8678688697190617,
|
2870 |
+
"learning_rate": 1.8491581149745941e-06,
|
2871 |
+
"loss": 0.6922,
|
2872 |
+
"step": 10225
|
2873 |
+
},
|
2874 |
+
{
|
2875 |
+
"epoch": 0.9190352371559222,
|
2876 |
+
"grad_norm": 1.611712478036576,
|
2877 |
+
"learning_rate": 1.7993424329979078e-06,
|
2878 |
+
"loss": 0.6811,
|
2879 |
+
"step": 10250
|
2880 |
+
},
|
2881 |
+
{
|
2882 |
+
"epoch": 0.921276786514839,
|
2883 |
+
"grad_norm": 1.6843339133008968,
|
2884 |
+
"learning_rate": 1.7495267510212217e-06,
|
2885 |
+
"loss": 0.6755,
|
2886 |
+
"step": 10275
|
2887 |
+
},
|
2888 |
+
{
|
2889 |
+
"epoch": 0.923518335873756,
|
2890 |
+
"grad_norm": 1.6194366447525863,
|
2891 |
+
"learning_rate": 1.6997110690445353e-06,
|
2892 |
+
"loss": 0.6812,
|
2893 |
+
"step": 10300
|
2894 |
+
},
|
2895 |
+
{
|
2896 |
+
"epoch": 0.9257598852326728,
|
2897 |
+
"grad_norm": 1.860646662108025,
|
2898 |
+
"learning_rate": 1.6498953870678492e-06,
|
2899 |
+
"loss": 0.6969,
|
2900 |
+
"step": 10325
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 0.9280014345915897,
|
2904 |
+
"grad_norm": 2.0713345944656907,
|
2905 |
+
"learning_rate": 1.6000797050911629e-06,
|
2906 |
+
"loss": 0.6728,
|
2907 |
+
"step": 10350
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 0.9302429839505066,
|
2911 |
+
"grad_norm": 1.8840185563281908,
|
2912 |
+
"learning_rate": 1.5502640231144768e-06,
|
2913 |
+
"loss": 0.6745,
|
2914 |
+
"step": 10375
|
2915 |
+
},
|
2916 |
+
{
|
2917 |
+
"epoch": 0.9324845333094235,
|
2918 |
+
"grad_norm": 1.938783236028355,
|
2919 |
+
"learning_rate": 1.5004483411377904e-06,
|
2920 |
+
"loss": 0.6662,
|
2921 |
+
"step": 10400
|
2922 |
+
},
|
2923 |
+
{
|
2924 |
+
"epoch": 0.9347260826683403,
|
2925 |
+
"grad_norm": 1.5778651962299233,
|
2926 |
+
"learning_rate": 1.4506326591611039e-06,
|
2927 |
+
"loss": 0.6677,
|
2928 |
+
"step": 10425
|
2929 |
+
},
|
2930 |
+
{
|
2931 |
+
"epoch": 0.9369676320272572,
|
2932 |
+
"grad_norm": 1.841716703463937,
|
2933 |
+
"learning_rate": 1.4008169771844178e-06,
|
2934 |
+
"loss": 0.7011,
|
2935 |
+
"step": 10450
|
2936 |
+
},
|
2937 |
+
{
|
2938 |
+
"epoch": 0.9392091813861742,
|
2939 |
+
"grad_norm": 1.7110561420246093,
|
2940 |
+
"learning_rate": 1.3510012952077314e-06,
|
2941 |
+
"loss": 0.6917,
|
2942 |
+
"step": 10475
|
2943 |
+
},
|
2944 |
+
{
|
2945 |
+
"epoch": 0.941450730745091,
|
2946 |
+
"grad_norm": 1.9073072846225319,
|
2947 |
+
"learning_rate": 1.3011856132310451e-06,
|
2948 |
+
"loss": 0.6819,
|
2949 |
+
"step": 10500
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 0.9436922801040079,
|
2953 |
+
"grad_norm": 1.9505417382169639,
|
2954 |
+
"learning_rate": 1.251369931254359e-06,
|
2955 |
+
"loss": 0.6775,
|
2956 |
+
"step": 10525
|
2957 |
+
},
|
2958 |
+
{
|
2959 |
+
"epoch": 0.9459338294629248,
|
2960 |
+
"grad_norm": 1.7446591705196661,
|
2961 |
+
"learning_rate": 1.2015542492776727e-06,
|
2962 |
+
"loss": 0.6689,
|
2963 |
+
"step": 10550
|
2964 |
+
},
|
2965 |
+
{
|
2966 |
+
"epoch": 0.9481753788218417,
|
2967 |
+
"grad_norm": 1.750359764202537,
|
2968 |
+
"learning_rate": 1.1517385673009865e-06,
|
2969 |
+
"loss": 0.6961,
|
2970 |
+
"step": 10575
|
2971 |
+
},
|
2972 |
+
{
|
2973 |
+
"epoch": 0.9504169281807585,
|
2974 |
+
"grad_norm": 1.7291009933484693,
|
2975 |
+
"learning_rate": 1.1019228853243002e-06,
|
2976 |
+
"loss": 0.6826,
|
2977 |
+
"step": 10600
|
2978 |
+
},
|
2979 |
+
{
|
2980 |
+
"epoch": 0.9526584775396755,
|
2981 |
+
"grad_norm": 1.632647267687145,
|
2982 |
+
"learning_rate": 1.0521072033476139e-06,
|
2983 |
+
"loss": 0.664,
|
2984 |
+
"step": 10625
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 0.9549000268985923,
|
2988 |
+
"grad_norm": 1.7161704518625818,
|
2989 |
+
"learning_rate": 1.0022915213709276e-06,
|
2990 |
+
"loss": 0.6859,
|
2991 |
+
"step": 10650
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 0.9571415762575092,
|
2995 |
+
"grad_norm": 1.6401263166918565,
|
2996 |
+
"learning_rate": 9.524758393942414e-07,
|
2997 |
+
"loss": 0.6786,
|
2998 |
+
"step": 10675
|
2999 |
+
},
|
3000 |
+
{
|
3001 |
+
"epoch": 0.959383125616426,
|
3002 |
+
"grad_norm": 1.7482513109597007,
|
3003 |
+
"learning_rate": 9.026601574175552e-07,
|
3004 |
+
"loss": 0.6663,
|
3005 |
+
"step": 10700
|
3006 |
+
},
|
3007 |
+
{
|
3008 |
+
"epoch": 0.961624674975343,
|
3009 |
+
"grad_norm": 1.684959994399361,
|
3010 |
+
"learning_rate": 8.528444754408688e-07,
|
3011 |
+
"loss": 0.6752,
|
3012 |
+
"step": 10725
|
3013 |
+
},
|
3014 |
+
{
|
3015 |
+
"epoch": 0.9638662243342598,
|
3016 |
+
"grad_norm": 1.8573881688476663,
|
3017 |
+
"learning_rate": 8.030287934641826e-07,
|
3018 |
+
"loss": 0.6843,
|
3019 |
+
"step": 10750
|
3020 |
+
},
|
3021 |
+
{
|
3022 |
+
"epoch": 0.9661077736931767,
|
3023 |
+
"grad_norm": 1.8062245924885205,
|
3024 |
+
"learning_rate": 7.532131114874963e-07,
|
3025 |
+
"loss": 0.6863,
|
3026 |
+
"step": 10775
|
3027 |
+
},
|
3028 |
+
{
|
3029 |
+
"epoch": 0.9683493230520936,
|
3030 |
+
"grad_norm": 1.7107706105839677,
|
3031 |
+
"learning_rate": 7.033974295108101e-07,
|
3032 |
+
"loss": 0.6934,
|
3033 |
+
"step": 10800
|
3034 |
+
},
|
3035 |
+
{
|
3036 |
+
"epoch": 0.9705908724110105,
|
3037 |
+
"grad_norm": 1.7092942609036264,
|
3038 |
+
"learning_rate": 6.535817475341239e-07,
|
3039 |
+
"loss": 0.6577,
|
3040 |
+
"step": 10825
|
3041 |
+
},
|
3042 |
+
{
|
3043 |
+
"epoch": 0.9728324217699273,
|
3044 |
+
"grad_norm": 1.7804059319379388,
|
3045 |
+
"learning_rate": 6.037660655574375e-07,
|
3046 |
+
"loss": 0.6699,
|
3047 |
+
"step": 10850
|
3048 |
+
},
|
3049 |
+
{
|
3050 |
+
"epoch": 0.9750739711288443,
|
3051 |
+
"grad_norm": 1.8514662312474457,
|
3052 |
+
"learning_rate": 5.539503835807512e-07,
|
3053 |
+
"loss": 0.6628,
|
3054 |
+
"step": 10875
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 0.9773155204877612,
|
3058 |
+
"grad_norm": 1.7868336576505317,
|
3059 |
+
"learning_rate": 5.04134701604065e-07,
|
3060 |
+
"loss": 0.6979,
|
3061 |
+
"step": 10900
|
3062 |
+
},
|
3063 |
+
{
|
3064 |
+
"epoch": 0.979557069846678,
|
3065 |
+
"grad_norm": 1.7157675627877909,
|
3066 |
+
"learning_rate": 4.5431901962737877e-07,
|
3067 |
+
"loss": 0.681,
|
3068 |
+
"step": 10925
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 0.9817986192055949,
|
3072 |
+
"grad_norm": 1.7269621963297628,
|
3073 |
+
"learning_rate": 4.0450333765069244e-07,
|
3074 |
+
"loss": 0.6748,
|
3075 |
+
"step": 10950
|
3076 |
+
},
|
3077 |
+
{
|
3078 |
+
"epoch": 0.9840401685645118,
|
3079 |
+
"grad_norm": 1.6849545670128994,
|
3080 |
+
"learning_rate": 3.546876556740062e-07,
|
3081 |
+
"loss": 0.6845,
|
3082 |
+
"step": 10975
|
3083 |
+
},
|
3084 |
+
{
|
3085 |
+
"epoch": 0.9862817179234287,
|
3086 |
+
"grad_norm": 1.712207675718165,
|
3087 |
+
"learning_rate": 3.0487197369731994e-07,
|
3088 |
+
"loss": 0.6648,
|
3089 |
+
"step": 11000
|
3090 |
+
},
|
3091 |
+
{
|
3092 |
+
"epoch": 0.9885232672823455,
|
3093 |
+
"grad_norm": 1.8999442305937304,
|
3094 |
+
"learning_rate": 2.5505629172063366e-07,
|
3095 |
+
"loss": 0.6558,
|
3096 |
+
"step": 11025
|
3097 |
+
},
|
3098 |
+
{
|
3099 |
+
"epoch": 0.9907648166412625,
|
3100 |
+
"grad_norm": 1.699393044053189,
|
3101 |
+
"learning_rate": 2.052406097439474e-07,
|
3102 |
+
"loss": 0.6864,
|
3103 |
+
"step": 11050
|
3104 |
+
},
|
3105 |
+
{
|
3106 |
+
"epoch": 0.9930063660001793,
|
3107 |
+
"grad_norm": 1.7110416398737864,
|
3108 |
+
"learning_rate": 1.5542492776726116e-07,
|
3109 |
+
"loss": 0.6724,
|
3110 |
+
"step": 11075
|
3111 |
+
},
|
3112 |
+
{
|
3113 |
+
"epoch": 0.9952479153590962,
|
3114 |
+
"grad_norm": 1.7936965958729694,
|
3115 |
+
"learning_rate": 1.0560924579057488e-07,
|
3116 |
+
"loss": 0.6524,
|
3117 |
+
"step": 11100
|
3118 |
+
},
|
3119 |
+
{
|
3120 |
+
"epoch": 0.9974894647180131,
|
3121 |
+
"grad_norm": 1.793636959019703,
|
3122 |
+
"learning_rate": 5.5793563813888614e-08,
|
3123 |
+
"loss": 0.6882,
|
3124 |
+
"step": 11125
|
3125 |
+
},
|
3126 |
+
{
|
3127 |
+
"epoch": 0.99973101407693,
|
3128 |
+
"grad_norm": 1.658624597079087,
|
3129 |
+
"learning_rate": 5.9778818372023515e-09,
|
3130 |
+
"loss": 0.6742,
|
3131 |
+
"step": 11150
|
3132 |
+
}
|
3133 |
+
],
|
3134 |
+
"logging_steps": 25,
|
3135 |
+
"max_steps": 11153,
|
3136 |
+
"num_input_tokens_seen": 0,
|
3137 |
+
"num_train_epochs": 1,
|
3138 |
+
"save_steps": 500,
|
3139 |
+
"total_flos": 583802824949760.0,
|
3140 |
+
"train_batch_size": 4,
|
3141 |
+
"trial_name": null,
|
3142 |
+
"trial_params": null
|
3143 |
+
}
|
checkpoint-11153/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b1d0e0bfafc928d0ee97b04e6b80105bb4334369cd7dcde0e604159bf51c593
|
3 |
+
size 6072
|
checkpoint-11153/zero_to_fp32.py
ADDED
@@ -0,0 +1,604 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/usr/bin/env python
|
2 |
+
|
3 |
+
# Copyright (c) Microsoft Corporation.
|
4 |
+
# SPDX-License-Identifier: Apache-2.0
|
5 |
+
|
6 |
+
# DeepSpeed Team
|
7 |
+
|
8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
11 |
+
# application.
|
12 |
+
#
|
13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
14 |
+
|
15 |
+
import argparse
|
16 |
+
import torch
|
17 |
+
import glob
|
18 |
+
import math
|
19 |
+
import os
|
20 |
+
import re
|
21 |
+
from collections import OrderedDict
|
22 |
+
from dataclasses import dataclass
|
23 |
+
|
24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
26 |
+
from deepspeed.utils import logger
|
27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
30 |
+
|
31 |
+
|
32 |
+
@dataclass
|
33 |
+
class zero_model_state:
|
34 |
+
buffers: dict()
|
35 |
+
param_shapes: dict()
|
36 |
+
shared_params: list
|
37 |
+
ds_version: int
|
38 |
+
frozen_param_shapes: dict()
|
39 |
+
frozen_param_fragments: dict()
|
40 |
+
|
41 |
+
|
42 |
+
debug = 0
|
43 |
+
|
44 |
+
# load to cpu
|
45 |
+
device = torch.device('cpu')
|
46 |
+
|
47 |
+
|
48 |
+
def atoi(text):
|
49 |
+
return int(text) if text.isdigit() else text
|
50 |
+
|
51 |
+
|
52 |
+
def natural_keys(text):
|
53 |
+
'''
|
54 |
+
alist.sort(key=natural_keys) sorts in human order
|
55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
56 |
+
(See Toothy's implementation in the comments)
|
57 |
+
'''
|
58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
59 |
+
|
60 |
+
|
61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
62 |
+
if not os.path.isdir(checkpoint_dir):
|
63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
64 |
+
|
65 |
+
# there should be only one file
|
66 |
+
if zero_stage <= 2:
|
67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
68 |
+
elif zero_stage == 3:
|
69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
70 |
+
|
71 |
+
if not os.path.exists(file):
|
72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
73 |
+
|
74 |
+
return file
|
75 |
+
|
76 |
+
|
77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
80 |
+
|
81 |
+
if len(ckpt_files) == 0:
|
82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
83 |
+
|
84 |
+
return ckpt_files
|
85 |
+
|
86 |
+
|
87 |
+
def get_optim_files(checkpoint_dir):
|
88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
89 |
+
|
90 |
+
|
91 |
+
def get_model_state_files(checkpoint_dir):
|
92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
93 |
+
|
94 |
+
|
95 |
+
def parse_model_states(files):
|
96 |
+
zero_model_states = []
|
97 |
+
for file in files:
|
98 |
+
state_dict = torch.load(file, map_location=device)
|
99 |
+
|
100 |
+
if BUFFER_NAMES not in state_dict:
|
101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
103 |
+
if debug:
|
104 |
+
print("Found buffers:", buffer_names)
|
105 |
+
|
106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
109 |
+
|
110 |
+
# collect parameters that are included in param_shapes
|
111 |
+
param_names = []
|
112 |
+
for s in param_shapes:
|
113 |
+
for name in s.keys():
|
114 |
+
param_names.append(name)
|
115 |
+
|
116 |
+
# update with frozen parameters
|
117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
118 |
+
if frozen_param_shapes is not None:
|
119 |
+
if debug:
|
120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
121 |
+
param_names += list(frozen_param_shapes.keys())
|
122 |
+
|
123 |
+
# handle shared params
|
124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
125 |
+
|
126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
127 |
+
|
128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
129 |
+
|
130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
131 |
+
param_shapes=param_shapes,
|
132 |
+
shared_params=shared_params,
|
133 |
+
ds_version=ds_version,
|
134 |
+
frozen_param_shapes=frozen_param_shapes,
|
135 |
+
frozen_param_fragments=frozen_param_fragments)
|
136 |
+
zero_model_states.append(z_model_state)
|
137 |
+
|
138 |
+
return zero_model_states
|
139 |
+
|
140 |
+
|
141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
142 |
+
|
143 |
+
total_files = len(files)
|
144 |
+
state_dicts = []
|
145 |
+
for f in files:
|
146 |
+
state_dict = torch.load(f, map_location=device)
|
147 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
148 |
+
# and also handle the case where it was already removed by another helper script
|
149 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
150 |
+
state_dicts.append(state_dict)
|
151 |
+
|
152 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
153 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
154 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
155 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
156 |
+
|
157 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
158 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
159 |
+
# use the max of the partition_count to get the dp world_size.
|
160 |
+
|
161 |
+
if type(world_size) is list:
|
162 |
+
world_size = max(world_size)
|
163 |
+
|
164 |
+
if world_size != total_files:
|
165 |
+
raise ValueError(
|
166 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
167 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
168 |
+
)
|
169 |
+
|
170 |
+
# the groups are named differently in each stage
|
171 |
+
if zero_stage <= 2:
|
172 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
173 |
+
elif zero_stage == 3:
|
174 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
175 |
+
else:
|
176 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
177 |
+
|
178 |
+
if zero_stage <= 2:
|
179 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
180 |
+
elif zero_stage == 3:
|
181 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
182 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
183 |
+
#
|
184 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
185 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
186 |
+
|
187 |
+
fp32_flat_groups = [
|
188 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
189 |
+
]
|
190 |
+
|
191 |
+
return zero_stage, world_size, fp32_flat_groups
|
192 |
+
|
193 |
+
|
194 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
195 |
+
"""
|
196 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
197 |
+
|
198 |
+
Args:
|
199 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
200 |
+
|
201 |
+
"""
|
202 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
203 |
+
|
204 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
205 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
206 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
207 |
+
|
208 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
209 |
+
|
210 |
+
zero_model_states = parse_model_states(model_files)
|
211 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
212 |
+
|
213 |
+
if zero_stage <= 2:
|
214 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
215 |
+
exclude_frozen_parameters)
|
216 |
+
elif zero_stage == 3:
|
217 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
218 |
+
exclude_frozen_parameters)
|
219 |
+
|
220 |
+
|
221 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
222 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
223 |
+
return
|
224 |
+
|
225 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
226 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
227 |
+
|
228 |
+
if debug:
|
229 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
230 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
231 |
+
|
232 |
+
wanted_params = len(frozen_param_shapes)
|
233 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
234 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
235 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
236 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
237 |
+
|
238 |
+
total_params = 0
|
239 |
+
total_numel = 0
|
240 |
+
for name, shape in frozen_param_shapes.items():
|
241 |
+
total_params += 1
|
242 |
+
unpartitioned_numel = shape.numel()
|
243 |
+
total_numel += unpartitioned_numel
|
244 |
+
|
245 |
+
state_dict[name] = frozen_param_fragments[name]
|
246 |
+
|
247 |
+
if debug:
|
248 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
249 |
+
|
250 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
251 |
+
|
252 |
+
|
253 |
+
def _has_callable(obj, fn):
|
254 |
+
attr = getattr(obj, fn, None)
|
255 |
+
return callable(attr)
|
256 |
+
|
257 |
+
|
258 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
259 |
+
param_shapes = zero_model_states[0].param_shapes
|
260 |
+
|
261 |
+
# Reconstruction protocol:
|
262 |
+
#
|
263 |
+
# XXX: document this
|
264 |
+
|
265 |
+
if debug:
|
266 |
+
for i in range(world_size):
|
267 |
+
for j in range(len(fp32_flat_groups[0])):
|
268 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
269 |
+
|
270 |
+
# XXX: memory usage doubles here (zero2)
|
271 |
+
num_param_groups = len(fp32_flat_groups[0])
|
272 |
+
merged_single_partition_of_fp32_groups = []
|
273 |
+
for i in range(num_param_groups):
|
274 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
275 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
276 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
277 |
+
avail_numel = sum(
|
278 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
279 |
+
|
280 |
+
if debug:
|
281 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
282 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
283 |
+
# not asserting if there is a mismatch due to possible padding
|
284 |
+
print(f"Have {avail_numel} numels to process.")
|
285 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
286 |
+
|
287 |
+
# params
|
288 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
289 |
+
# out-of-core computing solution
|
290 |
+
total_numel = 0
|
291 |
+
total_params = 0
|
292 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
293 |
+
offset = 0
|
294 |
+
avail_numel = full_single_fp32_vector.numel()
|
295 |
+
for name, shape in shapes.items():
|
296 |
+
|
297 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
298 |
+
total_numel += unpartitioned_numel
|
299 |
+
total_params += 1
|
300 |
+
|
301 |
+
if debug:
|
302 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
303 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
304 |
+
offset += unpartitioned_numel
|
305 |
+
|
306 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
307 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
308 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
309 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
310 |
+
align_to = 2 * world_size
|
311 |
+
|
312 |
+
def zero2_align(x):
|
313 |
+
return align_to * math.ceil(x / align_to)
|
314 |
+
|
315 |
+
if debug:
|
316 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
317 |
+
|
318 |
+
offset = zero2_align(offset)
|
319 |
+
avail_numel = zero2_align(avail_numel)
|
320 |
+
|
321 |
+
if debug:
|
322 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
323 |
+
|
324 |
+
# Sanity check
|
325 |
+
if offset != avail_numel:
|
326 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
327 |
+
|
328 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
329 |
+
|
330 |
+
|
331 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
332 |
+
exclude_frozen_parameters):
|
333 |
+
state_dict = OrderedDict()
|
334 |
+
|
335 |
+
# buffers
|
336 |
+
buffers = zero_model_states[0].buffers
|
337 |
+
state_dict.update(buffers)
|
338 |
+
if debug:
|
339 |
+
print(f"added {len(buffers)} buffers")
|
340 |
+
|
341 |
+
if not exclude_frozen_parameters:
|
342 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
343 |
+
|
344 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
345 |
+
|
346 |
+
# recover shared parameters
|
347 |
+
for pair in zero_model_states[0].shared_params:
|
348 |
+
if pair[1] in state_dict:
|
349 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
350 |
+
|
351 |
+
return state_dict
|
352 |
+
|
353 |
+
|
354 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
355 |
+
remainder = unpartitioned_numel % world_size
|
356 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
357 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
358 |
+
return partitioned_numel, padding_numel
|
359 |
+
|
360 |
+
|
361 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
362 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
363 |
+
return
|
364 |
+
|
365 |
+
if debug:
|
366 |
+
for i in range(world_size):
|
367 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
368 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
369 |
+
|
370 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
371 |
+
wanted_params = len(frozen_param_shapes)
|
372 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
373 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
374 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
375 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
376 |
+
|
377 |
+
total_params = 0
|
378 |
+
total_numel = 0
|
379 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
380 |
+
total_params += 1
|
381 |
+
unpartitioned_numel = shape.numel()
|
382 |
+
total_numel += unpartitioned_numel
|
383 |
+
|
384 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
385 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
386 |
+
|
387 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
388 |
+
|
389 |
+
if debug:
|
390 |
+
print(
|
391 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
392 |
+
)
|
393 |
+
|
394 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
395 |
+
|
396 |
+
|
397 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
398 |
+
param_shapes = zero_model_states[0].param_shapes
|
399 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
400 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
401 |
+
# param, re-consolidating each param, while dealing with padding if any
|
402 |
+
|
403 |
+
# merge list of dicts, preserving order
|
404 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
405 |
+
|
406 |
+
if debug:
|
407 |
+
for i in range(world_size):
|
408 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
409 |
+
|
410 |
+
wanted_params = len(param_shapes)
|
411 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
412 |
+
# not asserting if there is a mismatch due to possible padding
|
413 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
414 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
415 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
416 |
+
|
417 |
+
# params
|
418 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
419 |
+
# out-of-core computing solution
|
420 |
+
offset = 0
|
421 |
+
total_numel = 0
|
422 |
+
total_params = 0
|
423 |
+
for name, shape in param_shapes.items():
|
424 |
+
|
425 |
+
unpartitioned_numel = shape.numel()
|
426 |
+
total_numel += unpartitioned_numel
|
427 |
+
total_params += 1
|
428 |
+
|
429 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
430 |
+
|
431 |
+
if debug:
|
432 |
+
print(
|
433 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
434 |
+
)
|
435 |
+
|
436 |
+
# XXX: memory usage doubles here
|
437 |
+
state_dict[name] = torch.cat(
|
438 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
439 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
440 |
+
offset += partitioned_numel
|
441 |
+
|
442 |
+
offset *= world_size
|
443 |
+
|
444 |
+
# Sanity check
|
445 |
+
if offset != avail_numel:
|
446 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
447 |
+
|
448 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
449 |
+
|
450 |
+
|
451 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
452 |
+
exclude_frozen_parameters):
|
453 |
+
state_dict = OrderedDict()
|
454 |
+
|
455 |
+
# buffers
|
456 |
+
buffers = zero_model_states[0].buffers
|
457 |
+
state_dict.update(buffers)
|
458 |
+
if debug:
|
459 |
+
print(f"added {len(buffers)} buffers")
|
460 |
+
|
461 |
+
if not exclude_frozen_parameters:
|
462 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
463 |
+
|
464 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
465 |
+
|
466 |
+
# recover shared parameters
|
467 |
+
for pair in zero_model_states[0].shared_params:
|
468 |
+
if pair[1] in state_dict:
|
469 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
470 |
+
|
471 |
+
return state_dict
|
472 |
+
|
473 |
+
|
474 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
475 |
+
"""
|
476 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
477 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
478 |
+
via a model hub.
|
479 |
+
|
480 |
+
Args:
|
481 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
482 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
483 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
484 |
+
|
485 |
+
Returns:
|
486 |
+
- pytorch ``state_dict``
|
487 |
+
|
488 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
489 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
490 |
+
the checkpoint.
|
491 |
+
|
492 |
+
A typical usage might be ::
|
493 |
+
|
494 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
495 |
+
# do the training and checkpoint saving
|
496 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
497 |
+
model = model.cpu() # move to cpu
|
498 |
+
model.load_state_dict(state_dict)
|
499 |
+
# submit to model hub or save the model to share with others
|
500 |
+
|
501 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
502 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
503 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
504 |
+
|
505 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
506 |
+
|
507 |
+
"""
|
508 |
+
if tag is None:
|
509 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
510 |
+
if os.path.isfile(latest_path):
|
511 |
+
with open(latest_path, 'r') as fd:
|
512 |
+
tag = fd.read().strip()
|
513 |
+
else:
|
514 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
515 |
+
|
516 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
517 |
+
|
518 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
519 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
520 |
+
|
521 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
522 |
+
|
523 |
+
|
524 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
|
525 |
+
"""
|
526 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
527 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
528 |
+
|
529 |
+
Args:
|
530 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
531 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
532 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
533 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
534 |
+
"""
|
535 |
+
|
536 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
537 |
+
print(f"Saving fp32 state dict to {output_file}")
|
538 |
+
torch.save(state_dict, output_file)
|
539 |
+
|
540 |
+
|
541 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
542 |
+
"""
|
543 |
+
1. Put the provided model to cpu
|
544 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
545 |
+
3. Load it into the provided model
|
546 |
+
|
547 |
+
Args:
|
548 |
+
- ``model``: the model object to update
|
549 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
550 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
551 |
+
|
552 |
+
Returns:
|
553 |
+
- ``model`: modified model
|
554 |
+
|
555 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
556 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
557 |
+
conveniently placed for you in the checkpoint folder.
|
558 |
+
|
559 |
+
A typical usage might be ::
|
560 |
+
|
561 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
562 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
563 |
+
# submit to model hub or save the model to share with others
|
564 |
+
|
565 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
566 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
567 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
568 |
+
|
569 |
+
"""
|
570 |
+
logger.info(f"Extracting fp32 weights")
|
571 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
572 |
+
|
573 |
+
logger.info(f"Overwriting model with fp32 weights")
|
574 |
+
model = model.cpu()
|
575 |
+
model.load_state_dict(state_dict, strict=False)
|
576 |
+
|
577 |
+
return model
|
578 |
+
|
579 |
+
|
580 |
+
if __name__ == "__main__":
|
581 |
+
|
582 |
+
parser = argparse.ArgumentParser()
|
583 |
+
parser.add_argument("checkpoint_dir",
|
584 |
+
type=str,
|
585 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
586 |
+
parser.add_argument(
|
587 |
+
"output_file",
|
588 |
+
type=str,
|
589 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
590 |
+
parser.add_argument("-t",
|
591 |
+
"--tag",
|
592 |
+
type=str,
|
593 |
+
default=None,
|
594 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
595 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
596 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
597 |
+
args = parser.parse_args()
|
598 |
+
|
599 |
+
debug = args.debug
|
600 |
+
|
601 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
602 |
+
args.output_file,
|
603 |
+
tag=args.tag,
|
604 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 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": "4.40.0",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 128264
|
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": "4.40.0"
|
6 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4dc60ba1d2073bdd95a0f469265587e9711e0e35b5569da784f287cd6ab0356
|
3 |
+
size 4976764208
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cb22b1acddca151372ab19dda1bc7dfed4848c70e15bf93e20fc7c02b4fdb98
|
3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5136aa7410834a6af82d77dbbb7b3e854b09b750e55406a7c6b3ced0e24b4afb
|
3 |
+
size 4915916176
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8708006d0d25d48da829f87f16dd42ba10f7286b63ab292b7546c45be3ff2059
|
3 |
+
size 1168204344
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 16060653568
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>user",
|
4 |
+
"<|im_start|>assistant",
|
5 |
+
"<|im_start|>system",
|
6 |
+
"<|im_end|>",
|
7 |
+
"<s>",
|
8 |
+
"<pad>"
|
9 |
+
],
|
10 |
+
"bos_token": "<s>",
|
11 |
+
"eos_token": "<|im_end|>",
|
12 |
+
"pad_token": "<pad>"
|
13 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"128256": {
|
2052 |
+
"content": "<s>",
|
2053 |
+
"lstrip": false,
|
2054 |
+
"normalized": false,
|
2055 |
+
"rstrip": false,
|
2056 |
+
"single_word": false,
|
2057 |
+
"special": true
|
2058 |
+
},
|
2059 |
+
"128257": {
|
2060 |
+
"content": "<|im_end|>",
|
2061 |
+
"lstrip": false,
|
2062 |
+
"normalized": false,
|
2063 |
+
"rstrip": false,
|
2064 |
+
"single_word": false,
|
2065 |
+
"special": true
|
2066 |
+
},
|
2067 |
+
"128258": {
|
2068 |
+
"content": "<pad>",
|
2069 |
+
"lstrip": false,
|
2070 |
+
"normalized": false,
|
2071 |
+
"rstrip": false,
|
2072 |
+
"single_word": false,
|
2073 |
+
"special": true
|
2074 |
+
},
|
2075 |
+
"128259": {
|
2076 |
+
"content": "<|im_start|>user",
|
2077 |
+
"lstrip": false,
|
2078 |
+
"normalized": false,
|
2079 |
+
"rstrip": false,
|
2080 |
+
"single_word": false,
|
2081 |
+
"special": true
|
2082 |
+
},
|
2083 |
+
"128260": {
|
2084 |
+
"content": "<|im_start|>assistant",
|
2085 |
+
"lstrip": false,
|
2086 |
+
"normalized": false,
|
2087 |
+
"rstrip": false,
|
2088 |
+
"single_word": false,
|
2089 |
+
"special": true
|
2090 |
+
},
|
2091 |
+
"128261": {
|
2092 |
+
"content": "<|im_start|>system",
|
2093 |
+
"lstrip": false,
|
2094 |
+
"normalized": false,
|
2095 |
+
"rstrip": false,
|
2096 |
+
"single_word": false,
|
2097 |
+
"special": true
|
2098 |
+
}
|
2099 |
+
},
|
2100 |
+
"additional_special_tokens": [
|
2101 |
+
"<|im_start|>user",
|
2102 |
+
"<|im_start|>assistant",
|
2103 |
+
"<|im_start|>system",
|
2104 |
+
"<|im_end|>",
|
2105 |
+
"<s>",
|
2106 |
+
"<pad>"
|
2107 |
+
],
|
2108 |
+
"bos_token": "<s>",
|
2109 |
+
"chat_template": "{% for message in messages %}\n{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% if loop.last and add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}{% endfor %}",
|
2110 |
+
"clean_up_tokenization_spaces": true,
|
2111 |
+
"eos_token": "<|im_end|>",
|
2112 |
+
"model_input_names": [
|
2113 |
+
"input_ids",
|
2114 |
+
"attention_mask"
|
2115 |
+
],
|
2116 |
+
"model_max_length": 8192,
|
2117 |
+
"pad_token": "<pad>",
|
2118 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2119 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b1d0e0bfafc928d0ee97b04e6b80105bb4334369cd7dcde0e604159bf51c593
|
3 |
+
size 6072
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
+
"project_name": "autotrain-llama3-oh1",
|
4 |
+
"data_path": "HuggingFaceH4/OpenHermes-2.5",
|
5 |
+
"train_split": "train_sft",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": false,
|
8 |
+
"block_size": 1024,
|
9 |
+
"model_max_length": 8192,
|
10 |
+
"padding": "right",
|
11 |
+
"trainer": "sft",
|
12 |
+
"use_flash_attention_2": false,
|
13 |
+
"log": "none",
|
14 |
+
"disable_gradient_checkpointing": false,
|
15 |
+
"logging_steps": -1,
|
16 |
+
"evaluation_strategy": "epoch",
|
17 |
+
"save_total_limit": 1,
|
18 |
+
"save_strategy": "epoch",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "bf16",
|
21 |
+
"lr": 2e-05,
|
22 |
+
"epochs": 1,
|
23 |
+
"batch_size": 4,
|
24 |
+
"warmup_ratio": 0.1,
|
25 |
+
"gradient_accumulation": 1,
|
26 |
+
"optimizer": "adamw_torch",
|
27 |
+
"scheduler": "linear",
|
28 |
+
"weight_decay": 0.0,
|
29 |
+
"max_grad_norm": 1.0,
|
30 |
+
"seed": 42,
|
31 |
+
"chat_template": "chatml",
|
32 |
+
"quantization": null,
|
33 |
+
"target_modules": null,
|
34 |
+
"merge_adapter": false,
|
35 |
+
"peft": false,
|
36 |
+
"lora_r": 16,
|
37 |
+
"lora_alpha": 32,
|
38 |
+
"lora_dropout": 0.05,
|
39 |
+
"model_ref": null,
|
40 |
+
"dpo_beta": 0.1,
|
41 |
+
"prompt_text_column": "prompt",
|
42 |
+
"text_column": "messages",
|
43 |
+
"rejected_text_column": "rejected",
|
44 |
+
"push_to_hub": true,
|
45 |
+
"repo_id": "abhishek/autotrain-llama3-oh1",
|
46 |
+
"username": "abhishek"
|
47 |
+
}
|