jeromeramos commited on
Commit
906f965
·
verified ·
1 Parent(s): 7134ce1

Model save

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B
3
+ library_name: transformers
4
+ model_name: inter-play-sim-user-sft
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - sft
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for inter-play-sim-user-sft
13
+
14
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="Sim4Rec/inter-play-sim-user-sft", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jerome-ramos-20/huggingface/runs/wb8nxhk1)
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.14.0
38
+ - Transformers: 4.51.3
39
+ - Pytorch: 2.6.0
40
+ - Datasets: 3.0.1
41
+ - Tokenizers: 0.21.0
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @misc{vonwerra2022trl,
51
+ title = {{TRL: Transformer Reinforcement Learning}},
52
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
53
+ year = 2020,
54
+ journal = {GitHub repository},
55
+ publisher = {GitHub},
56
+ howpublished = {\url{https://github.com/huggingface/trl}}
57
+ }
58
+ ```
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 6.011530730704732e+18,
4
+ "train_loss": 0.6795949197244182,
5
+ "train_runtime": 13742.7497,
6
+ "train_samples": 46269,
7
+ "train_samples_per_second": 6.734,
8
+ "train_steps_per_second": 0.105
9
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128256,
8
+ "eos_token_id": 128257,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128004,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.51.3",
34
+ "use_cache": false,
35
+ "vocab_size": 128320
36
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.51.3"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b15c6381825c63b914fc3ae491fa0b051dcde0f5dd41ee0c94916bb984a8c41
3
+ size 4977222960
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5465c66718008ceab01e65b8a7ff760284b4208c0250328f95ad2c6ee0cfe763
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:f0c46bb5f8beb33abb2e43677b1cbdef9638a043142e739954efc8fe50663c8a
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:794c20aa3d6e5f53ff1c9a7a5325c99a9e8fcdc3847f938bcee06fb2b328c0b9
3
+ size 1168663096
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16061571072
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
+ }
runs/Apr29_16-14-53_w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-7dtpznf/events.out.tfevents.1745943519.w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-7dtpznf.13928.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbdf3e6e6b5aa245057d92e71d96671725c60d26dc72d0e84bf95fae760a31ae
3
+ size 13905
runs/Apr30_00-56-10_w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-55drk5l/events.out.tfevents.1745974844.w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-55drk5l.14492.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ed59c52e389e6d547e4e204671b816c3d38d4cbb57f7518ee3800b60f97b120
3
+ size 7436
runs/Apr30_21-13-36_w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-74x2cnd/events.out.tfevents.1746047994.w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-74x2cnd.9862.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6817b9554a795b4409f64c12127b6b2ea3e468970a7b6286c9f9dbb4258c7404
3
+ size 67220
special_tokens_map.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<response>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</response>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<answer>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</answer>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<inquire>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ ],
39
+ "bos_token": {
40
+ "content": "<|im_start|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "eos_token": {
47
+ "content": "<|im_end|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token": "<|finetune_right_pad_id|>"
54
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399c8422d1d7d647447d5522424c38669eb8b89394346f20c9ca2795800eeacb
3
+ size 17211327
tokenizer_config.json ADDED
@@ -0,0 +1,2127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|im_start|>",
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": "<response>",
2069
+ "lstrip": false,
2070
+ "normalized": false,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": true
2074
+ },
2075
+ "128259": {
2076
+ "content": "</response>",
2077
+ "lstrip": false,
2078
+ "normalized": false,
2079
+ "rstrip": false,
2080
+ "single_word": false,
2081
+ "special": true
2082
+ },
2083
+ "128260": {
2084
+ "content": "<answer>",
2085
+ "lstrip": false,
2086
+ "normalized": false,
2087
+ "rstrip": false,
2088
+ "single_word": false,
2089
+ "special": true
2090
+ },
2091
+ "128261": {
2092
+ "content": "</answer>",
2093
+ "lstrip": false,
2094
+ "normalized": false,
2095
+ "rstrip": false,
2096
+ "single_word": false,
2097
+ "special": true
2098
+ },
2099
+ "128262": {
2100
+ "content": "<inquire>",
2101
+ "lstrip": false,
2102
+ "normalized": false,
2103
+ "rstrip": false,
2104
+ "single_word": false,
2105
+ "special": true
2106
+ }
2107
+ },
2108
+ "additional_special_tokens": [
2109
+ "<response>",
2110
+ "</response>",
2111
+ "<answer>",
2112
+ "</answer>",
2113
+ "<inquire>"
2114
+ ],
2115
+ "bos_token": "<|im_start|>",
2116
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>user\n' }}{% endif %}",
2117
+ "clean_up_tokenization_spaces": true,
2118
+ "eos_token": "<|im_end|>",
2119
+ "extra_special_tokens": {},
2120
+ "model_input_names": [
2121
+ "input_ids",
2122
+ "attention_mask"
2123
+ ],
2124
+ "model_max_length": 131072,
2125
+ "pad_token": "<|finetune_right_pad_id|>",
2126
+ "tokenizer_class": "PreTrainedTokenizer"
2127
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 6.011530730704732e+18,
4
+ "train_loss": 0.6795949197244182,
5
+ "train_runtime": 13742.7497,
6
+ "train_samples": 46269,
7
+ "train_samples_per_second": 6.734,
8
+ "train_steps_per_second": 0.105
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,2073 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1446,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0013831258644536654,
14
+ "grad_norm": 133.08836364746094,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.6747,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.006915629322268326,
21
+ "grad_norm": 10.979754447937012,
22
+ "learning_rate": 5.517241379310345e-06,
23
+ "loss": 1.5287,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.013831258644536652,
28
+ "grad_norm": 5.598673343658447,
29
+ "learning_rate": 1.2413793103448277e-05,
30
+ "loss": 1.1371,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.02074688796680498,
35
+ "grad_norm": 4.170475959777832,
36
+ "learning_rate": 1.9310344827586207e-05,
37
+ "loss": 1.0279,
38
+ "step": 15
39
+ },
40
+ {
41
+ "epoch": 0.027662517289073305,
42
+ "grad_norm": 3.909233331680298,
43
+ "learning_rate": 2.620689655172414e-05,
44
+ "loss": 0.9947,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.034578146611341634,
49
+ "grad_norm": 3.94997501373291,
50
+ "learning_rate": 3.310344827586207e-05,
51
+ "loss": 0.9337,
52
+ "step": 25
53
+ },
54
+ {
55
+ "epoch": 0.04149377593360996,
56
+ "grad_norm": 3.896550178527832,
57
+ "learning_rate": 4e-05,
58
+ "loss": 0.8761,
59
+ "step": 30
60
+ },
61
+ {
62
+ "epoch": 0.048409405255878286,
63
+ "grad_norm": 3.581073522567749,
64
+ "learning_rate": 4.689655172413793e-05,
65
+ "loss": 0.8054,
66
+ "step": 35
67
+ },
68
+ {
69
+ "epoch": 0.05532503457814661,
70
+ "grad_norm": 2.294735908508301,
71
+ "learning_rate": 5.379310344827586e-05,
72
+ "loss": 0.7511,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 0.06224066390041494,
77
+ "grad_norm": 1.9514353275299072,
78
+ "learning_rate": 6.068965517241379e-05,
79
+ "loss": 0.7493,
80
+ "step": 45
81
+ },
82
+ {
83
+ "epoch": 0.06915629322268327,
84
+ "grad_norm": 2.1982648372650146,
85
+ "learning_rate": 6.758620689655173e-05,
86
+ "loss": 0.8087,
87
+ "step": 50
88
+ },
89
+ {
90
+ "epoch": 0.07607192254495158,
91
+ "grad_norm": 2.2902512550354004,
92
+ "learning_rate": 7.448275862068966e-05,
93
+ "loss": 0.7906,
94
+ "step": 55
95
+ },
96
+ {
97
+ "epoch": 0.08298755186721991,
98
+ "grad_norm": 1.9472178220748901,
99
+ "learning_rate": 8.137931034482759e-05,
100
+ "loss": 0.7872,
101
+ "step": 60
102
+ },
103
+ {
104
+ "epoch": 0.08990318118948824,
105
+ "grad_norm": 1.7574316263198853,
106
+ "learning_rate": 8.827586206896552e-05,
107
+ "loss": 0.7898,
108
+ "step": 65
109
+ },
110
+ {
111
+ "epoch": 0.09681881051175657,
112
+ "grad_norm": 1.8785020112991333,
113
+ "learning_rate": 9.517241379310345e-05,
114
+ "loss": 0.8166,
115
+ "step": 70
116
+ },
117
+ {
118
+ "epoch": 0.1037344398340249,
119
+ "grad_norm": 1.5703641176223755,
120
+ "learning_rate": 0.0001020689655172414,
121
+ "loss": 0.7987,
122
+ "step": 75
123
+ },
124
+ {
125
+ "epoch": 0.11065006915629322,
126
+ "grad_norm": 1.4895148277282715,
127
+ "learning_rate": 0.00010896551724137931,
128
+ "loss": 0.8054,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 0.11756569847856155,
133
+ "grad_norm": 1.7236794233322144,
134
+ "learning_rate": 0.00011586206896551725,
135
+ "loss": 0.8111,
136
+ "step": 85
137
+ },
138
+ {
139
+ "epoch": 0.12448132780082988,
140
+ "grad_norm": 1.788547396659851,
141
+ "learning_rate": 0.00012275862068965518,
142
+ "loss": 0.8067,
143
+ "step": 90
144
+ },
145
+ {
146
+ "epoch": 0.1313969571230982,
147
+ "grad_norm": 1.6218682527542114,
148
+ "learning_rate": 0.0001296551724137931,
149
+ "loss": 0.8175,
150
+ "step": 95
151
+ },
152
+ {
153
+ "epoch": 0.13831258644536654,
154
+ "grad_norm": 1.438413381576538,
155
+ "learning_rate": 0.00013655172413793104,
156
+ "loss": 0.8485,
157
+ "step": 100
158
+ },
159
+ {
160
+ "epoch": 0.14522821576763487,
161
+ "grad_norm": 1.6937086582183838,
162
+ "learning_rate": 0.00014344827586206896,
163
+ "loss": 0.8562,
164
+ "step": 105
165
+ },
166
+ {
167
+ "epoch": 0.15214384508990317,
168
+ "grad_norm": 1.4097000360488892,
169
+ "learning_rate": 0.0001503448275862069,
170
+ "loss": 0.851,
171
+ "step": 110
172
+ },
173
+ {
174
+ "epoch": 0.1590594744121715,
175
+ "grad_norm": 2.706479072570801,
176
+ "learning_rate": 0.00015724137931034485,
177
+ "loss": 0.8461,
178
+ "step": 115
179
+ },
180
+ {
181
+ "epoch": 0.16597510373443983,
182
+ "grad_norm": 2.0034353733062744,
183
+ "learning_rate": 0.00016413793103448276,
184
+ "loss": 0.8548,
185
+ "step": 120
186
+ },
187
+ {
188
+ "epoch": 0.17289073305670816,
189
+ "grad_norm": 1.3242019414901733,
190
+ "learning_rate": 0.0001710344827586207,
191
+ "loss": 0.8553,
192
+ "step": 125
193
+ },
194
+ {
195
+ "epoch": 0.1798063623789765,
196
+ "grad_norm": 2.6091411113739014,
197
+ "learning_rate": 0.00017793103448275862,
198
+ "loss": 0.848,
199
+ "step": 130
200
+ },
201
+ {
202
+ "epoch": 0.18672199170124482,
203
+ "grad_norm": 1.3679989576339722,
204
+ "learning_rate": 0.00018482758620689654,
205
+ "loss": 0.8716,
206
+ "step": 135
207
+ },
208
+ {
209
+ "epoch": 0.19363762102351315,
210
+ "grad_norm": 1.323454737663269,
211
+ "learning_rate": 0.0001917241379310345,
212
+ "loss": 0.8488,
213
+ "step": 140
214
+ },
215
+ {
216
+ "epoch": 0.20055325034578148,
217
+ "grad_norm": 2.7075045108795166,
218
+ "learning_rate": 0.00019862068965517243,
219
+ "loss": 0.9631,
220
+ "step": 145
221
+ },
222
+ {
223
+ "epoch": 0.2074688796680498,
224
+ "grad_norm": 2.2683520317077637,
225
+ "learning_rate": 0.0001999953352135947,
226
+ "loss": 0.9498,
227
+ "step": 150
228
+ },
229
+ {
230
+ "epoch": 0.2143845089903181,
231
+ "grad_norm": 8.38696002960205,
232
+ "learning_rate": 0.0001999763852647035,
233
+ "loss": 0.891,
234
+ "step": 155
235
+ },
236
+ {
237
+ "epoch": 0.22130013831258644,
238
+ "grad_norm": 24.307083129882812,
239
+ "learning_rate": 0.00019994286136445976,
240
+ "loss": 0.9308,
241
+ "step": 160
242
+ },
243
+ {
244
+ "epoch": 0.22821576763485477,
245
+ "grad_norm": 2.0212178230285645,
246
+ "learning_rate": 0.0001998947683997744,
247
+ "loss": 0.8901,
248
+ "step": 165
249
+ },
250
+ {
251
+ "epoch": 0.2351313969571231,
252
+ "grad_norm": 1.2989600896835327,
253
+ "learning_rate": 0.00019983211338134828,
254
+ "loss": 0.8546,
255
+ "step": 170
256
+ },
257
+ {
258
+ "epoch": 0.24204702627939143,
259
+ "grad_norm": 1.2097629308700562,
260
+ "learning_rate": 0.00019975490544265012,
261
+ "loss": 0.8543,
262
+ "step": 175
263
+ },
264
+ {
265
+ "epoch": 0.24896265560165975,
266
+ "grad_norm": 30.946725845336914,
267
+ "learning_rate": 0.00019966315583858516,
268
+ "loss": 1.6915,
269
+ "step": 180
270
+ },
271
+ {
272
+ "epoch": 0.25587828492392806,
273
+ "grad_norm": 2.118316173553467,
274
+ "learning_rate": 0.0001995568779438545,
275
+ "loss": 1.0665,
276
+ "step": 185
277
+ },
278
+ {
279
+ "epoch": 0.2627939142461964,
280
+ "grad_norm": 3.086249589920044,
281
+ "learning_rate": 0.00019943608725100532,
282
+ "loss": 0.9988,
283
+ "step": 190
284
+ },
285
+ {
286
+ "epoch": 0.2697095435684647,
287
+ "grad_norm": 1.1766245365142822,
288
+ "learning_rate": 0.00019930080136817255,
289
+ "loss": 0.9133,
290
+ "step": 195
291
+ },
292
+ {
293
+ "epoch": 0.2766251728907331,
294
+ "grad_norm": 1.33064603805542,
295
+ "learning_rate": 0.00019915104001651203,
296
+ "loss": 0.8809,
297
+ "step": 200
298
+ },
299
+ {
300
+ "epoch": 0.2835408022130014,
301
+ "grad_norm": 1.6439151763916016,
302
+ "learning_rate": 0.00019898682502732568,
303
+ "loss": 0.8967,
304
+ "step": 205
305
+ },
306
+ {
307
+ "epoch": 0.29045643153526973,
308
+ "grad_norm": 1.3271840810775757,
309
+ "learning_rate": 0.00019880818033887916,
310
+ "loss": 0.8866,
311
+ "step": 210
312
+ },
313
+ {
314
+ "epoch": 0.29737206085753803,
315
+ "grad_norm": 1.1745598316192627,
316
+ "learning_rate": 0.0001986151319929121,
317
+ "loss": 0.8598,
318
+ "step": 215
319
+ },
320
+ {
321
+ "epoch": 0.30428769017980634,
322
+ "grad_norm": 1.0390416383743286,
323
+ "learning_rate": 0.00019840770813084205,
324
+ "loss": 0.8434,
325
+ "step": 220
326
+ },
327
+ {
328
+ "epoch": 0.3112033195020747,
329
+ "grad_norm": 1.0289931297302246,
330
+ "learning_rate": 0.00019818593898966212,
331
+ "loss": 0.8765,
332
+ "step": 225
333
+ },
334
+ {
335
+ "epoch": 0.318118948824343,
336
+ "grad_norm": 1.1883145570755005,
337
+ "learning_rate": 0.00019794985689753337,
338
+ "loss": 0.8859,
339
+ "step": 230
340
+ },
341
+ {
342
+ "epoch": 0.32503457814661135,
343
+ "grad_norm": 1.2715511322021484,
344
+ "learning_rate": 0.00019769949626907186,
345
+ "loss": 0.8626,
346
+ "step": 235
347
+ },
348
+ {
349
+ "epoch": 0.33195020746887965,
350
+ "grad_norm": 1.287985920906067,
351
+ "learning_rate": 0.00019743489360033231,
352
+ "loss": 0.8805,
353
+ "step": 240
354
+ },
355
+ {
356
+ "epoch": 0.338865836791148,
357
+ "grad_norm": 1.1524231433868408,
358
+ "learning_rate": 0.00019715608746348763,
359
+ "loss": 0.8588,
360
+ "step": 245
361
+ },
362
+ {
363
+ "epoch": 0.3457814661134163,
364
+ "grad_norm": 1.0479854345321655,
365
+ "learning_rate": 0.00019686311850120625,
366
+ "loss": 0.858,
367
+ "step": 250
368
+ },
369
+ {
370
+ "epoch": 0.35269709543568467,
371
+ "grad_norm": 0.9751342535018921,
372
+ "learning_rate": 0.0001965560294207274,
373
+ "loss": 0.8558,
374
+ "step": 255
375
+ },
376
+ {
377
+ "epoch": 0.359612724757953,
378
+ "grad_norm": 0.9835847020149231,
379
+ "learning_rate": 0.00019623486498763555,
380
+ "loss": 0.8755,
381
+ "step": 260
382
+ },
383
+ {
384
+ "epoch": 0.3665283540802213,
385
+ "grad_norm": 3.7135465145111084,
386
+ "learning_rate": 0.00019589967201933471,
387
+ "loss": 0.8584,
388
+ "step": 265
389
+ },
390
+ {
391
+ "epoch": 0.37344398340248963,
392
+ "grad_norm": 1.0380736589431763,
393
+ "learning_rate": 0.00019555049937822384,
394
+ "loss": 0.8544,
395
+ "step": 270
396
+ },
397
+ {
398
+ "epoch": 0.38035961272475793,
399
+ "grad_norm": 1.0324746370315552,
400
+ "learning_rate": 0.00019518739796457366,
401
+ "loss": 0.8673,
402
+ "step": 275
403
+ },
404
+ {
405
+ "epoch": 0.3872752420470263,
406
+ "grad_norm": 1.0108332633972168,
407
+ "learning_rate": 0.00019481042070910705,
408
+ "loss": 0.8443,
409
+ "step": 280
410
+ },
411
+ {
412
+ "epoch": 0.3941908713692946,
413
+ "grad_norm": 0.8845415711402893,
414
+ "learning_rate": 0.00019441962256528292,
415
+ "loss": 0.857,
416
+ "step": 285
417
+ },
418
+ {
419
+ "epoch": 0.40110650069156295,
420
+ "grad_norm": 0.8270080089569092,
421
+ "learning_rate": 0.00019401506050128556,
422
+ "loss": 0.8583,
423
+ "step": 290
424
+ },
425
+ {
426
+ "epoch": 0.40802213001383125,
427
+ "grad_norm": 0.8553124070167542,
428
+ "learning_rate": 0.00019359679349172004,
429
+ "loss": 0.8291,
430
+ "step": 295
431
+ },
432
+ {
433
+ "epoch": 0.4149377593360996,
434
+ "grad_norm": 0.9521012306213379,
435
+ "learning_rate": 0.00019316488250901534,
436
+ "loss": 0.8486,
437
+ "step": 300
438
+ },
439
+ {
440
+ "epoch": 0.4218533886583679,
441
+ "grad_norm": 0.8840038776397705,
442
+ "learning_rate": 0.00019271939051453612,
443
+ "loss": 0.8258,
444
+ "step": 305
445
+ },
446
+ {
447
+ "epoch": 0.4287690179806362,
448
+ "grad_norm": 1.223691463470459,
449
+ "learning_rate": 0.00019226038244940464,
450
+ "loss": 0.8142,
451
+ "step": 310
452
+ },
453
+ {
454
+ "epoch": 0.43568464730290457,
455
+ "grad_norm": 0.8988921642303467,
456
+ "learning_rate": 0.00019178792522503394,
457
+ "loss": 0.8611,
458
+ "step": 315
459
+ },
460
+ {
461
+ "epoch": 0.4426002766251729,
462
+ "grad_norm": 0.813004732131958,
463
+ "learning_rate": 0.000191302087713374,
464
+ "loss": 0.8208,
465
+ "step": 320
466
+ },
467
+ {
468
+ "epoch": 0.44951590594744123,
469
+ "grad_norm": 0.8524804711341858,
470
+ "learning_rate": 0.00019080294073687193,
471
+ "loss": 0.8393,
472
+ "step": 325
473
+ },
474
+ {
475
+ "epoch": 0.45643153526970953,
476
+ "grad_norm": 0.9394051432609558,
477
+ "learning_rate": 0.000190290557058148,
478
+ "loss": 0.8567,
479
+ "step": 330
480
+ },
481
+ {
482
+ "epoch": 0.4633471645919779,
483
+ "grad_norm": 0.9042031168937683,
484
+ "learning_rate": 0.00018976501136938864,
485
+ "loss": 0.8387,
486
+ "step": 335
487
+ },
488
+ {
489
+ "epoch": 0.4702627939142462,
490
+ "grad_norm": 0.7205588221549988,
491
+ "learning_rate": 0.00018922638028145828,
492
+ "loss": 0.8231,
493
+ "step": 340
494
+ },
495
+ {
496
+ "epoch": 0.47717842323651455,
497
+ "grad_norm": 0.798876941204071,
498
+ "learning_rate": 0.0001886747423127316,
499
+ "loss": 0.8254,
500
+ "step": 345
501
+ },
502
+ {
503
+ "epoch": 0.48409405255878285,
504
+ "grad_norm": 0.7704493403434753,
505
+ "learning_rate": 0.00018811017787764747,
506
+ "loss": 0.8244,
507
+ "step": 350
508
+ },
509
+ {
510
+ "epoch": 0.49100968188105115,
511
+ "grad_norm": 0.8552532196044922,
512
+ "learning_rate": 0.00018753276927498659,
513
+ "loss": 0.8347,
514
+ "step": 355
515
+ },
516
+ {
517
+ "epoch": 0.4979253112033195,
518
+ "grad_norm": 0.7718790173530579,
519
+ "learning_rate": 0.00018694260067587463,
520
+ "loss": 0.7962,
521
+ "step": 360
522
+ },
523
+ {
524
+ "epoch": 0.5048409405255878,
525
+ "grad_norm": 0.888421356678009,
526
+ "learning_rate": 0.00018633975811151223,
527
+ "loss": 0.8284,
528
+ "step": 365
529
+ },
530
+ {
531
+ "epoch": 0.5117565698478561,
532
+ "grad_norm": 0.8525059819221497,
533
+ "learning_rate": 0.00018572432946063367,
534
+ "loss": 0.8241,
535
+ "step": 370
536
+ },
537
+ {
538
+ "epoch": 0.5186721991701245,
539
+ "grad_norm": 0.6882660388946533,
540
+ "learning_rate": 0.00018509640443669682,
541
+ "loss": 0.8001,
542
+ "step": 375
543
+ },
544
+ {
545
+ "epoch": 0.5255878284923928,
546
+ "grad_norm": 0.7356276512145996,
547
+ "learning_rate": 0.00018445607457480493,
548
+ "loss": 0.8177,
549
+ "step": 380
550
+ },
551
+ {
552
+ "epoch": 0.5325034578146611,
553
+ "grad_norm": 0.7074828147888184,
554
+ "learning_rate": 0.0001838034332183634,
555
+ "loss": 0.837,
556
+ "step": 385
557
+ },
558
+ {
559
+ "epoch": 0.5394190871369294,
560
+ "grad_norm": 0.7650839686393738,
561
+ "learning_rate": 0.0001831385755054726,
562
+ "loss": 0.8219,
563
+ "step": 390
564
+ },
565
+ {
566
+ "epoch": 0.5463347164591977,
567
+ "grad_norm": 0.6335296630859375,
568
+ "learning_rate": 0.00018246159835505932,
569
+ "loss": 0.8146,
570
+ "step": 395
571
+ },
572
+ {
573
+ "epoch": 0.5532503457814661,
574
+ "grad_norm": 0.8082166314125061,
575
+ "learning_rate": 0.0001817726004527485,
576
+ "loss": 0.8083,
577
+ "step": 400
578
+ },
579
+ {
580
+ "epoch": 0.5601659751037344,
581
+ "grad_norm": 0.6119678616523743,
582
+ "learning_rate": 0.0001810716822364774,
583
+ "loss": 0.7853,
584
+ "step": 405
585
+ },
586
+ {
587
+ "epoch": 0.5670816044260027,
588
+ "grad_norm": 0.7896009683609009,
589
+ "learning_rate": 0.00018035894588185438,
590
+ "loss": 0.7868,
591
+ "step": 410
592
+ },
593
+ {
594
+ "epoch": 0.573997233748271,
595
+ "grad_norm": 0.7086299657821655,
596
+ "learning_rate": 0.0001796344952872643,
597
+ "loss": 0.8234,
598
+ "step": 415
599
+ },
600
+ {
601
+ "epoch": 0.5809128630705395,
602
+ "grad_norm": 0.689249575138092,
603
+ "learning_rate": 0.00017889843605872305,
604
+ "loss": 0.7917,
605
+ "step": 420
606
+ },
607
+ {
608
+ "epoch": 0.5878284923928078,
609
+ "grad_norm": 0.6687580943107605,
610
+ "learning_rate": 0.0001781508754944827,
611
+ "loss": 0.7956,
612
+ "step": 425
613
+ },
614
+ {
615
+ "epoch": 0.5947441217150761,
616
+ "grad_norm": 0.7054949998855591,
617
+ "learning_rate": 0.0001773919225693903,
618
+ "loss": 0.7979,
619
+ "step": 430
620
+ },
621
+ {
622
+ "epoch": 0.6016597510373444,
623
+ "grad_norm": 0.8244301676750183,
624
+ "learning_rate": 0.00017662168791900232,
625
+ "loss": 0.7949,
626
+ "step": 435
627
+ },
628
+ {
629
+ "epoch": 0.6085753803596127,
630
+ "grad_norm": 0.7373748421669006,
631
+ "learning_rate": 0.00017584028382345654,
632
+ "loss": 0.7742,
633
+ "step": 440
634
+ },
635
+ {
636
+ "epoch": 0.6154910096818811,
637
+ "grad_norm": 0.716790497303009,
638
+ "learning_rate": 0.00017504782419110497,
639
+ "loss": 0.8082,
640
+ "step": 445
641
+ },
642
+ {
643
+ "epoch": 0.6224066390041494,
644
+ "grad_norm": 0.7063632011413574,
645
+ "learning_rate": 0.00017424442454190862,
646
+ "loss": 0.7859,
647
+ "step": 450
648
+ },
649
+ {
650
+ "epoch": 0.6293222683264177,
651
+ "grad_norm": 0.8756738901138306,
652
+ "learning_rate": 0.00017343020199059783,
653
+ "loss": 0.791,
654
+ "step": 455
655
+ },
656
+ {
657
+ "epoch": 0.636237897648686,
658
+ "grad_norm": 0.667121946811676,
659
+ "learning_rate": 0.0001726052752296001,
660
+ "loss": 0.8044,
661
+ "step": 460
662
+ },
663
+ {
664
+ "epoch": 0.6431535269709544,
665
+ "grad_norm": 0.7018240690231323,
666
+ "learning_rate": 0.00017176976451173758,
667
+ "loss": 0.7829,
668
+ "step": 465
669
+ },
670
+ {
671
+ "epoch": 0.6500691562932227,
672
+ "grad_norm": 0.6935915350914001,
673
+ "learning_rate": 0.00017092379163269764,
674
+ "loss": 0.7975,
675
+ "step": 470
676
+ },
677
+ {
678
+ "epoch": 0.656984785615491,
679
+ "grad_norm": 0.6710845232009888,
680
+ "learning_rate": 0.00017006747991327796,
681
+ "loss": 0.7777,
682
+ "step": 475
683
+ },
684
+ {
685
+ "epoch": 0.6639004149377593,
686
+ "grad_norm": 0.7099134922027588,
687
+ "learning_rate": 0.00016920095418140977,
688
+ "loss": 0.7755,
689
+ "step": 480
690
+ },
691
+ {
692
+ "epoch": 0.6708160442600276,
693
+ "grad_norm": 0.652553915977478,
694
+ "learning_rate": 0.00016832434075396101,
695
+ "loss": 0.7802,
696
+ "step": 485
697
+ },
698
+ {
699
+ "epoch": 0.677731673582296,
700
+ "grad_norm": 0.6347463130950928,
701
+ "learning_rate": 0.00016743776741832292,
702
+ "loss": 0.7814,
703
+ "step": 490
704
+ },
705
+ {
706
+ "epoch": 0.6846473029045643,
707
+ "grad_norm": 0.5948991179466248,
708
+ "learning_rate": 0.00016654136341378157,
709
+ "loss": 0.7704,
710
+ "step": 495
711
+ },
712
+ {
713
+ "epoch": 0.6915629322268326,
714
+ "grad_norm": 0.6586953401565552,
715
+ "learning_rate": 0.00016563525941267845,
716
+ "loss": 0.7781,
717
+ "step": 500
718
+ },
719
+ {
720
+ "epoch": 0.6984785615491009,
721
+ "grad_norm": 0.6398725509643555,
722
+ "learning_rate": 0.00016471958750136176,
723
+ "loss": 0.7707,
724
+ "step": 505
725
+ },
726
+ {
727
+ "epoch": 0.7053941908713693,
728
+ "grad_norm": 0.6144907474517822,
729
+ "learning_rate": 0.00016379448116093156,
730
+ "loss": 0.7714,
731
+ "step": 510
732
+ },
733
+ {
734
+ "epoch": 0.7123098201936376,
735
+ "grad_norm": 0.6330462694168091,
736
+ "learning_rate": 0.00016286007524778185,
737
+ "loss": 0.7653,
738
+ "step": 515
739
+ },
740
+ {
741
+ "epoch": 0.719225449515906,
742
+ "grad_norm": 0.5762836933135986,
743
+ "learning_rate": 0.00016191650597394198,
744
+ "loss": 0.7715,
745
+ "step": 520
746
+ },
747
+ {
748
+ "epoch": 0.7261410788381742,
749
+ "grad_norm": 0.578916609287262,
750
+ "learning_rate": 0.00016096391088722047,
751
+ "loss": 0.785,
752
+ "step": 525
753
+ },
754
+ {
755
+ "epoch": 0.7330567081604425,
756
+ "grad_norm": 0.5828131437301636,
757
+ "learning_rate": 0.0001600024288511541,
758
+ "loss": 0.7424,
759
+ "step": 530
760
+ },
761
+ {
762
+ "epoch": 0.739972337482711,
763
+ "grad_norm": 0.5606003999710083,
764
+ "learning_rate": 0.00015903220002476515,
765
+ "loss": 0.7782,
766
+ "step": 535
767
+ },
768
+ {
769
+ "epoch": 0.7468879668049793,
770
+ "grad_norm": 0.5754717588424683,
771
+ "learning_rate": 0.0001580533658421302,
772
+ "loss": 0.7865,
773
+ "step": 540
774
+ },
775
+ {
776
+ "epoch": 0.7538035961272476,
777
+ "grad_norm": 0.680016279220581,
778
+ "learning_rate": 0.0001570660689917623,
779
+ "loss": 0.7637,
780
+ "step": 545
781
+ },
782
+ {
783
+ "epoch": 0.7607192254495159,
784
+ "grad_norm": 0.6306326985359192,
785
+ "learning_rate": 0.00015607045339581096,
786
+ "loss": 0.7528,
787
+ "step": 550
788
+ },
789
+ {
790
+ "epoch": 0.7676348547717843,
791
+ "grad_norm": 0.5506445169448853,
792
+ "learning_rate": 0.00015506666418908203,
793
+ "loss": 0.767,
794
+ "step": 555
795
+ },
796
+ {
797
+ "epoch": 0.7745504840940526,
798
+ "grad_norm": 0.6151379346847534,
799
+ "learning_rate": 0.00015405484769788073,
800
+ "loss": 0.7511,
801
+ "step": 560
802
+ },
803
+ {
804
+ "epoch": 0.7814661134163209,
805
+ "grad_norm": 0.6520763635635376,
806
+ "learning_rate": 0.00015303515141868116,
807
+ "loss": 0.7529,
808
+ "step": 565
809
+ },
810
+ {
811
+ "epoch": 0.7883817427385892,
812
+ "grad_norm": 0.5401438474655151,
813
+ "learning_rate": 0.00015200772399662514,
814
+ "loss": 0.7754,
815
+ "step": 570
816
+ },
817
+ {
818
+ "epoch": 0.7952973720608575,
819
+ "grad_norm": 0.6025466322898865,
820
+ "learning_rate": 0.00015097271520385366,
821
+ "loss": 0.7577,
822
+ "step": 575
823
+ },
824
+ {
825
+ "epoch": 0.8022130013831259,
826
+ "grad_norm": 0.6601846218109131,
827
+ "learning_rate": 0.00014993027591767396,
828
+ "loss": 0.7406,
829
+ "step": 580
830
+ },
831
+ {
832
+ "epoch": 0.8091286307053942,
833
+ "grad_norm": 0.6068835854530334,
834
+ "learning_rate": 0.0001488805580985655,
835
+ "loss": 0.764,
836
+ "step": 585
837
+ },
838
+ {
839
+ "epoch": 0.8160442600276625,
840
+ "grad_norm": 0.586649477481842,
841
+ "learning_rate": 0.00014782371476802824,
842
+ "loss": 0.7547,
843
+ "step": 590
844
+ },
845
+ {
846
+ "epoch": 0.8229598893499308,
847
+ "grad_norm": 0.4942811131477356,
848
+ "learning_rate": 0.00014675989998627598,
849
+ "loss": 0.7539,
850
+ "step": 595
851
+ },
852
+ {
853
+ "epoch": 0.8298755186721992,
854
+ "grad_norm": 0.5191232562065125,
855
+ "learning_rate": 0.00014568926882977832,
856
+ "loss": 0.75,
857
+ "step": 600
858
+ },
859
+ {
860
+ "epoch": 0.8367911479944675,
861
+ "grad_norm": 0.5124319195747375,
862
+ "learning_rate": 0.00014461197736865481,
863
+ "loss": 0.7207,
864
+ "step": 605
865
+ },
866
+ {
867
+ "epoch": 0.8437067773167358,
868
+ "grad_norm": 0.5561709403991699,
869
+ "learning_rate": 0.00014352818264392364,
870
+ "loss": 0.7504,
871
+ "step": 610
872
+ },
873
+ {
874
+ "epoch": 0.8506224066390041,
875
+ "grad_norm": 0.5596902370452881,
876
+ "learning_rate": 0.00014243804264460957,
877
+ "loss": 0.7634,
878
+ "step": 615
879
+ },
880
+ {
881
+ "epoch": 0.8575380359612724,
882
+ "grad_norm": 0.5537763237953186,
883
+ "learning_rate": 0.00014134171628471276,
884
+ "loss": 0.7293,
885
+ "step": 620
886
+ },
887
+ {
888
+ "epoch": 0.8644536652835408,
889
+ "grad_norm": 0.6073982119560242,
890
+ "learning_rate": 0.00014023936338004373,
891
+ "loss": 0.7358,
892
+ "step": 625
893
+ },
894
+ {
895
+ "epoch": 0.8713692946058091,
896
+ "grad_norm": 0.5265364050865173,
897
+ "learning_rate": 0.00013913114462492601,
898
+ "loss": 0.7415,
899
+ "step": 630
900
+ },
901
+ {
902
+ "epoch": 0.8782849239280774,
903
+ "grad_norm": 0.5465463399887085,
904
+ "learning_rate": 0.00013801722156877143,
905
+ "loss": 0.7351,
906
+ "step": 635
907
+ },
908
+ {
909
+ "epoch": 0.8852005532503457,
910
+ "grad_norm": 0.5381340384483337,
911
+ "learning_rate": 0.00013689775659253006,
912
+ "loss": 0.7403,
913
+ "step": 640
914
+ },
915
+ {
916
+ "epoch": 0.8921161825726142,
917
+ "grad_norm": 0.5682520270347595,
918
+ "learning_rate": 0.00013577291288501952,
919
+ "loss": 0.7299,
920
+ "step": 645
921
+ },
922
+ {
923
+ "epoch": 0.8990318118948825,
924
+ "grad_norm": 0.538758397102356,
925
+ "learning_rate": 0.00013464285441913636,
926
+ "loss": 0.7501,
927
+ "step": 650
928
+ },
929
+ {
930
+ "epoch": 0.9059474412171508,
931
+ "grad_norm": 0.6069577932357788,
932
+ "learning_rate": 0.00013350774592795292,
933
+ "loss": 0.7373,
934
+ "step": 655
935
+ },
936
+ {
937
+ "epoch": 0.9128630705394191,
938
+ "grad_norm": 0.5356409549713135,
939
+ "learning_rate": 0.0001323677528807036,
940
+ "loss": 0.7343,
941
+ "step": 660
942
+ },
943
+ {
944
+ "epoch": 0.9197786998616874,
945
+ "grad_norm": 0.5176509618759155,
946
+ "learning_rate": 0.00013122304145866381,
947
+ "loss": 0.7298,
948
+ "step": 665
949
+ },
950
+ {
951
+ "epoch": 0.9266943291839558,
952
+ "grad_norm": 0.6070849895477295,
953
+ "learning_rate": 0.00013007377853092503,
954
+ "loss": 0.7352,
955
+ "step": 670
956
+ },
957
+ {
958
+ "epoch": 0.9336099585062241,
959
+ "grad_norm": 0.5752330422401428,
960
+ "learning_rate": 0.00012892013163006962,
961
+ "loss": 0.7323,
962
+ "step": 675
963
+ },
964
+ {
965
+ "epoch": 0.9405255878284924,
966
+ "grad_norm": 0.550092339515686,
967
+ "learning_rate": 0.00012776226892774903,
968
+ "loss": 0.7437,
969
+ "step": 680
970
+ },
971
+ {
972
+ "epoch": 0.9474412171507607,
973
+ "grad_norm": 0.5363165736198425,
974
+ "learning_rate": 0.00012660035921016854,
975
+ "loss": 0.7199,
976
+ "step": 685
977
+ },
978
+ {
979
+ "epoch": 0.9543568464730291,
980
+ "grad_norm": 0.5486807823181152,
981
+ "learning_rate": 0.00012543457185348298,
982
+ "loss": 0.7159,
983
+ "step": 690
984
+ },
985
+ {
986
+ "epoch": 0.9612724757952974,
987
+ "grad_norm": 0.6245793104171753,
988
+ "learning_rate": 0.00012426507679910576,
989
+ "loss": 0.7295,
990
+ "step": 695
991
+ },
992
+ {
993
+ "epoch": 0.9681881051175657,
994
+ "grad_norm": 0.5306342244148254,
995
+ "learning_rate": 0.00012309204452893606,
996
+ "loss": 0.7239,
997
+ "step": 700
998
+ },
999
+ {
1000
+ "epoch": 0.975103734439834,
1001
+ "grad_norm": 0.5488132238388062,
1002
+ "learning_rate": 0.00012191564604050683,
1003
+ "loss": 0.7027,
1004
+ "step": 705
1005
+ },
1006
+ {
1007
+ "epoch": 0.9820193637621023,
1008
+ "grad_norm": 0.5506658554077148,
1009
+ "learning_rate": 0.00012073605282205802,
1010
+ "loss": 0.7397,
1011
+ "step": 710
1012
+ },
1013
+ {
1014
+ "epoch": 0.9889349930843707,
1015
+ "grad_norm": 0.5438380241394043,
1016
+ "learning_rate": 0.00011955343682753794,
1017
+ "loss": 0.7241,
1018
+ "step": 715
1019
+ },
1020
+ {
1021
+ "epoch": 0.995850622406639,
1022
+ "grad_norm": 0.5309740900993347,
1023
+ "learning_rate": 0.0001183679704515368,
1024
+ "loss": 0.7209,
1025
+ "step": 720
1026
+ },
1027
+ {
1028
+ "epoch": 1.0027662517289073,
1029
+ "grad_norm": 0.6508172750473022,
1030
+ "learning_rate": 0.00011717982650415624,
1031
+ "loss": 0.6672,
1032
+ "step": 725
1033
+ },
1034
+ {
1035
+ "epoch": 1.0096818810511756,
1036
+ "grad_norm": 0.6566136479377747,
1037
+ "learning_rate": 0.00011598917818581791,
1038
+ "loss": 0.5846,
1039
+ "step": 730
1040
+ },
1041
+ {
1042
+ "epoch": 1.016597510373444,
1043
+ "grad_norm": 0.5107012987136841,
1044
+ "learning_rate": 0.00011479619906201557,
1045
+ "loss": 0.5685,
1046
+ "step": 735
1047
+ },
1048
+ {
1049
+ "epoch": 1.0235131396957122,
1050
+ "grad_norm": 0.48931655287742615,
1051
+ "learning_rate": 0.00011360106303801364,
1052
+ "loss": 0.5846,
1053
+ "step": 740
1054
+ },
1055
+ {
1056
+ "epoch": 1.0304287690179805,
1057
+ "grad_norm": 0.5219966769218445,
1058
+ "learning_rate": 0.00011240394433349637,
1059
+ "loss": 0.5588,
1060
+ "step": 745
1061
+ },
1062
+ {
1063
+ "epoch": 1.037344398340249,
1064
+ "grad_norm": 0.5277289152145386,
1065
+ "learning_rate": 0.00011120501745717112,
1066
+ "loss": 0.5727,
1067
+ "step": 750
1068
+ },
1069
+ {
1070
+ "epoch": 1.0442600276625174,
1071
+ "grad_norm": 0.5424395799636841,
1072
+ "learning_rate": 0.00011000445718132966,
1073
+ "loss": 0.566,
1074
+ "step": 755
1075
+ },
1076
+ {
1077
+ "epoch": 1.0511756569847857,
1078
+ "grad_norm": 0.5607298612594604,
1079
+ "learning_rate": 0.00010880243851637078,
1080
+ "loss": 0.57,
1081
+ "step": 760
1082
+ },
1083
+ {
1084
+ "epoch": 1.058091286307054,
1085
+ "grad_norm": 0.5789066553115845,
1086
+ "learning_rate": 0.00010759913668528841,
1087
+ "loss": 0.5659,
1088
+ "step": 765
1089
+ },
1090
+ {
1091
+ "epoch": 1.0650069156293223,
1092
+ "grad_norm": 0.5418556928634644,
1093
+ "learning_rate": 0.00010639472709812861,
1094
+ "loss": 0.573,
1095
+ "step": 770
1096
+ },
1097
+ {
1098
+ "epoch": 1.0719225449515906,
1099
+ "grad_norm": 0.49530017375946045,
1100
+ "learning_rate": 0.0001051893853264195,
1101
+ "loss": 0.5695,
1102
+ "step": 775
1103
+ },
1104
+ {
1105
+ "epoch": 1.0788381742738589,
1106
+ "grad_norm": 0.5037497878074646,
1107
+ "learning_rate": 0.00010398328707757738,
1108
+ "loss": 0.5651,
1109
+ "step": 780
1110
+ },
1111
+ {
1112
+ "epoch": 1.0857538035961272,
1113
+ "grad_norm": 0.5208268761634827,
1114
+ "learning_rate": 0.00010277660816929313,
1115
+ "loss": 0.5883,
1116
+ "step": 785
1117
+ },
1118
+ {
1119
+ "epoch": 1.0926694329183957,
1120
+ "grad_norm": 0.5543485283851624,
1121
+ "learning_rate": 0.00010156952450390269,
1122
+ "loss": 0.5537,
1123
+ "step": 790
1124
+ },
1125
+ {
1126
+ "epoch": 1.099585062240664,
1127
+ "grad_norm": 0.6337606310844421,
1128
+ "learning_rate": 0.00010036221204274512,
1129
+ "loss": 0.5649,
1130
+ "step": 795
1131
+ },
1132
+ {
1133
+ "epoch": 1.1065006915629323,
1134
+ "grad_norm": 0.4707985818386078,
1135
+ "learning_rate": 9.915484678051175e-05,
1136
+ "loss": 0.5471,
1137
+ "step": 800
1138
+ },
1139
+ {
1140
+ "epoch": 1.1134163208852006,
1141
+ "grad_norm": 0.5109753608703613,
1142
+ "learning_rate": 9.794760471959116e-05,
1143
+ "loss": 0.5663,
1144
+ "step": 805
1145
+ },
1146
+ {
1147
+ "epoch": 1.120331950207469,
1148
+ "grad_norm": 0.5100296139717102,
1149
+ "learning_rate": 9.674066184441221e-05,
1150
+ "loss": 0.5713,
1151
+ "step": 810
1152
+ },
1153
+ {
1154
+ "epoch": 1.1272475795297372,
1155
+ "grad_norm": 0.5414464473724365,
1156
+ "learning_rate": 9.553419409579035e-05,
1157
+ "loss": 0.5611,
1158
+ "step": 815
1159
+ },
1160
+ {
1161
+ "epoch": 1.1341632088520055,
1162
+ "grad_norm": 0.5717695355415344,
1163
+ "learning_rate": 9.432837734527995e-05,
1164
+ "loss": 0.5817,
1165
+ "step": 820
1166
+ },
1167
+ {
1168
+ "epoch": 1.1410788381742738,
1169
+ "grad_norm": 0.5524587035179138,
1170
+ "learning_rate": 9.312338736953683e-05,
1171
+ "loss": 0.5757,
1172
+ "step": 825
1173
+ },
1174
+ {
1175
+ "epoch": 1.147994467496542,
1176
+ "grad_norm": 0.5250436663627625,
1177
+ "learning_rate": 9.191939982469458e-05,
1178
+ "loss": 0.569,
1179
+ "step": 830
1180
+ },
1181
+ {
1182
+ "epoch": 1.1549100968188104,
1183
+ "grad_norm": 0.4710783064365387,
1184
+ "learning_rate": 9.071659022075849e-05,
1185
+ "loss": 0.565,
1186
+ "step": 835
1187
+ },
1188
+ {
1189
+ "epoch": 1.161825726141079,
1190
+ "grad_norm": 0.4436459541320801,
1191
+ "learning_rate": 8.951513389602076e-05,
1192
+ "loss": 0.5666,
1193
+ "step": 840
1194
+ },
1195
+ {
1196
+ "epoch": 1.1687413554633472,
1197
+ "grad_norm": 0.5180997252464294,
1198
+ "learning_rate": 8.831520599150083e-05,
1199
+ "loss": 0.5595,
1200
+ "step": 845
1201
+ },
1202
+ {
1203
+ "epoch": 1.1756569847856155,
1204
+ "grad_norm": 0.49515190720558167,
1205
+ "learning_rate": 8.71169814254142e-05,
1206
+ "loss": 0.584,
1207
+ "step": 850
1208
+ },
1209
+ {
1210
+ "epoch": 1.1825726141078838,
1211
+ "grad_norm": 0.5082345008850098,
1212
+ "learning_rate": 8.592063486767406e-05,
1213
+ "loss": 0.5687,
1214
+ "step": 855
1215
+ },
1216
+ {
1217
+ "epoch": 1.1894882434301521,
1218
+ "grad_norm": 0.5054699182510376,
1219
+ "learning_rate": 8.472634071442896e-05,
1220
+ "loss": 0.5796,
1221
+ "step": 860
1222
+ },
1223
+ {
1224
+ "epoch": 1.1964038727524204,
1225
+ "grad_norm": 0.4742473065853119,
1226
+ "learning_rate": 8.353427306264032e-05,
1227
+ "loss": 0.5575,
1228
+ "step": 865
1229
+ },
1230
+ {
1231
+ "epoch": 1.2033195020746887,
1232
+ "grad_norm": 0.46908038854599,
1233
+ "learning_rate": 8.23446056847037e-05,
1234
+ "loss": 0.5654,
1235
+ "step": 870
1236
+ },
1237
+ {
1238
+ "epoch": 1.210235131396957,
1239
+ "grad_norm": 0.4599679708480835,
1240
+ "learning_rate": 8.115751200311725e-05,
1241
+ "loss": 0.5452,
1242
+ "step": 875
1243
+ },
1244
+ {
1245
+ "epoch": 1.2171507607192256,
1246
+ "grad_norm": 0.48915913701057434,
1247
+ "learning_rate": 7.99731650652013e-05,
1248
+ "loss": 0.5667,
1249
+ "step": 880
1250
+ },
1251
+ {
1252
+ "epoch": 1.2240663900414939,
1253
+ "grad_norm": 0.5099295377731323,
1254
+ "learning_rate": 7.879173751787259e-05,
1255
+ "loss": 0.5673,
1256
+ "step": 885
1257
+ },
1258
+ {
1259
+ "epoch": 1.2309820193637622,
1260
+ "grad_norm": 0.49911564588546753,
1261
+ "learning_rate": 7.761340158247674e-05,
1262
+ "loss": 0.5695,
1263
+ "step": 890
1264
+ },
1265
+ {
1266
+ "epoch": 1.2378976486860305,
1267
+ "grad_norm": 0.4832319915294647,
1268
+ "learning_rate": 7.64383290296829e-05,
1269
+ "loss": 0.5477,
1270
+ "step": 895
1271
+ },
1272
+ {
1273
+ "epoch": 1.2448132780082988,
1274
+ "grad_norm": 0.4508809447288513,
1275
+ "learning_rate": 7.526669115444414e-05,
1276
+ "loss": 0.5738,
1277
+ "step": 900
1278
+ },
1279
+ {
1280
+ "epoch": 1.251728907330567,
1281
+ "grad_norm": 0.5219544768333435,
1282
+ "learning_rate": 7.409865875102704e-05,
1283
+ "loss": 0.5581,
1284
+ "step": 905
1285
+ },
1286
+ {
1287
+ "epoch": 1.2586445366528354,
1288
+ "grad_norm": 0.4636399745941162,
1289
+ "learning_rate": 7.293440208811435e-05,
1290
+ "loss": 0.5593,
1291
+ "step": 910
1292
+ },
1293
+ {
1294
+ "epoch": 1.2655601659751037,
1295
+ "grad_norm": 0.4862774908542633,
1296
+ "learning_rate": 7.177409088398425e-05,
1297
+ "loss": 0.5481,
1298
+ "step": 915
1299
+ },
1300
+ {
1301
+ "epoch": 1.272475795297372,
1302
+ "grad_norm": 0.5330405235290527,
1303
+ "learning_rate": 7.06178942817699e-05,
1304
+ "loss": 0.5595,
1305
+ "step": 920
1306
+ },
1307
+ {
1308
+ "epoch": 1.2793914246196403,
1309
+ "grad_norm": 0.49150362610816956,
1310
+ "learning_rate": 6.946598082480268e-05,
1311
+ "loss": 0.5429,
1312
+ "step": 925
1313
+ },
1314
+ {
1315
+ "epoch": 1.2863070539419086,
1316
+ "grad_norm": 0.5385686755180359,
1317
+ "learning_rate": 6.831851843204308e-05,
1318
+ "loss": 0.5692,
1319
+ "step": 930
1320
+ },
1321
+ {
1322
+ "epoch": 1.293222683264177,
1323
+ "grad_norm": 0.487090528011322,
1324
+ "learning_rate": 6.71756743736024e-05,
1325
+ "loss": 0.5484,
1326
+ "step": 935
1327
+ },
1328
+ {
1329
+ "epoch": 1.3001383125864454,
1330
+ "grad_norm": 0.5285480618476868,
1331
+ "learning_rate": 6.603761524635914e-05,
1332
+ "loss": 0.5563,
1333
+ "step": 940
1334
+ },
1335
+ {
1336
+ "epoch": 1.3070539419087137,
1337
+ "grad_norm": 0.48829564452171326,
1338
+ "learning_rate": 6.490450694967358e-05,
1339
+ "loss": 0.5606,
1340
+ "step": 945
1341
+ },
1342
+ {
1343
+ "epoch": 1.313969571230982,
1344
+ "grad_norm": 0.4818781912326813,
1345
+ "learning_rate": 6.377651466120391e-05,
1346
+ "loss": 0.5538,
1347
+ "step": 950
1348
+ },
1349
+ {
1350
+ "epoch": 1.3208852005532503,
1351
+ "grad_norm": 0.47652438282966614,
1352
+ "learning_rate": 6.265380281282762e-05,
1353
+ "loss": 0.5584,
1354
+ "step": 955
1355
+ },
1356
+ {
1357
+ "epoch": 1.3278008298755186,
1358
+ "grad_norm": 0.47311243414878845,
1359
+ "learning_rate": 6.15365350666718e-05,
1360
+ "loss": 0.5409,
1361
+ "step": 960
1362
+ },
1363
+ {
1364
+ "epoch": 1.334716459197787,
1365
+ "grad_norm": 0.46478375792503357,
1366
+ "learning_rate": 6.042487429125516e-05,
1367
+ "loss": 0.5554,
1368
+ "step": 965
1369
+ },
1370
+ {
1371
+ "epoch": 1.3416320885200554,
1372
+ "grad_norm": 0.4783475399017334,
1373
+ "learning_rate": 5.931898253774628e-05,
1374
+ "loss": 0.5465,
1375
+ "step": 970
1376
+ },
1377
+ {
1378
+ "epoch": 1.3485477178423237,
1379
+ "grad_norm": 0.48976966738700867,
1380
+ "learning_rate": 5.821902101634069e-05,
1381
+ "loss": 0.5563,
1382
+ "step": 975
1383
+ },
1384
+ {
1385
+ "epoch": 1.355463347164592,
1386
+ "grad_norm": 0.4838036298751831,
1387
+ "learning_rate": 5.7125150072760635e-05,
1388
+ "loss": 0.5628,
1389
+ "step": 980
1390
+ },
1391
+ {
1392
+ "epoch": 1.3623789764868603,
1393
+ "grad_norm": 0.46755191683769226,
1394
+ "learning_rate": 5.603752916488085e-05,
1395
+ "loss": 0.5472,
1396
+ "step": 985
1397
+ },
1398
+ {
1399
+ "epoch": 1.3692946058091287,
1400
+ "grad_norm": 0.50596022605896,
1401
+ "learning_rate": 5.4956316839483734e-05,
1402
+ "loss": 0.5632,
1403
+ "step": 990
1404
+ },
1405
+ {
1406
+ "epoch": 1.376210235131397,
1407
+ "grad_norm": 0.49392423033714294,
1408
+ "learning_rate": 5.388167070914738e-05,
1409
+ "loss": 0.5363,
1410
+ "step": 995
1411
+ },
1412
+ {
1413
+ "epoch": 1.3831258644536653,
1414
+ "grad_norm": 0.4692226052284241,
1415
+ "learning_rate": 5.281374742926987e-05,
1416
+ "loss": 0.536,
1417
+ "step": 1000
1418
+ },
1419
+ {
1420
+ "epoch": 1.3900414937759336,
1421
+ "grad_norm": 0.5283923745155334,
1422
+ "learning_rate": 5.175270267523278e-05,
1423
+ "loss": 0.5553,
1424
+ "step": 1005
1425
+ },
1426
+ {
1427
+ "epoch": 1.3969571230982019,
1428
+ "grad_norm": 0.47653043270111084,
1429
+ "learning_rate": 5.069869111970793e-05,
1430
+ "loss": 0.5492,
1431
+ "step": 1010
1432
+ },
1433
+ {
1434
+ "epoch": 1.4038727524204702,
1435
+ "grad_norm": 0.45839253067970276,
1436
+ "learning_rate": 4.965186641011013e-05,
1437
+ "loss": 0.5297,
1438
+ "step": 1015
1439
+ },
1440
+ {
1441
+ "epoch": 1.4107883817427385,
1442
+ "grad_norm": 0.4624306261539459,
1443
+ "learning_rate": 4.861238114619929e-05,
1444
+ "loss": 0.5384,
1445
+ "step": 1020
1446
+ },
1447
+ {
1448
+ "epoch": 1.417704011065007,
1449
+ "grad_norm": 0.48706522583961487,
1450
+ "learning_rate": 4.75803868578355e-05,
1451
+ "loss": 0.5369,
1452
+ "step": 1025
1453
+ },
1454
+ {
1455
+ "epoch": 1.4246196403872753,
1456
+ "grad_norm": 0.4311310350894928,
1457
+ "learning_rate": 4.655603398288979e-05,
1458
+ "loss": 0.5276,
1459
+ "step": 1030
1460
+ },
1461
+ {
1462
+ "epoch": 1.4315352697095436,
1463
+ "grad_norm": 0.47203701734542847,
1464
+ "learning_rate": 4.5539471845314304e-05,
1465
+ "loss": 0.5347,
1466
+ "step": 1035
1467
+ },
1468
+ {
1469
+ "epoch": 1.438450899031812,
1470
+ "grad_norm": 0.46674981713294983,
1471
+ "learning_rate": 4.453084863337471e-05,
1472
+ "loss": 0.5299,
1473
+ "step": 1040
1474
+ },
1475
+ {
1476
+ "epoch": 1.4453665283540802,
1477
+ "grad_norm": 0.42725497484207153,
1478
+ "learning_rate": 4.353031137804821e-05,
1479
+ "loss": 0.5369,
1480
+ "step": 1045
1481
+ },
1482
+ {
1483
+ "epoch": 1.4522821576763485,
1484
+ "grad_norm": 0.4412887990474701,
1485
+ "learning_rate": 4.253800593159029e-05,
1486
+ "loss": 0.5418,
1487
+ "step": 1050
1488
+ },
1489
+ {
1490
+ "epoch": 1.4591977869986168,
1491
+ "grad_norm": 0.45071831345558167,
1492
+ "learning_rate": 4.155407694627322e-05,
1493
+ "loss": 0.5551,
1494
+ "step": 1055
1495
+ },
1496
+ {
1497
+ "epoch": 1.4661134163208853,
1498
+ "grad_norm": 0.44687119126319885,
1499
+ "learning_rate": 4.057866785329959e-05,
1500
+ "loss": 0.5424,
1501
+ "step": 1060
1502
+ },
1503
+ {
1504
+ "epoch": 1.4730290456431536,
1505
+ "grad_norm": 0.45058682560920715,
1506
+ "learning_rate": 3.96119208418937e-05,
1507
+ "loss": 0.5524,
1508
+ "step": 1065
1509
+ },
1510
+ {
1511
+ "epoch": 1.479944674965422,
1512
+ "grad_norm": 0.5045320391654968,
1513
+ "learning_rate": 3.8653976838574104e-05,
1514
+ "loss": 0.5403,
1515
+ "step": 1070
1516
+ },
1517
+ {
1518
+ "epoch": 1.4868603042876902,
1519
+ "grad_norm": 0.4632035791873932,
1520
+ "learning_rate": 3.770497548661021e-05,
1521
+ "loss": 0.5346,
1522
+ "step": 1075
1523
+ },
1524
+ {
1525
+ "epoch": 1.4937759336099585,
1526
+ "grad_norm": 0.4648893177509308,
1527
+ "learning_rate": 3.676505512566597e-05,
1528
+ "loss": 0.5423,
1529
+ "step": 1080
1530
+ },
1531
+ {
1532
+ "epoch": 1.5006915629322268,
1533
+ "grad_norm": 0.4647049605846405,
1534
+ "learning_rate": 3.5834352771633475e-05,
1535
+ "loss": 0.5319,
1536
+ "step": 1085
1537
+ },
1538
+ {
1539
+ "epoch": 1.5076071922544951,
1540
+ "grad_norm": 0.45878130197525024,
1541
+ "learning_rate": 3.491300409665963e-05,
1542
+ "loss": 0.533,
1543
+ "step": 1090
1544
+ },
1545
+ {
1546
+ "epoch": 1.5145228215767634,
1547
+ "grad_norm": 0.4348316192626953,
1548
+ "learning_rate": 3.4001143409368773e-05,
1549
+ "loss": 0.5111,
1550
+ "step": 1095
1551
+ },
1552
+ {
1553
+ "epoch": 1.5214384508990317,
1554
+ "grad_norm": 0.47867557406425476,
1555
+ "learning_rate": 3.309890363528386e-05,
1556
+ "loss": 0.527,
1557
+ "step": 1100
1558
+ },
1559
+ {
1560
+ "epoch": 1.5283540802213,
1561
+ "grad_norm": 0.47667166590690613,
1562
+ "learning_rate": 3.220641629744947e-05,
1563
+ "loss": 0.5184,
1564
+ "step": 1105
1565
+ },
1566
+ {
1567
+ "epoch": 1.5352697095435683,
1568
+ "grad_norm": 0.4480649530887604,
1569
+ "learning_rate": 3.132381149725916e-05,
1570
+ "loss": 0.5218,
1571
+ "step": 1110
1572
+ },
1573
+ {
1574
+ "epoch": 1.5421853388658366,
1575
+ "grad_norm": 0.4330606460571289,
1576
+ "learning_rate": 3.0451217895489992e-05,
1577
+ "loss": 0.5317,
1578
+ "step": 1115
1579
+ },
1580
+ {
1581
+ "epoch": 1.5491009681881052,
1582
+ "grad_norm": 0.45356714725494385,
1583
+ "learning_rate": 2.9588762693547355e-05,
1584
+ "loss": 0.5307,
1585
+ "step": 1120
1586
+ },
1587
+ {
1588
+ "epoch": 1.5560165975103735,
1589
+ "grad_norm": 0.46869832277297974,
1590
+ "learning_rate": 2.8736571614922046e-05,
1591
+ "loss": 0.5231,
1592
+ "step": 1125
1593
+ },
1594
+ {
1595
+ "epoch": 1.5629322268326418,
1596
+ "grad_norm": 0.5013293623924255,
1597
+ "learning_rate": 2.7894768886863233e-05,
1598
+ "loss": 0.5272,
1599
+ "step": 1130
1600
+ },
1601
+ {
1602
+ "epoch": 1.56984785615491,
1603
+ "grad_norm": 0.44263824820518494,
1604
+ "learning_rate": 2.7063477222269306e-05,
1605
+ "loss": 0.53,
1606
+ "step": 1135
1607
+ },
1608
+ {
1609
+ "epoch": 1.5767634854771784,
1610
+ "grad_norm": 0.45062586665153503,
1611
+ "learning_rate": 2.6242817801799557e-05,
1612
+ "loss": 0.5116,
1613
+ "step": 1140
1614
+ },
1615
+ {
1616
+ "epoch": 1.583679114799447,
1617
+ "grad_norm": 0.4699437618255615,
1618
+ "learning_rate": 2.5432910256209187e-05,
1619
+ "loss": 0.5314,
1620
+ "step": 1145
1621
+ },
1622
+ {
1623
+ "epoch": 1.5905947441217152,
1624
+ "grad_norm": 0.45320945978164673,
1625
+ "learning_rate": 2.4633872648910252e-05,
1626
+ "loss": 0.5244,
1627
+ "step": 1150
1628
+ },
1629
+ {
1630
+ "epoch": 1.5975103734439835,
1631
+ "grad_norm": 0.45921820402145386,
1632
+ "learning_rate": 2.3845821458761063e-05,
1633
+ "loss": 0.5265,
1634
+ "step": 1155
1635
+ },
1636
+ {
1637
+ "epoch": 1.6044260027662518,
1638
+ "grad_norm": 0.4836861789226532,
1639
+ "learning_rate": 2.3068871563086757e-05,
1640
+ "loss": 0.5397,
1641
+ "step": 1160
1642
+ },
1643
+ {
1644
+ "epoch": 1.61134163208852,
1645
+ "grad_norm": 0.4829198122024536,
1646
+ "learning_rate": 2.230313622093295e-05,
1647
+ "loss": 0.5247,
1648
+ "step": 1165
1649
+ },
1650
+ {
1651
+ "epoch": 1.6182572614107884,
1652
+ "grad_norm": 0.42497992515563965,
1653
+ "learning_rate": 2.154872705655566e-05,
1654
+ "loss": 0.4998,
1655
+ "step": 1170
1656
+ },
1657
+ {
1658
+ "epoch": 1.6251728907330567,
1659
+ "grad_norm": 0.4427035450935364,
1660
+ "learning_rate": 2.0805754043149394e-05,
1661
+ "loss": 0.52,
1662
+ "step": 1175
1663
+ },
1664
+ {
1665
+ "epoch": 1.632088520055325,
1666
+ "grad_norm": 0.4457587003707886,
1667
+ "learning_rate": 2.0074325486815883e-05,
1668
+ "loss": 0.4931,
1669
+ "step": 1180
1670
+ },
1671
+ {
1672
+ "epoch": 1.6390041493775933,
1673
+ "grad_norm": 0.46790486574172974,
1674
+ "learning_rate": 1.9354548010775896e-05,
1675
+ "loss": 0.529,
1676
+ "step": 1185
1677
+ },
1678
+ {
1679
+ "epoch": 1.6459197786998616,
1680
+ "grad_norm": 0.4801090955734253,
1681
+ "learning_rate": 1.864652653982636e-05,
1682
+ "loss": 0.5188,
1683
+ "step": 1190
1684
+ },
1685
+ {
1686
+ "epoch": 1.65283540802213,
1687
+ "grad_norm": 0.4337711036205292,
1688
+ "learning_rate": 1.7950364285044996e-05,
1689
+ "loss": 0.5105,
1690
+ "step": 1195
1691
+ },
1692
+ {
1693
+ "epoch": 1.6597510373443982,
1694
+ "grad_norm": 0.45500195026397705,
1695
+ "learning_rate": 1.7266162728744993e-05,
1696
+ "loss": 0.5049,
1697
+ "step": 1200
1698
+ },
1699
+ {
1700
+ "epoch": 1.6666666666666665,
1701
+ "grad_norm": 0.4910541772842407,
1702
+ "learning_rate": 1.6594021609681344e-05,
1703
+ "loss": 0.5079,
1704
+ "step": 1205
1705
+ },
1706
+ {
1707
+ "epoch": 1.673582295988935,
1708
+ "grad_norm": 0.4468669295310974,
1709
+ "learning_rate": 1.5934038908511616e-05,
1710
+ "loss": 0.5135,
1711
+ "step": 1210
1712
+ },
1713
+ {
1714
+ "epoch": 1.6804979253112033,
1715
+ "grad_norm": 0.4427061975002289,
1716
+ "learning_rate": 1.5286310833512963e-05,
1717
+ "loss": 0.5019,
1718
+ "step": 1215
1719
+ },
1720
+ {
1721
+ "epoch": 1.6874135546334716,
1722
+ "grad_norm": 0.44807228446006775,
1723
+ "learning_rate": 1.4650931806557389e-05,
1724
+ "loss": 0.5121,
1725
+ "step": 1220
1726
+ },
1727
+ {
1728
+ "epoch": 1.69432918395574,
1729
+ "grad_norm": 0.45542779564857483,
1730
+ "learning_rate": 1.402799444934757e-05,
1731
+ "loss": 0.5183,
1732
+ "step": 1225
1733
+ },
1734
+ {
1735
+ "epoch": 1.7012448132780082,
1736
+ "grad_norm": 0.44287553429603577,
1737
+ "learning_rate": 1.3417589569914978e-05,
1738
+ "loss": 0.4962,
1739
+ "step": 1230
1740
+ },
1741
+ {
1742
+ "epoch": 1.7081604426002768,
1743
+ "grad_norm": 0.43979722261428833,
1744
+ "learning_rate": 1.2819806149382441e-05,
1745
+ "loss": 0.5065,
1746
+ "step": 1235
1747
+ },
1748
+ {
1749
+ "epoch": 1.715076071922545,
1750
+ "grad_norm": 0.4374731481075287,
1751
+ "learning_rate": 1.2234731328993055e-05,
1752
+ "loss": 0.5144,
1753
+ "step": 1240
1754
+ },
1755
+ {
1756
+ "epoch": 1.7219917012448134,
1757
+ "grad_norm": 0.4652646481990814,
1758
+ "learning_rate": 1.1662450397407188e-05,
1759
+ "loss": 0.5017,
1760
+ "step": 1245
1761
+ },
1762
+ {
1763
+ "epoch": 1.7289073305670817,
1764
+ "grad_norm": 0.4413568377494812,
1765
+ "learning_rate": 1.1103046778269687e-05,
1766
+ "loss": 0.5109,
1767
+ "step": 1250
1768
+ },
1769
+ {
1770
+ "epoch": 1.73582295988935,
1771
+ "grad_norm": 0.4495951235294342,
1772
+ "learning_rate": 1.0556602018048866e-05,
1773
+ "loss": 0.502,
1774
+ "step": 1255
1775
+ },
1776
+ {
1777
+ "epoch": 1.7427385892116183,
1778
+ "grad_norm": 0.4346306025981903,
1779
+ "learning_rate": 1.0023195774149119e-05,
1780
+ "loss": 0.4963,
1781
+ "step": 1260
1782
+ },
1783
+ {
1784
+ "epoch": 1.7496542185338866,
1785
+ "grad_norm": 0.4612555503845215,
1786
+ "learning_rate": 9.502905803299e-06,
1787
+ "loss": 0.5006,
1788
+ "step": 1265
1789
+ },
1790
+ {
1791
+ "epoch": 1.7565698478561549,
1792
+ "grad_norm": 0.46448782086372375,
1793
+ "learning_rate": 8.995807950216262e-06,
1794
+ "loss": 0.5195,
1795
+ "step": 1270
1796
+ },
1797
+ {
1798
+ "epoch": 1.7634854771784232,
1799
+ "grad_norm": 0.44382619857788086,
1800
+ "learning_rate": 8.501976136551749e-06,
1801
+ "loss": 0.5061,
1802
+ "step": 1275
1803
+ },
1804
+ {
1805
+ "epoch": 1.7704011065006915,
1806
+ "grad_norm": 0.45043641328811646,
1807
+ "learning_rate": 8.021482350113474e-06,
1808
+ "loss": 0.5254,
1809
+ "step": 1280
1810
+ },
1811
+ {
1812
+ "epoch": 1.7773167358229598,
1813
+ "grad_norm": 0.44958069920539856,
1814
+ "learning_rate": 7.554396634372707e-06,
1815
+ "loss": 0.5311,
1816
+ "step": 1285
1817
+ },
1818
+ {
1819
+ "epoch": 1.784232365145228,
1820
+ "grad_norm": 0.433776319026947,
1821
+ "learning_rate": 7.100787078253446e-06,
1822
+ "loss": 0.486,
1823
+ "step": 1290
1824
+ },
1825
+ {
1826
+ "epoch": 1.7911479944674964,
1827
+ "grad_norm": 0.41777148842811584,
1828
+ "learning_rate": 6.660719806206839e-06,
1829
+ "loss": 0.5108,
1830
+ "step": 1295
1831
+ },
1832
+ {
1833
+ "epoch": 1.798063623789765,
1834
+ "grad_norm": 0.4487934112548828,
1835
+ "learning_rate": 6.234258968571971e-06,
1836
+ "loss": 0.5006,
1837
+ "step": 1300
1838
+ },
1839
+ {
1840
+ "epoch": 1.8049792531120332,
1841
+ "grad_norm": 0.4544650614261627,
1842
+ "learning_rate": 5.821466732224412e-06,
1843
+ "loss": 0.5037,
1844
+ "step": 1305
1845
+ },
1846
+ {
1847
+ "epoch": 1.8118948824343015,
1848
+ "grad_norm": 0.41929152607917786,
1849
+ "learning_rate": 5.422403271513854e-06,
1850
+ "loss": 0.4978,
1851
+ "step": 1310
1852
+ },
1853
+ {
1854
+ "epoch": 1.8188105117565698,
1855
+ "grad_norm": 0.4613235294818878,
1856
+ "learning_rate": 5.0371267594923834e-06,
1857
+ "loss": 0.5209,
1858
+ "step": 1315
1859
+ },
1860
+ {
1861
+ "epoch": 1.8257261410788381,
1862
+ "grad_norm": 0.44448205828666687,
1863
+ "learning_rate": 4.66569335943422e-06,
1864
+ "loss": 0.5014,
1865
+ "step": 1320
1866
+ },
1867
+ {
1868
+ "epoch": 1.8326417704011067,
1869
+ "grad_norm": 0.43924444913864136,
1870
+ "learning_rate": 4.3081572166486675e-06,
1871
+ "loss": 0.5247,
1872
+ "step": 1325
1873
+ },
1874
+ {
1875
+ "epoch": 1.839557399723375,
1876
+ "grad_norm": 0.44769856333732605,
1877
+ "learning_rate": 3.964570450587113e-06,
1878
+ "loss": 0.5005,
1879
+ "step": 1330
1880
+ },
1881
+ {
1882
+ "epoch": 1.8464730290456433,
1883
+ "grad_norm": 0.4331699311733246,
1884
+ "learning_rate": 3.6349831472453743e-06,
1885
+ "loss": 0.5041,
1886
+ "step": 1335
1887
+ },
1888
+ {
1889
+ "epoch": 1.8533886583679116,
1890
+ "grad_norm": 0.43336230516433716,
1891
+ "learning_rate": 3.3194433518624614e-06,
1892
+ "loss": 0.5162,
1893
+ "step": 1340
1894
+ },
1895
+ {
1896
+ "epoch": 1.8603042876901799,
1897
+ "grad_norm": 0.4407755434513092,
1898
+ "learning_rate": 3.017997061916833e-06,
1899
+ "loss": 0.501,
1900
+ "step": 1345
1901
+ },
1902
+ {
1903
+ "epoch": 1.8672199170124482,
1904
+ "grad_norm": 0.43583956360816956,
1905
+ "learning_rate": 2.7306882204211626e-06,
1906
+ "loss": 0.5009,
1907
+ "step": 1350
1908
+ },
1909
+ {
1910
+ "epoch": 1.8741355463347165,
1911
+ "grad_norm": 0.42576801776885986,
1912
+ "learning_rate": 2.4575587095166054e-06,
1913
+ "loss": 0.5128,
1914
+ "step": 1355
1915
+ },
1916
+ {
1917
+ "epoch": 1.8810511756569848,
1918
+ "grad_norm": 0.42050647735595703,
1919
+ "learning_rate": 2.198648344367449e-06,
1920
+ "loss": 0.5069,
1921
+ "step": 1360
1922
+ },
1923
+ {
1924
+ "epoch": 1.887966804979253,
1925
+ "grad_norm": 0.4313651919364929,
1926
+ "learning_rate": 1.953994867357134e-06,
1927
+ "loss": 0.5055,
1928
+ "step": 1365
1929
+ },
1930
+ {
1931
+ "epoch": 1.8948824343015214,
1932
+ "grad_norm": 0.43365243077278137,
1933
+ "learning_rate": 1.7236339425863446e-06,
1934
+ "loss": 0.5145,
1935
+ "step": 1370
1936
+ },
1937
+ {
1938
+ "epoch": 1.9017980636237897,
1939
+ "grad_norm": 0.4598560035228729,
1940
+ "learning_rate": 1.507599150674177e-06,
1941
+ "loss": 0.5191,
1942
+ "step": 1375
1943
+ },
1944
+ {
1945
+ "epoch": 1.908713692946058,
1946
+ "grad_norm": 0.4304969310760498,
1947
+ "learning_rate": 1.3059219838629234e-06,
1948
+ "loss": 0.501,
1949
+ "step": 1380
1950
+ },
1951
+ {
1952
+ "epoch": 1.9156293222683263,
1953
+ "grad_norm": 0.44647660851478577,
1954
+ "learning_rate": 1.11863184142732e-06,
1955
+ "loss": 0.5063,
1956
+ "step": 1385
1957
+ },
1958
+ {
1959
+ "epoch": 1.9225449515905948,
1960
+ "grad_norm": 0.40728816390037537,
1961
+ "learning_rate": 9.457560253889219e-07,
1962
+ "loss": 0.5009,
1963
+ "step": 1390
1964
+ },
1965
+ {
1966
+ "epoch": 1.929460580912863,
1967
+ "grad_norm": 0.4395773410797119,
1968
+ "learning_rate": 7.873197365361407e-07,
1969
+ "loss": 0.4993,
1970
+ "step": 1395
1971
+ },
1972
+ {
1973
+ "epoch": 1.9363762102351314,
1974
+ "grad_norm": 0.44724011421203613,
1975
+ "learning_rate": 6.433460707506722e-07,
1976
+ "loss": 0.5065,
1977
+ "step": 1400
1978
+ },
1979
+ {
1980
+ "epoch": 1.9432918395573997,
1981
+ "grad_norm": 0.41976112127304077,
1982
+ "learning_rate": 5.138560156407124e-07,
1983
+ "loss": 0.5058,
1984
+ "step": 1405
1985
+ },
1986
+ {
1987
+ "epoch": 1.950207468879668,
1988
+ "grad_norm": 0.43243739008903503,
1989
+ "learning_rate": 3.988684474814819e-07,
1990
+ "loss": 0.4919,
1991
+ "step": 1410
1992
+ },
1993
+ {
1994
+ "epoch": 1.9571230982019365,
1995
+ "grad_norm": 0.4788164496421814,
1996
+ "learning_rate": 2.984001284635496e-07,
1997
+ "loss": 0.5128,
1998
+ "step": 1415
1999
+ },
2000
+ {
2001
+ "epoch": 1.9640387275242048,
2002
+ "grad_norm": 0.42695632576942444,
2003
+ "learning_rate": 2.1246570424940936e-07,
2004
+ "loss": 0.5116,
2005
+ "step": 1420
2006
+ },
2007
+ {
2008
+ "epoch": 1.9709543568464731,
2009
+ "grad_norm": 0.40510523319244385,
2010
+ "learning_rate": 1.4107770183845458e-07,
2011
+ "loss": 0.5058,
2012
+ "step": 1425
2013
+ },
2014
+ {
2015
+ "epoch": 1.9778699861687414,
2016
+ "grad_norm": 0.4062838554382324,
2017
+ "learning_rate": 8.424652774089436e-08,
2018
+ "loss": 0.5128,
2019
+ "step": 1430
2020
+ },
2021
+ {
2022
+ "epoch": 1.9847856154910097,
2023
+ "grad_norm": 0.4485253393650055,
2024
+ "learning_rate": 4.198046646075593e-08,
2025
+ "loss": 0.5062,
2026
+ "step": 1435
2027
+ },
2028
+ {
2029
+ "epoch": 1.991701244813278,
2030
+ "grad_norm": 0.43608593940734863,
2031
+ "learning_rate": 1.4285679288228437e-08,
2032
+ "loss": 0.4919,
2033
+ "step": 1440
2034
+ },
2035
+ {
2036
+ "epoch": 1.9986168741355463,
2037
+ "grad_norm": 0.4265099763870239,
2038
+ "learning_rate": 1.166203401481436e-09,
2039
+ "loss": 0.5001,
2040
+ "step": 1445
2041
+ },
2042
+ {
2043
+ "epoch": 2.0,
2044
+ "step": 1446,
2045
+ "total_flos": 6.011530730704732e+18,
2046
+ "train_loss": 0.6795949197244182,
2047
+ "train_runtime": 13742.7497,
2048
+ "train_samples_per_second": 6.734,
2049
+ "train_steps_per_second": 0.105
2050
+ }
2051
+ ],
2052
+ "logging_steps": 5,
2053
+ "max_steps": 1446,
2054
+ "num_input_tokens_seen": 0,
2055
+ "num_train_epochs": 2,
2056
+ "save_steps": 500,
2057
+ "stateful_callbacks": {
2058
+ "TrainerControl": {
2059
+ "args": {
2060
+ "should_epoch_stop": false,
2061
+ "should_evaluate": false,
2062
+ "should_log": false,
2063
+ "should_save": false,
2064
+ "should_training_stop": false
2065
+ },
2066
+ "attributes": {}
2067
+ }
2068
+ },
2069
+ "total_flos": 6.011530730704732e+18,
2070
+ "train_batch_size": 4,
2071
+ "trial_name": null,
2072
+ "trial_params": null
2073
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866fc066538def660b5fabd18598af79ac48a91e9239f0323747193025ad16fb
3
+ size 7096