Hugging Face's logo

Haitao999
/
Llama-3.2-3B-Instruct-GRPO-numia_prompt_dpo1

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files Community
Haitao999 commited on
Commit
17bc122
·
verified ·
1 Parent(s): cfc1728

Model save

Browse files
Files changed (7) hide show
  1. README.md +67 -0
  2. all_results.json +8 -0
  3. generation_config.json +12 -0
  4. model-00001-of-00002.safetensors +1 -1
  5. model-00002-of-00002.safetensors +1 -1
  6. train_results.json +8 -0
  7. trainer_state.json +2000 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ model_name: Llama-3.2-3B-Instruct-GRPO-numia_prompt_dpo1
4
+ tags:
5
+ - generated_from_trainer
6
+ - trl
7
+ - grpo
8
+ licence: license
9
+ ---
10
+
11
+ # Model Card for Llama-3.2-3B-Instruct-GRPO-numia_prompt_dpo1
12
+
13
+ This model is a fine-tuned version of [None](https://huggingface.co/None).
14
+ It has been trained using [TRL](https://github.com/huggingface/trl).
15
+
16
+ ## Quick start
17
+
18
+ ```python
19
+ from transformers import pipeline
20
+
21
+ 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?"
22
+ generator = pipeline("text-generation", model="Haitao999/Llama-3.2-3B-Instruct-GRPO-numia_prompt_dpo1", device="cuda")
23
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
24
+ print(output["generated_text"])
25
+ ```
26
+
27
+ ## Training procedure
28
+
29
+ [<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/tjucsailab/huggingface/runs/ua3dma86)
30
+
31
+
32
+ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
33
+
34
+ ### Framework versions
35
+
36
+ - TRL: 0.14.0
37
+ - Transformers: 4.48.3
38
+ - Pytorch: 2.5.1
39
+ - Datasets: 3.2.0
40
+ - Tokenizers: 0.21.1
41
+
42
+ ## Citations
43
+
44
+ Cite GRPO as:
45
+
46
+ ```bibtex
47
+ @article{zhihong2024deepseekmath,
48
+ title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
49
+ author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
50
+ year = 2024,
51
+ eprint = {arXiv:2402.03300},
52
+ }
53
+
54
+ ```
55
+
56
+ Cite TRL as:
57
+
58
+ ```bibtex
59
+ @misc{vonwerra2022trl,
60
+ title = {{TRL: Transformer Reinforcement Learning}},
61
+ 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},
62
+ year = 2020,
63
+ journal = {GitHub repository},
64
+ publisher = {GitHub},
65
+ howpublished = {\url{https://github.com/huggingface/trl}}
66
+ }
67
+ ```
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_flos": 0.0,
3
+ "train_loss": 1.5679008615386834e-09,
4
+ "train_runtime": 33567.1333,
5
+ "train_samples": 20000,
6
+ "train_samples_per_second": 0.596,
7
+ "train_steps_per_second": 0.005
8
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.48.3"
12
+ }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:972836f4bffbc4bd732f96175ff67f40f7c1c0eb1d176e9c3fe658666ea305c2
3
  size 4965799096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41496d7e1cd655f34f76f30b26b0ac459ac354d50886525c9e9244b11db5da4e
3
  size 4965799096
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2c8440c921ebe73252783cfd0537b25ec956679b6d180f22bfd8ddbb9909df7
3
  size 1459729952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0b5706cdf0c1c7874b08957e92aec448a196bce2a613285a4b87d604e846cd4
3
  size 1459729952
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_flos": 0.0,
3
+ "train_loss": 1.5679008615386834e-09,
4
+ "train_runtime": 33567.1333,
5
+ "train_samples": 20000,
6
+ "train_samples_per_second": 0.596,
7
+ "train_steps_per_second": 0.005
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,2000 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9965010496850945,
5
+ "eval_steps": 100,
6
+ "global_step": 178,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "completion_length": 548.2455501556396,
13
+ "epoch": 0.005598320503848845,
14
+ "grad_norm": 0.003676735097542405,
15
+ "learning_rate": 3e-07,
16
+ "loss": 0.0,
17
+ "reward": 0.03125000128056854,
18
+ "reward_std": 0.035294653847813606,
19
+ "rewards/accuracy_reward": 0.03125000128056854,
20
+ "step": 1
21
+ },
22
+ {
23
+ "completion_length": 521.3355770111084,
24
+ "epoch": 0.01119664100769769,
25
+ "grad_norm": 0.001673316117376089,
26
+ "learning_rate": 3e-07,
27
+ "loss": 0.0,
28
+ "reward": 0.005952381179668009,
29
+ "reward_std": 0.008138235658407211,
30
+ "rewards/accuracy_reward": 0.005952381179668009,
31
+ "step": 2
32
+ },
33
+ {
34
+ "completion_length": 565.3147449493408,
35
+ "epoch": 0.016794961511546535,
36
+ "grad_norm": 0.002517723012715578,
37
+ "learning_rate": 3e-07,
38
+ "loss": 0.0,
39
+ "reward": 0.009672619285993278,
40
+ "reward_std": 0.01636804547160864,
41
+ "rewards/accuracy_reward": 0.009672619285993278,
42
+ "step": 3
43
+ },
44
+ {
45
+ "completion_length": 577.5029792785645,
46
+ "epoch": 0.02239328201539538,
47
+ "grad_norm": 0.003224034095183015,
48
+ "learning_rate": 3e-07,
49
+ "loss": 0.0,
50
+ "reward": 0.029761905316263437,
51
+ "reward_std": 0.02953372267074883,
52
+ "rewards/accuracy_reward": 0.029761905316263437,
53
+ "step": 4
54
+ },
55
+ {
56
+ "completion_length": 564.710578918457,
57
+ "epoch": 0.02799160251924423,
58
+ "grad_norm": 0.0038144055288285017,
59
+ "learning_rate": 3e-07,
60
+ "loss": 0.0,
61
+ "reward": 0.020833333779592067,
62
+ "reward_std": 0.022426264360547066,
63
+ "rewards/accuracy_reward": 0.020833333779592067,
64
+ "step": 5
65
+ },
66
+ {
67
+ "completion_length": 534.8861694335938,
68
+ "epoch": 0.03358992302309307,
69
+ "grad_norm": 0.003479737089946866,
70
+ "learning_rate": 3e-07,
71
+ "loss": 0.0,
72
+ "reward": 0.026785714842844754,
73
+ "reward_std": 0.031758472323417664,
74
+ "rewards/accuracy_reward": 0.026785714842844754,
75
+ "step": 6
76
+ },
77
+ {
78
+ "completion_length": 580.7991256713867,
79
+ "epoch": 0.03918824352694192,
80
+ "grad_norm": 0.0025944788940250874,
81
+ "learning_rate": 3e-07,
82
+ "loss": 0.0,
83
+ "reward": 0.014880952483508736,
84
+ "reward_std": 0.010090996511280537,
85
+ "rewards/accuracy_reward": 0.014880952483508736,
86
+ "step": 7
87
+ },
88
+ {
89
+ "completion_length": 515.3296279907227,
90
+ "epoch": 0.04478656403079076,
91
+ "grad_norm": 0.003000692930072546,
92
+ "learning_rate": 3e-07,
93
+ "loss": 0.0,
94
+ "reward": 0.021577381354290992,
95
+ "reward_std": 0.019644177984446287,
96
+ "rewards/accuracy_reward": 0.021577381354290992,
97
+ "step": 8
98
+ },
99
+ {
100
+ "completion_length": 571.0290279388428,
101
+ "epoch": 0.05038488453463961,
102
+ "grad_norm": 0.003332852851599455,
103
+ "learning_rate": 3e-07,
104
+ "loss": 0.0,
105
+ "reward": 0.02901785750873387,
106
+ "reward_std": 0.026531722396612167,
107
+ "rewards/accuracy_reward": 0.02901785750873387,
108
+ "step": 9
109
+ },
110
+ {
111
+ "completion_length": 580.1770935058594,
112
+ "epoch": 0.05598320503848846,
113
+ "grad_norm": 0.0018766584107652307,
114
+ "learning_rate": 3e-07,
115
+ "loss": 0.0,
116
+ "reward": 0.0074404762126505375,
117
+ "reward_std": 0.003475441597402096,
118
+ "rewards/accuracy_reward": 0.0074404762126505375,
119
+ "step": 10
120
+ },
121
+ {
122
+ "completion_length": 576.3244209289551,
123
+ "epoch": 0.0615815255423373,
124
+ "grad_norm": 0.004447213374078274,
125
+ "learning_rate": 3e-07,
126
+ "loss": 0.0,
127
+ "reward": 0.03497023892123252,
128
+ "reward_std": 0.03141464572399855,
129
+ "rewards/accuracy_reward": 0.03497023892123252,
130
+ "step": 11
131
+ },
132
+ {
133
+ "completion_length": 555.8616218566895,
134
+ "epoch": 0.06717984604618614,
135
+ "grad_norm": 0.003440001280978322,
136
+ "learning_rate": 3e-07,
137
+ "loss": 0.0,
138
+ "reward": 0.033482144062872976,
139
+ "reward_std": 0.03174867480993271,
140
+ "rewards/accuracy_reward": 0.033482144062872976,
141
+ "step": 12
142
+ },
143
+ {
144
+ "completion_length": 555.1770973205566,
145
+ "epoch": 0.072778166550035,
146
+ "grad_norm": 0.004410188645124435,
147
+ "learning_rate": 3e-07,
148
+ "loss": 0.0,
149
+ "reward": 0.02604166732635349,
150
+ "reward_std": 0.03677397267892957,
151
+ "rewards/accuracy_reward": 0.02604166732635349,
152
+ "step": 13
153
+ },
154
+ {
155
+ "completion_length": 582.8259029388428,
156
+ "epoch": 0.07837648705388384,
157
+ "grad_norm": 0.0032948441803455353,
158
+ "learning_rate": 3e-07,
159
+ "loss": 0.0,
160
+ "reward": 0.019345238630194217,
161
+ "reward_std": 0.02020683465525508,
162
+ "rewards/accuracy_reward": 0.019345238630194217,
163
+ "step": 14
164
+ },
165
+ {
166
+ "completion_length": 573.2150402069092,
167
+ "epoch": 0.08397480755773268,
168
+ "grad_norm": 0.004153064452111721,
169
+ "learning_rate": 3e-07,
170
+ "loss": 0.0,
171
+ "reward": 0.02083333395421505,
172
+ "reward_std": 0.024796947836875916,
173
+ "rewards/accuracy_reward": 0.02083333395421505,
174
+ "step": 15
175
+ },
176
+ {
177
+ "completion_length": 511.9151840209961,
178
+ "epoch": 0.08957312806158152,
179
+ "grad_norm": 0.0052322824485599995,
180
+ "learning_rate": 3e-07,
181
+ "loss": 0.0,
182
+ "reward": 0.04017857229337096,
183
+ "reward_std": 0.04290085076354444,
184
+ "rewards/accuracy_reward": 0.04017857229337096,
185
+ "step": 16
186
+ },
187
+ {
188
+ "completion_length": 538.8735218048096,
189
+ "epoch": 0.09517144856543037,
190
+ "grad_norm": 0.005073050037026405,
191
+ "learning_rate": 3e-07,
192
+ "loss": 0.0,
193
+ "reward": 0.0349702388048172,
194
+ "reward_std": 0.03157654171809554,
195
+ "rewards/accuracy_reward": 0.0349702388048172,
196
+ "step": 17
197
+ },
198
+ {
199
+ "completion_length": 594.4494113922119,
200
+ "epoch": 0.10076976906927922,
201
+ "grad_norm": 0.004708003718405962,
202
+ "learning_rate": 3e-07,
203
+ "loss": 0.0,
204
+ "reward": 0.030505953240208328,
205
+ "reward_std": 0.035523281432688236,
206
+ "rewards/accuracy_reward": 0.030505953240208328,
207
+ "step": 18
208
+ },
209
+ {
210
+ "completion_length": 557.1242733001709,
211
+ "epoch": 0.10636808957312806,
212
+ "grad_norm": 0.0028041391633450985,
213
+ "learning_rate": 3e-07,
214
+ "loss": 0.0,
215
+ "reward": 0.02827381028328091,
216
+ "reward_std": 0.01928615104407072,
217
+ "rewards/accuracy_reward": 0.02827381028328091,
218
+ "step": 19
219
+ },
220
+ {
221
+ "completion_length": 560.6994209289551,
222
+ "epoch": 0.11196641007697691,
223
+ "grad_norm": 0.004033979959785938,
224
+ "learning_rate": 3e-07,
225
+ "loss": 0.0,
226
+ "reward": 0.029761905258055776,
227
+ "reward_std": 0.03157439874485135,
228
+ "rewards/accuracy_reward": 0.029761905258055776,
229
+ "step": 20
230
+ },
231
+ {
232
+ "completion_length": 565.3564147949219,
233
+ "epoch": 0.11756473058082575,
234
+ "grad_norm": 0.0020209557842463255,
235
+ "learning_rate": 3e-07,
236
+ "loss": 0.0,
237
+ "reward": 0.004464285797439516,
238
+ "reward_std": 0.00787156680598855,
239
+ "rewards/accuracy_reward": 0.004464285797439516,
240
+ "step": 21
241
+ },
242
+ {
243
+ "completion_length": 618.4695091247559,
244
+ "epoch": 0.1231630510846746,
245
+ "grad_norm": 0.002670794492587447,
246
+ "learning_rate": 3e-07,
247
+ "loss": 0.0,
248
+ "reward": 0.021577381703536958,
249
+ "reward_std": 0.01789072621613741,
250
+ "rewards/accuracy_reward": 0.021577381703536958,
251
+ "step": 22
252
+ },
253
+ {
254
+ "completion_length": 584.6480770111084,
255
+ "epoch": 0.12876137158852344,
256
+ "grad_norm": 0.005253300536423922,
257
+ "learning_rate": 3e-07,
258
+ "loss": 0.0,
259
+ "reward": 0.03720238187815994,
260
+ "reward_std": 0.03154852241277695,
261
+ "rewards/accuracy_reward": 0.03720238187815994,
262
+ "step": 23
263
+ },
264
+ {
265
+ "completion_length": 581.5640029907227,
266
+ "epoch": 0.13435969209237228,
267
+ "grad_norm": 0.0021275475155562162,
268
+ "learning_rate": 3e-07,
269
+ "loss": 0.0,
270
+ "reward": 0.005952381179668009,
271
+ "reward_std": 0.008138235658407211,
272
+ "rewards/accuracy_reward": 0.005952381179668009,
273
+ "step": 24
274
+ },
275
+ {
276
+ "completion_length": 545.2701072692871,
277
+ "epoch": 0.13995801259622112,
278
+ "grad_norm": 0.002449671970680356,
279
+ "learning_rate": 3e-07,
280
+ "loss": 0.0,
281
+ "reward": 0.015625000465661287,
282
+ "reward_std": 0.017629378009587526,
283
+ "rewards/accuracy_reward": 0.015625000465661287,
284
+ "step": 25
285
+ },
286
+ {
287
+ "completion_length": 545.0669708251953,
288
+ "epoch": 0.14555633310007,
289
+ "grad_norm": 0.0028808764182031155,
290
+ "learning_rate": 3e-07,
291
+ "loss": 0.0,
292
+ "reward": 0.0200892859720625,
293
+ "reward_std": 0.018164015375077724,
294
+ "rewards/accuracy_reward": 0.0200892859720625,
295
+ "step": 26
296
+ },
297
+ {
298
+ "completion_length": 561.1131038665771,
299
+ "epoch": 0.15115465360391883,
300
+ "grad_norm": 0.004521294496953487,
301
+ "learning_rate": 3e-07,
302
+ "loss": 0.0,
303
+ "reward": 0.043898809934034944,
304
+ "reward_std": 0.027857428416609764,
305
+ "rewards/accuracy_reward": 0.043898809934034944,
306
+ "step": 27
307
+ },
308
+ {
309
+ "completion_length": 573.0468807220459,
310
+ "epoch": 0.15675297410776767,
311
+ "grad_norm": 0.004434187430888414,
312
+ "learning_rate": 3e-07,
313
+ "loss": 0.0,
314
+ "reward": 0.03050595335662365,
315
+ "reward_std": 0.03036304796114564,
316
+ "rewards/accuracy_reward": 0.03050595335662365,
317
+ "step": 28
318
+ },
319
+ {
320
+ "completion_length": 573.6540298461914,
321
+ "epoch": 0.16235129461161651,
322
+ "grad_norm": 0.0023913481272757053,
323
+ "learning_rate": 3e-07,
324
+ "loss": 0.0,
325
+ "reward": 0.03422619198681787,
326
+ "reward_std": 0.01964203454554081,
327
+ "rewards/accuracy_reward": 0.03422619198681787,
328
+ "step": 29
329
+ },
330
+ {
331
+ "completion_length": 582.3474769592285,
332
+ "epoch": 0.16794961511546536,
333
+ "grad_norm": 0.0027055193204432726,
334
+ "learning_rate": 3e-07,
335
+ "loss": 0.0,
336
+ "reward": 0.027529762592166662,
337
+ "reward_std": 0.02218207810074091,
338
+ "rewards/accuracy_reward": 0.027529762592166662,
339
+ "step": 30
340
+ },
341
+ {
342
+ "completion_length": 583.9047756195068,
343
+ "epoch": 0.1735479356193142,
344
+ "grad_norm": 0.003626331454142928,
345
+ "learning_rate": 3e-07,
346
+ "loss": 0.0,
347
+ "reward": 0.03720238181995228,
348
+ "reward_std": 0.028277710545808077,
349
+ "rewards/accuracy_reward": 0.03720238181995228,
350
+ "step": 31
351
+ },
352
+ {
353
+ "completion_length": 576.6346855163574,
354
+ "epoch": 0.17914625612316304,
355
+ "grad_norm": 0.0032239772845059633,
356
+ "learning_rate": 3e-07,
357
+ "loss": 0.0,
358
+ "reward": 0.015625000291038305,
359
+ "reward_std": 0.022000661585479975,
360
+ "rewards/accuracy_reward": 0.015625000291038305,
361
+ "step": 32
362
+ },
363
+ {
364
+ "completion_length": 568.7916736602783,
365
+ "epoch": 0.1847445766270119,
366
+ "grad_norm": 0.0029333089478313923,
367
+ "learning_rate": 3e-07,
368
+ "loss": 0.0,
369
+ "reward": 0.025297619693446904,
370
+ "reward_std": 0.020201513543725014,
371
+ "rewards/accuracy_reward": 0.025297619693446904,
372
+ "step": 33
373
+ },
374
+ {
375
+ "completion_length": 555.8154830932617,
376
+ "epoch": 0.19034289713086075,
377
+ "grad_norm": 0.003082014387473464,
378
+ "learning_rate": 3e-07,
379
+ "loss": -0.0,
380
+ "reward": 0.01264880975941196,
381
+ "reward_std": 0.019351367838680744,
382
+ "rewards/accuracy_reward": 0.01264880975941196,
383
+ "step": 34
384
+ },
385
+ {
386
+ "completion_length": 593.186767578125,
387
+ "epoch": 0.1959412176347096,
388
+ "grad_norm": 0.003542139893397689,
389
+ "learning_rate": 3e-07,
390
+ "loss": 0.0,
391
+ "reward": 0.029017857741564512,
392
+ "reward_std": 0.03906076308339834,
393
+ "rewards/accuracy_reward": 0.029017857741564512,
394
+ "step": 35
395
+ },
396
+ {
397
+ "completion_length": 539.3273983001709,
398
+ "epoch": 0.20153953813855843,
399
+ "grad_norm": 0.0035734642297029495,
400
+ "learning_rate": 3e-07,
401
+ "loss": 0.0,
402
+ "reward": 0.04092262004269287,
403
+ "reward_std": 0.02163945697247982,
404
+ "rewards/accuracy_reward": 0.04092262004269287,
405
+ "step": 36
406
+ },
407
+ {
408
+ "completion_length": 528.0818519592285,
409
+ "epoch": 0.20713785864240727,
410
+ "grad_norm": 0.004155021160840988,
411
+ "learning_rate": 3e-07,
412
+ "loss": 0.0,
413
+ "reward": 0.04241071513388306,
414
+ "reward_std": 0.031058762688189745,
415
+ "rewards/accuracy_reward": 0.04241071513388306,
416
+ "step": 37
417
+ },
418
+ {
419
+ "completion_length": 572.0044708251953,
420
+ "epoch": 0.21273617914625612,
421
+ "grad_norm": 0.0043424940668046474,
422
+ "learning_rate": 3e-07,
423
+ "loss": 0.0,
424
+ "reward": 0.031250000349245965,
425
+ "reward_std": 0.03391032665967941,
426
+ "rewards/accuracy_reward": 0.031250000349245965,
427
+ "step": 38
428
+ },
429
+ {
430
+ "completion_length": 561.321439743042,
431
+ "epoch": 0.21833449965010496,
432
+ "grad_norm": 0.0013517189072445035,
433
+ "learning_rate": 3e-07,
434
+ "loss": 0.0,
435
+ "reward": 0.014136905316263437,
436
+ "reward_std": 0.004597577266395092,
437
+ "rewards/accuracy_reward": 0.014136905316263437,
438
+ "step": 39
439
+ },
440
+ {
441
+ "completion_length": 604.6815567016602,
442
+ "epoch": 0.22393282015395383,
443
+ "grad_norm": 0.004611727315932512,
444
+ "learning_rate": 3e-07,
445
+ "loss": 0.0,
446
+ "reward": 0.04464285826543346,
447
+ "reward_std": 0.042770151514559984,
448
+ "rewards/accuracy_reward": 0.04464285826543346,
449
+ "step": 40
450
+ },
451
+ {
452
+ "completion_length": 591.9910755157471,
453
+ "epoch": 0.22953114065780267,
454
+ "grad_norm": 0.003368583507835865,
455
+ "learning_rate": 3e-07,
456
+ "loss": 0.0,
457
+ "reward": 0.03720238246023655,
458
+ "reward_std": 0.022582839708775282,
459
+ "rewards/accuracy_reward": 0.03720238246023655,
460
+ "step": 41
461
+ },
462
+ {
463
+ "completion_length": 585.0193538665771,
464
+ "epoch": 0.2351294611616515,
465
+ "grad_norm": 0.0034278561361134052,
466
+ "learning_rate": 3e-07,
467
+ "loss": 0.0,
468
+ "reward": 0.04315476305782795,
469
+ "reward_std": 0.02897424390539527,
470
+ "rewards/accuracy_reward": 0.04315476305782795,
471
+ "step": 42
472
+ },
473
+ {
474
+ "completion_length": 588.648078918457,
475
+ "epoch": 0.24072778166550035,
476
+ "grad_norm": 0.003546294756233692,
477
+ "learning_rate": 3e-07,
478
+ "loss": 0.0,
479
+ "reward": 0.04092262068297714,
480
+ "reward_std": 0.02937500481493771,
481
+ "rewards/accuracy_reward": 0.04092262068297714,
482
+ "step": 43
483
+ },
484
+ {
485
+ "completion_length": 591.8616180419922,
486
+ "epoch": 0.2463261021693492,
487
+ "grad_norm": 0.0032863786909729242,
488
+ "learning_rate": 3e-07,
489
+ "loss": 0.0,
490
+ "reward": 0.029017857741564512,
491
+ "reward_std": 0.02016195748001337,
492
+ "rewards/accuracy_reward": 0.029017857741564512,
493
+ "step": 44
494
+ },
495
+ {
496
+ "completion_length": 595.4494113922119,
497
+ "epoch": 0.25192442267319803,
498
+ "grad_norm": 0.003891779575496912,
499
+ "learning_rate": 3e-07,
500
+ "loss": 0.0,
501
+ "reward": 0.0513392873108387,
502
+ "reward_std": 0.021664298605173826,
503
+ "rewards/accuracy_reward": 0.0513392873108387,
504
+ "step": 45
505
+ },
506
+ {
507
+ "completion_length": 576.5751647949219,
508
+ "epoch": 0.2575227431770469,
509
+ "grad_norm": 0.004738082177937031,
510
+ "learning_rate": 3e-07,
511
+ "loss": 0.0,
512
+ "reward": 0.04092262021731585,
513
+ "reward_std": 0.03612527949735522,
514
+ "rewards/accuracy_reward": 0.04092262021731585,
515
+ "step": 46
516
+ },
517
+ {
518
+ "completion_length": 582.7514915466309,
519
+ "epoch": 0.2631210636808957,
520
+ "grad_norm": 0.005118933971971273,
521
+ "learning_rate": 3e-07,
522
+ "loss": 0.0,
523
+ "reward": 0.044642857857979834,
524
+ "reward_std": 0.02991444803774357,
525
+ "rewards/accuracy_reward": 0.044642857857979834,
526
+ "step": 47
527
+ },
528
+ {
529
+ "completion_length": 597.6398983001709,
530
+ "epoch": 0.26871938418474456,
531
+ "grad_norm": 0.003335759276524186,
532
+ "learning_rate": 3e-07,
533
+ "loss": 0.0,
534
+ "reward": 0.017857143247965723,
535
+ "reward_std": 0.02291816775687039,
536
+ "rewards/accuracy_reward": 0.017857143247965723,
537
+ "step": 48
538
+ },
539
+ {
540
+ "completion_length": 632.6994171142578,
541
+ "epoch": 0.2743177046885934,
542
+ "grad_norm": 0.002710092579945922,
543
+ "learning_rate": 3e-07,
544
+ "loss": 0.0,
545
+ "reward": 0.026785714959260076,
546
+ "reward_std": 0.018883246928453445,
547
+ "rewards/accuracy_reward": 0.026785714959260076,
548
+ "step": 49
549
+ },
550
+ {
551
+ "completion_length": 614.4695072174072,
552
+ "epoch": 0.27991602519244224,
553
+ "grad_norm": 0.004074351862072945,
554
+ "learning_rate": 3e-07,
555
+ "loss": 0.0,
556
+ "reward": 0.034970239736139774,
557
+ "reward_std": 0.0352512919344008,
558
+ "rewards/accuracy_reward": 0.034970239736139774,
559
+ "step": 50
560
+ },
561
+ {
562
+ "completion_length": 564.6369132995605,
563
+ "epoch": 0.28551434569629114,
564
+ "grad_norm": 0.00433464627712965,
565
+ "learning_rate": 3e-07,
566
+ "loss": 0.0,
567
+ "reward": 0.04761904897168279,
568
+ "reward_std": 0.036211316008120775,
569
+ "rewards/accuracy_reward": 0.04761904897168279,
570
+ "step": 51
571
+ },
572
+ {
573
+ "completion_length": 574.7514991760254,
574
+ "epoch": 0.29111266620014,
575
+ "grad_norm": 0.0021451774518936872,
576
+ "learning_rate": 3e-07,
577
+ "loss": 0.0,
578
+ "reward": 0.02232142904540524,
579
+ "reward_std": 0.01412591733969748,
580
+ "rewards/accuracy_reward": 0.02232142904540524,
581
+ "step": 52
582
+ },
583
+ {
584
+ "completion_length": 587.8154850006104,
585
+ "epoch": 0.2967109867039888,
586
+ "grad_norm": 0.004314142279326916,
587
+ "learning_rate": 3e-07,
588
+ "loss": 0.0,
589
+ "reward": 0.04017857281723991,
590
+ "reward_std": 0.03161609871312976,
591
+ "rewards/accuracy_reward": 0.04017857281723991,
592
+ "step": 53
593
+ },
594
+ {
595
+ "completion_length": 612.7529888153076,
596
+ "epoch": 0.30230930720783766,
597
+ "grad_norm": 0.003322584554553032,
598
+ "learning_rate": 3e-07,
599
+ "loss": 0.0,
600
+ "reward": 0.023809524485841393,
601
+ "reward_std": 0.029193072579801083,
602
+ "rewards/accuracy_reward": 0.023809524485841393,
603
+ "step": 54
604
+ },
605
+ {
606
+ "completion_length": 602.6979274749756,
607
+ "epoch": 0.3079076277116865,
608
+ "grad_norm": 0.0024285970721393824,
609
+ "learning_rate": 3e-07,
610
+ "loss": 0.0,
611
+ "reward": 0.014136904967017472,
612
+ "reward_std": 0.017268173396587372,
613
+ "rewards/accuracy_reward": 0.014136904967017472,
614
+ "step": 55
615
+ },
616
+ {
617
+ "completion_length": 594.776798248291,
618
+ "epoch": 0.31350594821553535,
619
+ "grad_norm": 0.002405191073194146,
620
+ "learning_rate": 3e-07,
621
+ "loss": 0.0,
622
+ "reward": 0.031250000931322575,
623
+ "reward_std": 0.008076196536421776,
624
+ "rewards/accuracy_reward": 0.031250000931322575,
625
+ "step": 56
626
+ },
627
+ {
628
+ "completion_length": 569.1354274749756,
629
+ "epoch": 0.3191042687193842,
630
+ "grad_norm": 0.004245223011821508,
631
+ "learning_rate": 3e-07,
632
+ "loss": 0.0,
633
+ "reward": 0.056547619809862226,
634
+ "reward_std": 0.03459409927017987,
635
+ "rewards/accuracy_reward": 0.056547619809862226,
636
+ "step": 57
637
+ },
638
+ {
639
+ "completion_length": 610.0952472686768,
640
+ "epoch": 0.32470258922323303,
641
+ "grad_norm": 0.003974903374910355,
642
+ "learning_rate": 3e-07,
643
+ "loss": 0.0,
644
+ "reward": 0.035714287078008056,
645
+ "reward_std": 0.02040082309395075,
646
+ "rewards/accuracy_reward": 0.035714287078008056,
647
+ "step": 58
648
+ },
649
+ {
650
+ "completion_length": 645.4836387634277,
651
+ "epoch": 0.33030090972708187,
652
+ "grad_norm": 0.0026164394803345203,
653
+ "learning_rate": 3e-07,
654
+ "loss": 0.0,
655
+ "reward": 0.011160714784637094,
656
+ "reward_std": 0.011207811534404755,
657
+ "rewards/accuracy_reward": 0.011160714784637094,
658
+ "step": 59
659
+ },
660
+ {
661
+ "completion_length": 626.8445014953613,
662
+ "epoch": 0.3358992302309307,
663
+ "grad_norm": 0.0031215217895805836,
664
+ "learning_rate": 3e-07,
665
+ "loss": 0.0,
666
+ "reward": 0.024553572467993945,
667
+ "reward_std": 0.02602896187454462,
668
+ "rewards/accuracy_reward": 0.024553572467993945,
669
+ "step": 60
670
+ },
671
+ {
672
+ "completion_length": 602.254472732544,
673
+ "epoch": 0.34149755073477955,
674
+ "grad_norm": 0.0025609612930566072,
675
+ "learning_rate": 3e-07,
676
+ "loss": 0.0,
677
+ "reward": 0.03273809637175873,
678
+ "reward_std": 0.02431014971807599,
679
+ "rewards/accuracy_reward": 0.03273809637175873,
680
+ "step": 61
681
+ },
682
+ {
683
+ "completion_length": 605.808048248291,
684
+ "epoch": 0.3470958712386284,
685
+ "grad_norm": 0.0041216155514121056,
686
+ "learning_rate": 3e-07,
687
+ "loss": 0.0,
688
+ "reward": 0.0223214291036129,
689
+ "reward_std": 0.027785591781139374,
690
+ "rewards/accuracy_reward": 0.0223214291036129,
691
+ "step": 62
692
+ },
693
+ {
694
+ "completion_length": 620.4248657226562,
695
+ "epoch": 0.35269419174247724,
696
+ "grad_norm": 0.0027605677023530006,
697
+ "learning_rate": 3e-07,
698
+ "loss": 0.0,
699
+ "reward": 0.020089286204893142,
700
+ "reward_std": 0.02404030319303274,
701
+ "rewards/accuracy_reward": 0.020089286204893142,
702
+ "step": 63
703
+ },
704
+ {
705
+ "completion_length": 616.587064743042,
706
+ "epoch": 0.3582925122463261,
707
+ "grad_norm": 0.006433432921767235,
708
+ "learning_rate": 3e-07,
709
+ "loss": 0.0,
710
+ "reward": 0.034970238571986556,
711
+ "reward_std": 0.0240207826718688,
712
+ "rewards/accuracy_reward": 0.034970238571986556,
713
+ "step": 64
714
+ },
715
+ {
716
+ "completion_length": 656.1890068054199,
717
+ "epoch": 0.363890832750175,
718
+ "grad_norm": 0.002678812015801668,
719
+ "learning_rate": 3e-07,
720
+ "loss": 0.0,
721
+ "reward": 0.038690476736519486,
722
+ "reward_std": 0.026529580354690552,
723
+ "rewards/accuracy_reward": 0.038690476736519486,
724
+ "step": 65
725
+ },
726
+ {
727
+ "completion_length": 615.4241199493408,
728
+ "epoch": 0.3694891532540238,
729
+ "grad_norm": 0.004133144393563271,
730
+ "learning_rate": 3e-07,
731
+ "loss": 0.0,
732
+ "reward": 0.055059525300748646,
733
+ "reward_std": 0.030434885527938604,
734
+ "rewards/accuracy_reward": 0.055059525300748646,
735
+ "step": 66
736
+ },
737
+ {
738
+ "completion_length": 631.1212978363037,
739
+ "epoch": 0.37508747375787266,
740
+ "grad_norm": 0.004037661012262106,
741
+ "learning_rate": 3e-07,
742
+ "loss": 0.0,
743
+ "reward": 0.038690477376803756,
744
+ "reward_std": 0.028071781154721975,
745
+ "rewards/accuracy_reward": 0.038690477376803756,
746
+ "step": 67
747
+ },
748
+ {
749
+ "completion_length": 577.1934661865234,
750
+ "epoch": 0.3806857942617215,
751
+ "grad_norm": 0.0031959640327841043,
752
+ "learning_rate": 3e-07,
753
+ "loss": 0.0,
754
+ "reward": 0.023809524427633733,
755
+ "reward_std": 0.0161665934138,
756
+ "rewards/accuracy_reward": 0.023809524427633733,
757
+ "step": 68
758
+ },
759
+ {
760
+ "completion_length": 645.9285850524902,
761
+ "epoch": 0.38628411476557034,
762
+ "grad_norm": 0.004407494328916073,
763
+ "learning_rate": 3e-07,
764
+ "loss": 0.0,
765
+ "reward": 0.030505953065585345,
766
+ "reward_std": 0.03433060785755515,
767
+ "rewards/accuracy_reward": 0.030505953065585345,
768
+ "step": 69
769
+ },
770
+ {
771
+ "completion_length": 629.8266506195068,
772
+ "epoch": 0.3918824352694192,
773
+ "grad_norm": 0.0024215257726609707,
774
+ "learning_rate": 3e-07,
775
+ "loss": 0.0,
776
+ "reward": 0.019345238513778895,
777
+ "reward_std": 0.02312279725447297,
778
+ "rewards/accuracy_reward": 0.019345238513778895,
779
+ "step": 70
780
+ },
781
+ {
782
+ "completion_length": 604.0178699493408,
783
+ "epoch": 0.397480755773268,
784
+ "grad_norm": 0.003344905562698841,
785
+ "learning_rate": 3e-07,
786
+ "loss": 0.0,
787
+ "reward": 0.02306547691114247,
788
+ "reward_std": 0.019507942255586386,
789
+ "rewards/accuracy_reward": 0.02306547691114247,
790
+ "step": 71
791
+ },
792
+ {
793
+ "completion_length": 590.7827472686768,
794
+ "epoch": 0.40307907627711687,
795
+ "grad_norm": 0.0028942637145519257,
796
+ "learning_rate": 3e-07,
797
+ "loss": 0.0,
798
+ "reward": 0.05803571501746774,
799
+ "reward_std": 0.03128055343404412,
800
+ "rewards/accuracy_reward": 0.05803571501746774,
801
+ "step": 72
802
+ },
803
+ {
804
+ "completion_length": 599.7842330932617,
805
+ "epoch": 0.4086773967809657,
806
+ "grad_norm": 0.0034949486143887043,
807
+ "learning_rate": 3e-07,
808
+ "loss": 0.0,
809
+ "reward": 0.05580357339931652,
810
+ "reward_std": 0.015248052775859833,
811
+ "rewards/accuracy_reward": 0.05580357339931652,
812
+ "step": 73
813
+ },
814
+ {
815
+ "completion_length": 635.7009048461914,
816
+ "epoch": 0.41427571728481455,
817
+ "grad_norm": 0.0022625280544161797,
818
+ "learning_rate": 3e-07,
819
+ "loss": 0.0,
820
+ "reward": 0.02678571466822177,
821
+ "reward_std": 0.021662155631929636,
822
+ "rewards/accuracy_reward": 0.02678571466822177,
823
+ "step": 74
824
+ },
825
+ {
826
+ "completion_length": 631.5788726806641,
827
+ "epoch": 0.4198740377886634,
828
+ "grad_norm": 0.0037094622384756804,
829
+ "learning_rate": 3e-07,
830
+ "loss": 0.0,
831
+ "reward": 0.02604166726814583,
832
+ "reward_std": 0.02264805557206273,
833
+ "rewards/accuracy_reward": 0.02604166726814583,
834
+ "step": 75
835
+ },
836
+ {
837
+ "completion_length": 636.7358722686768,
838
+ "epoch": 0.42547235829251223,
839
+ "grad_norm": 0.003503567073494196,
840
+ "learning_rate": 3e-07,
841
+ "loss": 0.0,
842
+ "reward": 0.03273809503298253,
843
+ "reward_std": 0.02112219762057066,
844
+ "rewards/accuracy_reward": 0.03273809503298253,
845
+ "step": 76
846
+ },
847
+ {
848
+ "completion_length": 635.9628219604492,
849
+ "epoch": 0.4310706787963611,
850
+ "grad_norm": 0.0047474331222474575,
851
+ "learning_rate": 3e-07,
852
+ "loss": 0.0,
853
+ "reward": 0.04166666779201478,
854
+ "reward_std": 0.03789610881358385,
855
+ "rewards/accuracy_reward": 0.04166666779201478,
856
+ "step": 77
857
+ },
858
+ {
859
+ "completion_length": 638.1703987121582,
860
+ "epoch": 0.4366689993002099,
861
+ "grad_norm": 0.0018300635274499655,
862
+ "learning_rate": 3e-07,
863
+ "loss": 0.0,
864
+ "reward": 0.05282738315872848,
865
+ "reward_std": 0.01760453707538545,
866
+ "rewards/accuracy_reward": 0.05282738315872848,
867
+ "step": 78
868
+ },
869
+ {
870
+ "completion_length": 617.7492637634277,
871
+ "epoch": 0.44226731980405876,
872
+ "grad_norm": 0.0036325210239738226,
873
+ "learning_rate": 3e-07,
874
+ "loss": 0.0,
875
+ "reward": 0.04092262010090053,
876
+ "reward_std": 0.03621981432661414,
877
+ "rewards/accuracy_reward": 0.04092262010090053,
878
+ "step": 79
879
+ },
880
+ {
881
+ "completion_length": 621.1123561859131,
882
+ "epoch": 0.44786564030790765,
883
+ "grad_norm": 0.0025254676584154367,
884
+ "learning_rate": 3e-07,
885
+ "loss": 0.0,
886
+ "reward": 0.04092262004269287,
887
+ "reward_std": 0.02054001996293664,
888
+ "rewards/accuracy_reward": 0.04092262004269287,
889
+ "step": 80
890
+ },
891
+ {
892
+ "completion_length": 670.346004486084,
893
+ "epoch": 0.4534639608117565,
894
+ "grad_norm": 0.0038352429401129484,
895
+ "learning_rate": 3e-07,
896
+ "loss": 0.0,
897
+ "reward": 0.03497023903764784,
898
+ "reward_std": 0.03099754173308611,
899
+ "rewards/accuracy_reward": 0.03497023903764784,
900
+ "step": 81
901
+ },
902
+ {
903
+ "completion_length": 632.6949424743652,
904
+ "epoch": 0.45906228131560534,
905
+ "grad_norm": 0.005097648594528437,
906
+ "learning_rate": 3e-07,
907
+ "loss": 0.0,
908
+ "reward": 0.05059524026000872,
909
+ "reward_std": 0.02744494192302227,
910
+ "rewards/accuracy_reward": 0.05059524026000872,
911
+ "step": 82
912
+ },
913
+ {
914
+ "completion_length": 630.6183204650879,
915
+ "epoch": 0.4646606018194542,
916
+ "grad_norm": 0.0024996348656713963,
917
+ "learning_rate": 3e-07,
918
+ "loss": 0.0,
919
+ "reward": 0.012648809934034944,
920
+ "reward_std": 0.014683252666145563,
921
+ "rewards/accuracy_reward": 0.012648809934034944,
922
+ "step": 83
923
+ },
924
+ {
925
+ "completion_length": 582.6726245880127,
926
+ "epoch": 0.470258922323303,
927
+ "grad_norm": 0.0026008612476289272,
928
+ "learning_rate": 3e-07,
929
+ "loss": 0.0,
930
+ "reward": 0.037202382169198245,
931
+ "reward_std": 0.021662155631929636,
932
+ "rewards/accuracy_reward": 0.037202382169198245,
933
+ "step": 84
934
+ },
935
+ {
936
+ "completion_length": 665.8355827331543,
937
+ "epoch": 0.47585724282715186,
938
+ "grad_norm": 0.002596538746729493,
939
+ "learning_rate": 3e-07,
940
+ "loss": 0.0,
941
+ "reward": 0.04389881080714986,
942
+ "reward_std": 0.02897106483578682,
943
+ "rewards/accuracy_reward": 0.04389881080714986,
944
+ "step": 85
945
+ },
946
+ {
947
+ "completion_length": 635.4821529388428,
948
+ "epoch": 0.4814555633310007,
949
+ "grad_norm": 0.0027116115670651197,
950
+ "learning_rate": 3e-07,
951
+ "loss": 0.0,
952
+ "reward": 0.024553571769502014,
953
+ "reward_std": 0.025856829015538096,
954
+ "rewards/accuracy_reward": 0.024553571769502014,
955
+ "step": 86
956
+ },
957
+ {
958
+ "completion_length": 642.225456237793,
959
+ "epoch": 0.48705388383484954,
960
+ "grad_norm": 0.00335879810154438,
961
+ "learning_rate": 3e-07,
962
+ "loss": 0.0,
963
+ "reward": 0.0535714304423891,
964
+ "reward_std": 0.04018289828673005,
965
+ "rewards/accuracy_reward": 0.0535714304423891,
966
+ "step": 87
967
+ },
968
+ {
969
+ "completion_length": 611.2046222686768,
970
+ "epoch": 0.4926522043386984,
971
+ "grad_norm": 0.004874168895184994,
972
+ "learning_rate": 3e-07,
973
+ "loss": 0.0,
974
+ "reward": 0.06994047714397311,
975
+ "reward_std": 0.030564499087631702,
976
+ "rewards/accuracy_reward": 0.06994047714397311,
977
+ "step": 88
978
+ },
979
+ {
980
+ "completion_length": 634.81325340271,
981
+ "epoch": 0.4982505248425472,
982
+ "grad_norm": 0.0030458923429250717,
983
+ "learning_rate": 3e-07,
984
+ "loss": 0.0,
985
+ "reward": 0.03273809637175873,
986
+ "reward_std": 0.025404266081750393,
987
+ "rewards/accuracy_reward": 0.03273809637175873,
988
+ "step": 89
989
+ },
990
+ {
991
+ "completion_length": 606.618314743042,
992
+ "epoch": 0.5038488453463961,
993
+ "grad_norm": 0.0029052915051579475,
994
+ "learning_rate": 3e-07,
995
+ "loss": 0.0,
996
+ "reward": 0.034226191812194884,
997
+ "reward_std": 0.018181392922997475,
998
+ "rewards/accuracy_reward": 0.034226191812194884,
999
+ "step": 90
1000
+ },
1001
+ {
1002
+ "completion_length": 649.934534072876,
1003
+ "epoch": 0.509447165850245,
1004
+ "grad_norm": 0.0023663390893489122,
1005
+ "learning_rate": 3e-07,
1006
+ "loss": 0.0,
1007
+ "reward": 0.028273810050450265,
1008
+ "reward_std": 0.014822450000792742,
1009
+ "rewards/accuracy_reward": 0.028273810050450265,
1010
+ "step": 91
1011
+ },
1012
+ {
1013
+ "completion_length": 645.944206237793,
1014
+ "epoch": 0.5150454863540938,
1015
+ "grad_norm": 0.002700702054426074,
1016
+ "learning_rate": 3e-07,
1017
+ "loss": -0.0,
1018
+ "reward": 0.026041666977107525,
1019
+ "reward_std": 0.023188014514744282,
1020
+ "rewards/accuracy_reward": 0.026041666977107525,
1021
+ "step": 92
1022
+ },
1023
+ {
1024
+ "completion_length": 606.7001571655273,
1025
+ "epoch": 0.5206438068579426,
1026
+ "grad_norm": 0.002376874443143606,
1027
+ "learning_rate": 3e-07,
1028
+ "loss": 0.0,
1029
+ "reward": 0.02455357206054032,
1030
+ "reward_std": 0.02123525319620967,
1031
+ "rewards/accuracy_reward": 0.02455357206054032,
1032
+ "step": 93
1033
+ },
1034
+ {
1035
+ "completion_length": 635.0580425262451,
1036
+ "epoch": 0.5262421273617914,
1037
+ "grad_norm": 0.0022008493542671204,
1038
+ "learning_rate": 3e-07,
1039
+ "loss": 0.0,
1040
+ "reward": 0.02678571513388306,
1041
+ "reward_std": 0.016507241874933243,
1042
+ "rewards/accuracy_reward": 0.02678571513388306,
1043
+ "step": 94
1044
+ },
1045
+ {
1046
+ "completion_length": 651.9226360321045,
1047
+ "epoch": 0.5318404478656403,
1048
+ "grad_norm": 0.003217194229364395,
1049
+ "learning_rate": 3e-07,
1050
+ "loss": 0.0,
1051
+ "reward": 0.04464285826543346,
1052
+ "reward_std": 0.018883246928453445,
1053
+ "rewards/accuracy_reward": 0.04464285826543346,
1054
+ "step": 95
1055
+ },
1056
+ {
1057
+ "completion_length": 621.9144458770752,
1058
+ "epoch": 0.5374387683694891,
1059
+ "grad_norm": 0.0026905853301286697,
1060
+ "learning_rate": 3e-07,
1061
+ "loss": 0.0,
1062
+ "reward": 0.04166666849050671,
1063
+ "reward_std": 0.022358688060194254,
1064
+ "rewards/accuracy_reward": 0.04166666849050671,
1065
+ "step": 96
1066
+ },
1067
+ {
1068
+ "completion_length": 630.8422737121582,
1069
+ "epoch": 0.543037088873338,
1070
+ "grad_norm": 0.00430277269333601,
1071
+ "learning_rate": 3e-07,
1072
+ "loss": 0.0,
1073
+ "reward": 0.03422619169577956,
1074
+ "reward_std": 0.03490746580064297,
1075
+ "rewards/accuracy_reward": 0.03422619169577956,
1076
+ "step": 97
1077
+ },
1078
+ {
1079
+ "completion_length": 635.1577453613281,
1080
+ "epoch": 0.5486354093771868,
1081
+ "grad_norm": 0.0027177336160093546,
1082
+ "learning_rate": 3e-07,
1083
+ "loss": 0.0,
1084
+ "reward": 0.024553572409786284,
1085
+ "reward_std": 0.01907807867974043,
1086
+ "rewards/accuracy_reward": 0.024553572409786284,
1087
+ "step": 98
1088
+ },
1089
+ {
1090
+ "completion_length": 621.9509105682373,
1091
+ "epoch": 0.5542337298810357,
1092
+ "grad_norm": 0.0029670181684195995,
1093
+ "learning_rate": 3e-07,
1094
+ "loss": 0.0,
1095
+ "reward": 0.04761904920451343,
1096
+ "reward_std": 0.024105519521981478,
1097
+ "rewards/accuracy_reward": 0.04761904920451343,
1098
+ "step": 99
1099
+ },
1100
+ {
1101
+ "completion_length": 645.11012840271,
1102
+ "epoch": 0.5598320503848845,
1103
+ "grad_norm": 0.004191585350781679,
1104
+ "learning_rate": 3e-07,
1105
+ "loss": 0.0,
1106
+ "reward": 0.03720238246023655,
1107
+ "reward_std": 0.027021698653697968,
1108
+ "rewards/accuracy_reward": 0.03720238246023655,
1109
+ "step": 100
1110
+ },
1111
+ {
1112
+ "completion_length": 628.647331237793,
1113
+ "epoch": 0.5654303708887334,
1114
+ "grad_norm": 0.005200605373829603,
1115
+ "learning_rate": 3e-07,
1116
+ "loss": 0.0,
1117
+ "reward": 0.04017857293365523,
1118
+ "reward_std": 0.032400546595454216,
1119
+ "rewards/accuracy_reward": 0.04017857293365523,
1120
+ "step": 101
1121
+ },
1122
+ {
1123
+ "completion_length": 674.1391506195068,
1124
+ "epoch": 0.5710286913925823,
1125
+ "grad_norm": 0.00332686142064631,
1126
+ "learning_rate": 3e-07,
1127
+ "loss": 0.0,
1128
+ "reward": 0.039434525242540985,
1129
+ "reward_std": 0.02585682924836874,
1130
+ "rewards/accuracy_reward": 0.039434525242540985,
1131
+ "step": 102
1132
+ },
1133
+ {
1134
+ "completion_length": 635.6376628875732,
1135
+ "epoch": 0.5766270118964311,
1136
+ "grad_norm": 0.002928570844233036,
1137
+ "learning_rate": 3e-07,
1138
+ "loss": 0.0,
1139
+ "reward": 0.03348214377183467,
1140
+ "reward_std": 0.017823366448283195,
1141
+ "rewards/accuracy_reward": 0.03348214377183467,
1142
+ "step": 103
1143
+ },
1144
+ {
1145
+ "completion_length": 667.8132553100586,
1146
+ "epoch": 0.58222533240028,
1147
+ "grad_norm": 0.0027422241400927305,
1148
+ "learning_rate": 3e-07,
1149
+ "loss": 0.0,
1150
+ "reward": 0.05059524020180106,
1151
+ "reward_std": 0.02381271030753851,
1152
+ "rewards/accuracy_reward": 0.05059524020180106,
1153
+ "step": 104
1154
+ },
1155
+ {
1156
+ "completion_length": 607.5372142791748,
1157
+ "epoch": 0.5878236529041287,
1158
+ "grad_norm": 0.0026503645349293947,
1159
+ "learning_rate": 3e-07,
1160
+ "loss": 0.0,
1161
+ "reward": 0.023809524660464376,
1162
+ "reward_std": 0.021662155631929636,
1163
+ "rewards/accuracy_reward": 0.023809524660464376,
1164
+ "step": 105
1165
+ },
1166
+ {
1167
+ "completion_length": 622.7715854644775,
1168
+ "epoch": 0.5934219734079776,
1169
+ "grad_norm": 0.003517127363011241,
1170
+ "learning_rate": 3e-07,
1171
+ "loss": 0.0,
1172
+ "reward": 0.04836309718666598,
1173
+ "reward_std": 0.03329852968454361,
1174
+ "rewards/accuracy_reward": 0.04836309718666598,
1175
+ "step": 106
1176
+ },
1177
+ {
1178
+ "completion_length": 647.0959930419922,
1179
+ "epoch": 0.5990202939118264,
1180
+ "grad_norm": 0.0036508163902908564,
1181
+ "learning_rate": 3e-07,
1182
+ "loss": 0.0,
1183
+ "reward": 0.061755954287946224,
1184
+ "reward_std": 0.03932873113080859,
1185
+ "rewards/accuracy_reward": 0.061755954287946224,
1186
+ "step": 107
1187
+ },
1188
+ {
1189
+ "completion_length": 623.8727836608887,
1190
+ "epoch": 0.6046186144156753,
1191
+ "grad_norm": 0.0034824141766875982,
1192
+ "learning_rate": 3e-07,
1193
+ "loss": 0.0,
1194
+ "reward": 0.05282738321693614,
1195
+ "reward_std": 0.023543079383671284,
1196
+ "rewards/accuracy_reward": 0.05282738321693614,
1197
+ "step": 108
1198
+ },
1199
+ {
1200
+ "completion_length": 646.765645980835,
1201
+ "epoch": 0.6102169349195241,
1202
+ "grad_norm": 0.0026973283383995295,
1203
+ "learning_rate": 3e-07,
1204
+ "loss": 0.0,
1205
+ "reward": 0.017113095498643816,
1206
+ "reward_std": 0.017985261976718903,
1207
+ "rewards/accuracy_reward": 0.017113095498643816,
1208
+ "step": 109
1209
+ },
1210
+ {
1211
+ "completion_length": 625.6376571655273,
1212
+ "epoch": 0.615815255423373,
1213
+ "grad_norm": 0.0037007054779678583,
1214
+ "learning_rate": 3e-07,
1215
+ "loss": 0.0,
1216
+ "reward": 0.06547619227785617,
1217
+ "reward_std": 0.040159355383366346,
1218
+ "rewards/accuracy_reward": 0.06547619227785617,
1219
+ "step": 110
1220
+ },
1221
+ {
1222
+ "completion_length": 657.3631019592285,
1223
+ "epoch": 0.6214135759272218,
1224
+ "grad_norm": 0.0027858198154717684,
1225
+ "learning_rate": 3e-07,
1226
+ "loss": 0.0,
1227
+ "reward": 0.027529762883204967,
1228
+ "reward_std": 0.016143894754350185,
1229
+ "rewards/accuracy_reward": 0.027529762883204967,
1230
+ "step": 111
1231
+ },
1232
+ {
1233
+ "completion_length": 627.3422756195068,
1234
+ "epoch": 0.6270118964310707,
1235
+ "grad_norm": 0.0035545658320188522,
1236
+ "learning_rate": 3e-07,
1237
+ "loss": 0.0,
1238
+ "reward": 0.05059523967793211,
1239
+ "reward_std": 0.03195094550028443,
1240
+ "rewards/accuracy_reward": 0.05059523967793211,
1241
+ "step": 112
1242
+ },
1243
+ {
1244
+ "completion_length": 629.8177185058594,
1245
+ "epoch": 0.6326102169349195,
1246
+ "grad_norm": 0.0040982505306601524,
1247
+ "learning_rate": 3e-07,
1248
+ "loss": 0.0,
1249
+ "reward": 0.05357142956927419,
1250
+ "reward_std": 0.03337568882852793,
1251
+ "rewards/accuracy_reward": 0.05357142956927419,
1252
+ "step": 113
1253
+ },
1254
+ {
1255
+ "completion_length": 650.6034278869629,
1256
+ "epoch": 0.6382085374387684,
1257
+ "grad_norm": 0.0028056029696017504,
1258
+ "learning_rate": 3e-07,
1259
+ "loss": 0.0,
1260
+ "reward": 0.05208333529299125,
1261
+ "reward_std": 0.01970939477905631,
1262
+ "rewards/accuracy_reward": 0.05208333529299125,
1263
+ "step": 114
1264
+ },
1265
+ {
1266
+ "completion_length": 649.5796318054199,
1267
+ "epoch": 0.6438068579426172,
1268
+ "grad_norm": 0.0023333376739174128,
1269
+ "learning_rate": 3e-07,
1270
+ "loss": 0.0,
1271
+ "reward": 0.014880952483508736,
1272
+ "reward_std": 0.010090996511280537,
1273
+ "rewards/accuracy_reward": 0.014880952483508736,
1274
+ "step": 115
1275
+ },
1276
+ {
1277
+ "completion_length": 645.5312652587891,
1278
+ "epoch": 0.6494051784464661,
1279
+ "grad_norm": 0.0031304731965065002,
1280
+ "learning_rate": 3e-07,
1281
+ "loss": 0.0,
1282
+ "reward": 0.022321428870782256,
1283
+ "reward_std": 0.015947763342410326,
1284
+ "rewards/accuracy_reward": 0.022321428870782256,
1285
+ "step": 116
1286
+ },
1287
+ {
1288
+ "completion_length": 606.377986907959,
1289
+ "epoch": 0.655003498950315,
1290
+ "grad_norm": 0.004076777026057243,
1291
+ "learning_rate": 3e-07,
1292
+ "loss": 0.0,
1293
+ "reward": 0.030505952949170023,
1294
+ "reward_std": 0.028484483249485493,
1295
+ "rewards/accuracy_reward": 0.030505952949170023,
1296
+ "step": 117
1297
+ },
1298
+ {
1299
+ "completion_length": 633.9389953613281,
1300
+ "epoch": 0.6606018194541637,
1301
+ "grad_norm": 0.0019400623859837651,
1302
+ "learning_rate": 3e-07,
1303
+ "loss": -0.0,
1304
+ "reward": 0.01934523874660954,
1305
+ "reward_std": 0.014487121719866991,
1306
+ "rewards/accuracy_reward": 0.01934523874660954,
1307
+ "step": 118
1308
+ },
1309
+ {
1310
+ "completion_length": 626.8236713409424,
1311
+ "epoch": 0.6662001399580126,
1312
+ "grad_norm": 0.0019256924279034138,
1313
+ "learning_rate": 3e-07,
1314
+ "loss": 0.0,
1315
+ "reward": 0.040178572409786284,
1316
+ "reward_std": 0.013790588825941086,
1317
+ "rewards/accuracy_reward": 0.040178572409786284,
1318
+ "step": 119
1319
+ },
1320
+ {
1321
+ "completion_length": 633.7790336608887,
1322
+ "epoch": 0.6717984604618614,
1323
+ "grad_norm": 0.0031517883762717247,
1324
+ "learning_rate": 3e-07,
1325
+ "loss": 0.0,
1326
+ "reward": 0.04092261998448521,
1327
+ "reward_std": 0.022219491191208363,
1328
+ "rewards/accuracy_reward": 0.04092261998448521,
1329
+ "step": 120
1330
+ },
1331
+ {
1332
+ "completion_length": 648.1837844848633,
1333
+ "epoch": 0.6773967809657103,
1334
+ "grad_norm": 0.0026536902878433466,
1335
+ "learning_rate": 3e-07,
1336
+ "loss": 0.0,
1337
+ "reward": 0.032738096197135746,
1338
+ "reward_std": 0.02146284654736519,
1339
+ "rewards/accuracy_reward": 0.032738096197135746,
1340
+ "step": 121
1341
+ },
1342
+ {
1343
+ "completion_length": 652.9933204650879,
1344
+ "epoch": 0.6829951014695591,
1345
+ "grad_norm": 0.0033722377847880125,
1346
+ "learning_rate": 3e-07,
1347
+ "loss": 0.0,
1348
+ "reward": 0.023809524544049054,
1349
+ "reward_std": 0.020562718622386456,
1350
+ "rewards/accuracy_reward": 0.023809524544049054,
1351
+ "step": 122
1352
+ },
1353
+ {
1354
+ "completion_length": 656.3534355163574,
1355
+ "epoch": 0.688593421973408,
1356
+ "grad_norm": 0.002776005771011114,
1357
+ "learning_rate": 3e-07,
1358
+ "loss": 0.0,
1359
+ "reward": 0.034970239794347435,
1360
+ "reward_std": 0.01705795805901289,
1361
+ "rewards/accuracy_reward": 0.034970239794347435,
1362
+ "step": 123
1363
+ },
1364
+ {
1365
+ "completion_length": 610.5788822174072,
1366
+ "epoch": 0.6941917424772568,
1367
+ "grad_norm": 0.0037796536926180124,
1368
+ "learning_rate": 3e-07,
1369
+ "loss": 0.0,
1370
+ "reward": 0.07142857392318547,
1371
+ "reward_std": 0.03704408532939851,
1372
+ "rewards/accuracy_reward": 0.07142857392318547,
1373
+ "step": 124
1374
+ },
1375
+ {
1376
+ "completion_length": 639.4814128875732,
1377
+ "epoch": 0.6997900629811057,
1378
+ "grad_norm": 0.003291892819106579,
1379
+ "learning_rate": 3e-07,
1380
+ "loss": 0.0,
1381
+ "reward": 0.05133928789291531,
1382
+ "reward_std": 0.033701435662806034,
1383
+ "rewards/accuracy_reward": 0.05133928789291531,
1384
+ "step": 125
1385
+ },
1386
+ {
1387
+ "completion_length": 627.3214416503906,
1388
+ "epoch": 0.7053883834849545,
1389
+ "grad_norm": 0.002914518816396594,
1390
+ "learning_rate": 3e-07,
1391
+ "loss": 0.0,
1392
+ "reward": 0.0386904776096344,
1393
+ "reward_std": 0.02166215470060706,
1394
+ "rewards/accuracy_reward": 0.0386904776096344,
1395
+ "step": 126
1396
+ },
1397
+ {
1398
+ "completion_length": 614.4308052062988,
1399
+ "epoch": 0.7109867039888034,
1400
+ "grad_norm": 0.003878154093399644,
1401
+ "learning_rate": 3e-07,
1402
+ "loss": 0.0,
1403
+ "reward": 0.03348214388824999,
1404
+ "reward_std": 0.018164014909416437,
1405
+ "rewards/accuracy_reward": 0.03348214388824999,
1406
+ "step": 127
1407
+ },
1408
+ {
1409
+ "completion_length": 637.3244171142578,
1410
+ "epoch": 0.7165850244926522,
1411
+ "grad_norm": 0.002592942677438259,
1412
+ "learning_rate": 3e-07,
1413
+ "loss": 0.0,
1414
+ "reward": 0.026785714901052415,
1415
+ "reward_std": 0.01852204231545329,
1416
+ "rewards/accuracy_reward": 0.026785714901052415,
1417
+ "step": 128
1418
+ },
1419
+ {
1420
+ "completion_length": 662.0282936096191,
1421
+ "epoch": 0.722183344996501,
1422
+ "grad_norm": 0.0030688210390508175,
1423
+ "learning_rate": 3e-07,
1424
+ "loss": 0.0,
1425
+ "reward": 0.0424107150756754,
1426
+ "reward_std": 0.029373969649896026,
1427
+ "rewards/accuracy_reward": 0.0424107150756754,
1428
+ "step": 129
1429
+ },
1430
+ {
1431
+ "completion_length": 609.4747123718262,
1432
+ "epoch": 0.72778166550035,
1433
+ "grad_norm": 0.0026889187283813953,
1434
+ "learning_rate": 3e-07,
1435
+ "loss": 0.0,
1436
+ "reward": 0.03869047720218077,
1437
+ "reward_std": 0.021642634645104408,
1438
+ "rewards/accuracy_reward": 0.03869047720218077,
1439
+ "step": 130
1440
+ },
1441
+ {
1442
+ "completion_length": 628.831859588623,
1443
+ "epoch": 0.7333799860041987,
1444
+ "grad_norm": 0.0032478254288434982,
1445
+ "learning_rate": 3e-07,
1446
+ "loss": 0.0,
1447
+ "reward": 0.019345238571986556,
1448
+ "reward_std": 0.01975191291421652,
1449
+ "rewards/accuracy_reward": 0.019345238571986556,
1450
+ "step": 131
1451
+ },
1452
+ {
1453
+ "completion_length": 642.3846893310547,
1454
+ "epoch": 0.7389783065080476,
1455
+ "grad_norm": 0.0019529862329363823,
1456
+ "learning_rate": 3e-07,
1457
+ "loss": 0.0,
1458
+ "reward": 0.01116071455180645,
1459
+ "reward_std": 0.013233252801001072,
1460
+ "rewards/accuracy_reward": 0.01116071455180645,
1461
+ "step": 132
1462
+ },
1463
+ {
1464
+ "completion_length": 634.9181728363037,
1465
+ "epoch": 0.7445766270118964,
1466
+ "grad_norm": 0.004057868849486113,
1467
+ "learning_rate": 3e-07,
1468
+ "loss": 0.0,
1469
+ "reward": 0.031250000873114914,
1470
+ "reward_std": 0.040879431180655956,
1471
+ "rewards/accuracy_reward": 0.031250000873114914,
1472
+ "step": 133
1473
+ },
1474
+ {
1475
+ "completion_length": 609.6331977844238,
1476
+ "epoch": 0.7501749475157453,
1477
+ "grad_norm": 0.003426521783694625,
1478
+ "learning_rate": 3e-07,
1479
+ "loss": 0.0,
1480
+ "reward": 0.038690477260388434,
1481
+ "reward_std": 0.029601082671433687,
1482
+ "rewards/accuracy_reward": 0.038690477260388434,
1483
+ "step": 134
1484
+ },
1485
+ {
1486
+ "completion_length": 639.4613227844238,
1487
+ "epoch": 0.7557732680195941,
1488
+ "grad_norm": 0.003970231860876083,
1489
+ "learning_rate": 3e-07,
1490
+ "loss": 0.0,
1491
+ "reward": 0.054315477260388434,
1492
+ "reward_std": 0.029604259878396988,
1493
+ "rewards/accuracy_reward": 0.054315477260388434,
1494
+ "step": 135
1495
+ },
1496
+ {
1497
+ "completion_length": 614.8199501037598,
1498
+ "epoch": 0.761371588523443,
1499
+ "grad_norm": 0.0031252307817339897,
1500
+ "learning_rate": 3e-07,
1501
+ "loss": 0.0,
1502
+ "reward": 0.05654762062476948,
1503
+ "reward_std": 0.02807308081537485,
1504
+ "rewards/accuracy_reward": 0.05654762062476948,
1505
+ "step": 136
1506
+ },
1507
+ {
1508
+ "completion_length": 640.7924194335938,
1509
+ "epoch": 0.7669699090272918,
1510
+ "grad_norm": 0.0020789685659110546,
1511
+ "learning_rate": 3e-07,
1512
+ "loss": 0.0,
1513
+ "reward": 0.019345238397363573,
1514
+ "reward_std": 0.015046600718051195,
1515
+ "rewards/accuracy_reward": 0.019345238397363573,
1516
+ "step": 137
1517
+ },
1518
+ {
1519
+ "completion_length": 640.4226322174072,
1520
+ "epoch": 0.7725682295311407,
1521
+ "grad_norm": 0.0019399580778554082,
1522
+ "learning_rate": 3e-07,
1523
+ "loss": 0.0,
1524
+ "reward": 0.012648809934034944,
1525
+ "reward_std": 0.013656496535986662,
1526
+ "rewards/accuracy_reward": 0.012648809934034944,
1527
+ "step": 138
1528
+ },
1529
+ {
1530
+ "completion_length": 594.6205444335938,
1531
+ "epoch": 0.7781665500349895,
1532
+ "grad_norm": 0.0063768248073756695,
1533
+ "learning_rate": 3e-07,
1534
+ "loss": 0.0,
1535
+ "reward": 0.052083334885537624,
1536
+ "reward_std": 0.023117476608604193,
1537
+ "rewards/accuracy_reward": 0.052083334885537624,
1538
+ "step": 139
1539
+ },
1540
+ {
1541
+ "completion_length": 613.655517578125,
1542
+ "epoch": 0.7837648705388384,
1543
+ "grad_norm": 0.0031261774711310863,
1544
+ "learning_rate": 3e-07,
1545
+ "loss": 0.0,
1546
+ "reward": 0.039434525300748646,
1547
+ "reward_std": 0.020764170680195093,
1548
+ "rewards/accuracy_reward": 0.039434525300748646,
1549
+ "step": 140
1550
+ },
1551
+ {
1552
+ "completion_length": 645.6837902069092,
1553
+ "epoch": 0.7893631910426872,
1554
+ "grad_norm": 0.0014134430093690753,
1555
+ "learning_rate": 3e-07,
1556
+ "loss": -0.0,
1557
+ "reward": 0.02157738187815994,
1558
+ "reward_std": 0.007513539865612984,
1559
+ "rewards/accuracy_reward": 0.02157738187815994,
1560
+ "step": 141
1561
+ },
1562
+ {
1563
+ "completion_length": 630.043176651001,
1564
+ "epoch": 0.794961511546536,
1565
+ "grad_norm": 0.004378010053187609,
1566
+ "learning_rate": 3e-07,
1567
+ "loss": 0.0,
1568
+ "reward": 0.04241071571595967,
1569
+ "reward_std": 0.03774271160364151,
1570
+ "rewards/accuracy_reward": 0.04241071571595967,
1571
+ "step": 142
1572
+ },
1573
+ {
1574
+ "completion_length": 622.1555137634277,
1575
+ "epoch": 0.8005598320503848,
1576
+ "grad_norm": 0.0029741383623331785,
1577
+ "learning_rate": 3e-07,
1578
+ "loss": 0.0,
1579
+ "reward": 0.00892857153667137,
1580
+ "reward_std": 0.016726072411984205,
1581
+ "rewards/accuracy_reward": 0.00892857153667137,
1582
+ "step": 143
1583
+ },
1584
+ {
1585
+ "completion_length": 646.7626647949219,
1586
+ "epoch": 0.8061581525542337,
1587
+ "grad_norm": 0.0028938716277480125,
1588
+ "learning_rate": 3e-07,
1589
+ "loss": 0.0,
1590
+ "reward": 0.021577381528913975,
1591
+ "reward_std": 0.022778970655053854,
1592
+ "rewards/accuracy_reward": 0.021577381528913975,
1593
+ "step": 144
1594
+ },
1595
+ {
1596
+ "completion_length": 651.0178699493408,
1597
+ "epoch": 0.8117564730580826,
1598
+ "grad_norm": 0.003098010318353772,
1599
+ "learning_rate": 3e-07,
1600
+ "loss": 0.0,
1601
+ "reward": 0.023809524718672037,
1602
+ "reward_std": 0.00955103849992156,
1603
+ "rewards/accuracy_reward": 0.023809524718672037,
1604
+ "step": 145
1605
+ },
1606
+ {
1607
+ "completion_length": 655.3891487121582,
1608
+ "epoch": 0.8173547935619314,
1609
+ "grad_norm": 0.002411956200376153,
1610
+ "learning_rate": 3e-07,
1611
+ "loss": 0.0,
1612
+ "reward": 0.028273810166865587,
1613
+ "reward_std": 0.024912146851420403,
1614
+ "rewards/accuracy_reward": 0.028273810166865587,
1615
+ "step": 146
1616
+ },
1617
+ {
1618
+ "completion_length": 660.3393001556396,
1619
+ "epoch": 0.8229531140657803,
1620
+ "grad_norm": 0.0024566147476434708,
1621
+ "learning_rate": 3e-07,
1622
+ "loss": 0.0,
1623
+ "reward": 0.03199404838960618,
1624
+ "reward_std": 0.021460703574121,
1625
+ "rewards/accuracy_reward": 0.03199404838960618,
1626
+ "step": 147
1627
+ },
1628
+ {
1629
+ "completion_length": 660.4471855163574,
1630
+ "epoch": 0.8285514345696291,
1631
+ "grad_norm": 0.0033500257413834333,
1632
+ "learning_rate": 3e-07,
1633
+ "loss": 0.0,
1634
+ "reward": 0.03199404838960618,
1635
+ "reward_std": 0.026453721337020397,
1636
+ "rewards/accuracy_reward": 0.03199404838960618,
1637
+ "step": 148
1638
+ },
1639
+ {
1640
+ "completion_length": 616.9553737640381,
1641
+ "epoch": 0.834149755073478,
1642
+ "grad_norm": 0.0035977945663034916,
1643
+ "learning_rate": 3e-07,
1644
+ "loss": 0.0,
1645
+ "reward": 0.04613095358945429,
1646
+ "reward_std": 0.03803316270932555,
1647
+ "rewards/accuracy_reward": 0.04613095358945429,
1648
+ "step": 149
1649
+ },
1650
+ {
1651
+ "completion_length": 624.0811023712158,
1652
+ "epoch": 0.8397480755773268,
1653
+ "grad_norm": 0.0024934441316872835,
1654
+ "learning_rate": 3e-07,
1655
+ "loss": -0.0,
1656
+ "reward": 0.020089286321308464,
1657
+ "reward_std": 0.014129094779491425,
1658
+ "rewards/accuracy_reward": 0.020089286321308464,
1659
+ "step": 150
1660
+ },
1661
+ {
1662
+ "completion_length": 649.3125076293945,
1663
+ "epoch": 0.8453463960811757,
1664
+ "grad_norm": 0.0040410468354821205,
1665
+ "learning_rate": 3e-07,
1666
+ "loss": 0.0,
1667
+ "reward": 0.08035714528523386,
1668
+ "reward_std": 0.037069959565997124,
1669
+ "rewards/accuracy_reward": 0.08035714528523386,
1670
+ "step": 151
1671
+ },
1672
+ {
1673
+ "completion_length": 655.87575340271,
1674
+ "epoch": 0.8509447165850245,
1675
+ "grad_norm": 0.0036378325894474983,
1676
+ "learning_rate": 3e-07,
1677
+ "loss": 0.0,
1678
+ "reward": 0.020089286554139107,
1679
+ "reward_std": 0.025742772268131375,
1680
+ "rewards/accuracy_reward": 0.020089286554139107,
1681
+ "step": 152
1682
+ },
1683
+ {
1684
+ "completion_length": 608.526050567627,
1685
+ "epoch": 0.8565430370888734,
1686
+ "grad_norm": 0.0019003109773620963,
1687
+ "learning_rate": 3e-07,
1688
+ "loss": 0.0,
1689
+ "reward": 0.019345238339155912,
1690
+ "reward_std": 0.013455044478178024,
1691
+ "rewards/accuracy_reward": 0.019345238339155912,
1692
+ "step": 153
1693
+ },
1694
+ {
1695
+ "completion_length": 605.8340892791748,
1696
+ "epoch": 0.8621413575927221,
1697
+ "grad_norm": 0.002737295813858509,
1698
+ "learning_rate": 3e-07,
1699
+ "loss": 0.0,
1700
+ "reward": 0.04538690613117069,
1701
+ "reward_std": 0.025694933719933033,
1702
+ "rewards/accuracy_reward": 0.04538690613117069,
1703
+ "step": 154
1704
+ },
1705
+ {
1706
+ "completion_length": 649.8913841247559,
1707
+ "epoch": 0.867739678096571,
1708
+ "grad_norm": 0.0013863355852663517,
1709
+ "learning_rate": 3e-07,
1710
+ "loss": -0.0,
1711
+ "reward": 0.012648810050450265,
1712
+ "reward_std": 0.007513539865612984,
1713
+ "rewards/accuracy_reward": 0.012648810050450265,
1714
+ "step": 155
1715
+ },
1716
+ {
1717
+ "completion_length": 649.567720413208,
1718
+ "epoch": 0.8733379986004198,
1719
+ "grad_norm": 0.003731328761205077,
1720
+ "learning_rate": 3e-07,
1721
+ "loss": 0.0,
1722
+ "reward": 0.020089286379516125,
1723
+ "reward_std": 0.022558840923011303,
1724
+ "rewards/accuracy_reward": 0.020089286379516125,
1725
+ "step": 156
1726
+ },
1727
+ {
1728
+ "completion_length": 661.0640029907227,
1729
+ "epoch": 0.8789363191042687,
1730
+ "grad_norm": 0.0034664925187826157,
1731
+ "learning_rate": 3e-07,
1732
+ "loss": 0.0,
1733
+ "reward": 0.05505952559178695,
1734
+ "reward_std": 0.035452743992209435,
1735
+ "rewards/accuracy_reward": 0.05505952559178695,
1736
+ "step": 157
1737
+ },
1738
+ {
1739
+ "completion_length": 616.1681728363037,
1740
+ "epoch": 0.8845346396081175,
1741
+ "grad_norm": 0.003077705856412649,
1742
+ "learning_rate": 3e-07,
1743
+ "loss": 0.0,
1744
+ "reward": 0.020833333721384406,
1745
+ "reward_std": 0.023389466106891632,
1746
+ "rewards/accuracy_reward": 0.020833333721384406,
1747
+ "step": 158
1748
+ },
1749
+ {
1750
+ "completion_length": 645.6845321655273,
1751
+ "epoch": 0.8901329601119664,
1752
+ "grad_norm": 0.0034521420020610094,
1753
+ "learning_rate": 3e-07,
1754
+ "loss": 0.0,
1755
+ "reward": 0.02380952425301075,
1756
+ "reward_std": 0.01677391119301319,
1757
+ "rewards/accuracy_reward": 0.02380952425301075,
1758
+ "step": 159
1759
+ },
1760
+ {
1761
+ "completion_length": 621.7961502075195,
1762
+ "epoch": 0.8957312806158153,
1763
+ "grad_norm": 0.0036637301091104746,
1764
+ "learning_rate": 3e-07,
1765
+ "loss": 0.0,
1766
+ "reward": 0.04092262004269287,
1767
+ "reward_std": 0.02751574432477355,
1768
+ "rewards/accuracy_reward": 0.04092262004269287,
1769
+ "step": 160
1770
+ },
1771
+ {
1772
+ "completion_length": 661.4003067016602,
1773
+ "epoch": 0.9013296011196641,
1774
+ "grad_norm": 0.0030420024413615465,
1775
+ "learning_rate": 3e-07,
1776
+ "loss": 0.0,
1777
+ "reward": 0.031250000989530236,
1778
+ "reward_std": 0.022196792997419834,
1779
+ "rewards/accuracy_reward": 0.031250000989530236,
1780
+ "step": 161
1781
+ },
1782
+ {
1783
+ "completion_length": 636.8690567016602,
1784
+ "epoch": 0.906927921623513,
1785
+ "grad_norm": 0.003414291888475418,
1786
+ "learning_rate": 3e-07,
1787
+ "loss": 0.0,
1788
+ "reward": 0.05357143084984273,
1789
+ "reward_std": 0.021321506705135107,
1790
+ "rewards/accuracy_reward": 0.05357143084984273,
1791
+ "step": 162
1792
+ },
1793
+ {
1794
+ "completion_length": 641.8973331451416,
1795
+ "epoch": 0.9125262421273618,
1796
+ "grad_norm": 0.0033480250276625156,
1797
+ "learning_rate": 3e-07,
1798
+ "loss": 0.0,
1799
+ "reward": 0.03720238176174462,
1800
+ "reward_std": 0.029198394622653723,
1801
+ "rewards/accuracy_reward": 0.03720238176174462,
1802
+ "step": 163
1803
+ },
1804
+ {
1805
+ "completion_length": 623.6264972686768,
1806
+ "epoch": 0.9181245626312107,
1807
+ "grad_norm": 0.003853818401694298,
1808
+ "learning_rate": 3e-07,
1809
+ "loss": 0.0,
1810
+ "reward": 0.05729166802484542,
1811
+ "reward_std": 0.037587220780551434,
1812
+ "rewards/accuracy_reward": 0.05729166802484542,
1813
+ "step": 164
1814
+ },
1815
+ {
1816
+ "completion_length": 649.7075996398926,
1817
+ "epoch": 0.9237228831350595,
1818
+ "grad_norm": 0.0024723373353481293,
1819
+ "learning_rate": 3e-07,
1820
+ "loss": 0.0,
1821
+ "reward": 0.019345238513778895,
1822
+ "reward_std": 0.01928615104407072,
1823
+ "rewards/accuracy_reward": 0.019345238513778895,
1824
+ "step": 165
1825
+ },
1826
+ {
1827
+ "completion_length": 680.0818481445312,
1828
+ "epoch": 0.9293212036389084,
1829
+ "grad_norm": 0.00249727675691247,
1830
+ "learning_rate": 3e-07,
1831
+ "loss": 0.0,
1832
+ "reward": 0.03869047743501142,
1833
+ "reward_std": 0.015805388800799847,
1834
+ "rewards/accuracy_reward": 0.03869047743501142,
1835
+ "step": 166
1836
+ },
1837
+ {
1838
+ "completion_length": 606.4137096405029,
1839
+ "epoch": 0.9349195241427571,
1840
+ "grad_norm": 0.0031826056074351072,
1841
+ "learning_rate": 3e-07,
1842
+ "loss": 0.0,
1843
+ "reward": 0.04166666814126074,
1844
+ "reward_std": 0.02047350350767374,
1845
+ "rewards/accuracy_reward": 0.04166666814126074,
1846
+ "step": 167
1847
+ },
1848
+ {
1849
+ "completion_length": 620.4821529388428,
1850
+ "epoch": 0.940517844646606,
1851
+ "grad_norm": 0.0025734296068549156,
1852
+ "learning_rate": 3e-07,
1853
+ "loss": 0.0,
1854
+ "reward": 0.02380952431121841,
1855
+ "reward_std": 0.0181671935133636,
1856
+ "rewards/accuracy_reward": 0.02380952431121841,
1857
+ "step": 168
1858
+ },
1859
+ {
1860
+ "completion_length": 617.4836406707764,
1861
+ "epoch": 0.9461161651504548,
1862
+ "grad_norm": 0.0036193837877362967,
1863
+ "learning_rate": 3e-07,
1864
+ "loss": 0.0,
1865
+ "reward": 0.03199404873885214,
1866
+ "reward_std": 0.018744049593806267,
1867
+ "rewards/accuracy_reward": 0.03199404873885214,
1868
+ "step": 169
1869
+ },
1870
+ {
1871
+ "completion_length": 630.1562633514404,
1872
+ "epoch": 0.9517144856543037,
1873
+ "grad_norm": 0.0025704463478177786,
1874
+ "learning_rate": 3e-07,
1875
+ "loss": 0.0,
1876
+ "reward": 0.03497023897944018,
1877
+ "reward_std": 0.01300378143787384,
1878
+ "rewards/accuracy_reward": 0.03497023897944018,
1879
+ "step": 170
1880
+ },
1881
+ {
1882
+ "completion_length": 608.0171241760254,
1883
+ "epoch": 0.9573128061581525,
1884
+ "grad_norm": 0.003403712995350361,
1885
+ "learning_rate": 3e-07,
1886
+ "loss": 0.0,
1887
+ "reward": 0.05357143055880442,
1888
+ "reward_std": 0.030789734097197652,
1889
+ "rewards/accuracy_reward": 0.05357143055880442,
1890
+ "step": 171
1891
+ },
1892
+ {
1893
+ "completion_length": 624.5669803619385,
1894
+ "epoch": 0.9629111266620014,
1895
+ "grad_norm": 0.00244723167270422,
1896
+ "learning_rate": 3e-07,
1897
+ "loss": 0.0,
1898
+ "reward": 0.018601191113702953,
1899
+ "reward_std": 0.014688573777675629,
1900
+ "rewards/accuracy_reward": 0.018601191113702953,
1901
+ "step": 172
1902
+ },
1903
+ {
1904
+ "completion_length": 619.2753105163574,
1905
+ "epoch": 0.9685094471658502,
1906
+ "grad_norm": 0.003216799348592758,
1907
+ "learning_rate": 3e-07,
1908
+ "loss": 0.0,
1909
+ "reward": 0.015625000465661287,
1910
+ "reward_std": 0.011909665539860725,
1911
+ "rewards/accuracy_reward": 0.015625000465661287,
1912
+ "step": 173
1913
+ },
1914
+ {
1915
+ "completion_length": 603.6629619598389,
1916
+ "epoch": 0.9741077676696991,
1917
+ "grad_norm": 0.004921557381749153,
1918
+ "learning_rate": 3e-07,
1919
+ "loss": 0.0,
1920
+ "reward": 0.1026785732829012,
1921
+ "reward_std": 0.035813949070870876,
1922
+ "rewards/accuracy_reward": 0.1026785732829012,
1923
+ "step": 174
1924
+ },
1925
+ {
1926
+ "completion_length": 619.9709911346436,
1927
+ "epoch": 0.979706088173548,
1928
+ "grad_norm": 0.0021367412991821766,
1929
+ "learning_rate": 3e-07,
1930
+ "loss": 0.0,
1931
+ "reward": 0.03943452483508736,
1932
+ "reward_std": 0.017064577899873257,
1933
+ "rewards/accuracy_reward": 0.03943452483508736,
1934
+ "step": 175
1935
+ },
1936
+ {
1937
+ "completion_length": 661.3519515991211,
1938
+ "epoch": 0.9853044086773968,
1939
+ "grad_norm": 0.003553919028490782,
1940
+ "learning_rate": 3e-07,
1941
+ "loss": 0.0,
1942
+ "reward": 0.03422619169577956,
1943
+ "reward_std": 0.02724563330411911,
1944
+ "rewards/accuracy_reward": 0.03422619169577956,
1945
+ "step": 176
1946
+ },
1947
+ {
1948
+ "completion_length": 638.8660793304443,
1949
+ "epoch": 0.9909027291812457,
1950
+ "grad_norm": 0.0027842505369335413,
1951
+ "learning_rate": 3e-07,
1952
+ "loss": 0.0,
1953
+ "reward": 0.05803571594879031,
1954
+ "reward_std": 0.021928824484348297,
1955
+ "rewards/accuracy_reward": 0.05803571594879031,
1956
+ "step": 177
1957
+ },
1958
+ {
1959
+ "completion_length": 666.0945014953613,
1960
+ "epoch": 0.9965010496850945,
1961
+ "grad_norm": 0.004953757394105196,
1962
+ "learning_rate": 3e-07,
1963
+ "loss": 0.0,
1964
+ "reward": 0.03571428661234677,
1965
+ "reward_std": 0.03300916403532028,
1966
+ "rewards/accuracy_reward": 0.03571428661234677,
1967
+ "step": 178
1968
+ },
1969
+ {
1970
+ "epoch": 0.9965010496850945,
1971
+ "step": 178,
1972
+ "total_flos": 0.0,
1973
+ "train_loss": 1.5679008615386834e-09,
1974
+ "train_runtime": 33567.1333,
1975
+ "train_samples_per_second": 0.596,
1976
+ "train_steps_per_second": 0.005
1977
+ }
1978
+ ],
1979
+ "logging_steps": 1,
1980
+ "max_steps": 178,
1981
+ "num_input_tokens_seen": 0,
1982
+ "num_train_epochs": 1,
1983
+ "save_steps": 10,
1984
+ "stateful_callbacks": {
1985
+ "TrainerControl": {
1986
+ "args": {
1987
+ "should_epoch_stop": false,
1988
+ "should_evaluate": false,
1989
+ "should_log": false,
1990
+ "should_save": true,
1991
+ "should_training_stop": true
1992
+ },
1993
+ "attributes": {}
1994
+ }
1995
+ },
1996
+ "total_flos": 0.0,
1997
+ "train_batch_size": 1,
1998
+ "trial_name": null,
1999
+ "trial_params": null
2000
+ }