Hugging Face's logo

LEAP-LAB-KUS
/
jevkt-checkpoints

PEFT
Safetensors
knowledge-tracing
system-one
typed-decisions
lora
calibration
Model card Files
xet
 Community
Unggi commited on
Commit
50b689a
·
verified ·
1 Parent(s): 0e75087

backup e16/S2-grpo (Pod B)

Browse files
Files changed (19) hide show
  1. e16/S2-grpo/ckpt-16000/adapter/README.md +206 -0
  2. e16/S2-grpo/ckpt-16000/adapter/adapter_config.json +57 -0
  3. e16/S2-grpo/ckpt-16000/adapter/adapter_model.safetensors +3 -0
  4. e16/S2-grpo/ckpt-16000/adapter_vllm/adapter_config.json +58 -0
  5. e16/S2-grpo/ckpt-16000/adapter_vllm/adapter_model.safetensors +3 -0
  6. e16/S2-grpo/ckpt-16000/adapter_vllm/decision_head.json +99 -0
  7. e16/S2-grpo/ckpt-16000/calibration.json +17 -0
  8. e16/S2-grpo/ckpt-16000/head.safetensors +3 -0
  9. e16/S2-grpo/ckpt-16000/judge_config.json +160 -0
  10. e16/S2-grpo/ckpt-4000/adapter/README.md +206 -0
  11. e16/S2-grpo/ckpt-4000/adapter/adapter_config.json +57 -0
  12. e16/S2-grpo/ckpt-4000/adapter/adapter_model.safetensors +3 -0
  13. e16/S2-grpo/ckpt-4000/adapter_vllm/adapter_config.json +58 -0
  14. e16/S2-grpo/ckpt-4000/adapter_vllm/adapter_model.safetensors +3 -0
  15. e16/S2-grpo/ckpt-4000/adapter_vllm/decision_head.json +99 -0
  16. e16/S2-grpo/ckpt-4000/calibration.json +17 -0
  17. e16/S2-grpo/ckpt-4000/head.safetensors +3 -0
  18. e16/S2-grpo/ckpt-4000/judge_config.json +160 -0
  19. e16/S2-grpo/train_log.jsonl +58 -0
e16/S2-grpo/ckpt-16000/adapter/README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /workspace/jev_kt/models/hf/JEV-9B
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:/workspace/jev_kt/models/hf/JEV-9B
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.21.2
e16/S2-grpo/ckpt-16000/adapter/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen3_5ForCausalLM",
7
+ "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
8
+ },
9
+ "base_model_name_or_path": "/workspace/jev_kt/models/hf/JEV-9B",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "kasa_config": null,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.05,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.21.0",
33
+ "qalora_group_size": 16,
34
+ "r": 16,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": [
38
+ "q_proj",
39
+ "o_proj",
40
+ "up_proj",
41
+ "in_proj_z",
42
+ "k_proj",
43
+ "out_proj",
44
+ "gate_proj",
45
+ "v_proj",
46
+ "in_proj_qkv",
47
+ "down_proj"
48
+ ],
49
+ "target_parameters": null,
50
+ "task_type": null,
51
+ "trainable_token_indices": null,
52
+ "use_bdlora": null,
53
+ "use_dora": false,
54
+ "use_qalora": false,
55
+ "use_rslora": false,
56
+ "velora_config": null
57
+ }
e16/S2-grpo/ckpt-16000/adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd449c6fd299561a723c627753341c0f9de02849a4ab9a738e8dc5a8f8ee9fd4
3
+ size 160486456
e16/S2-grpo/ckpt-16000/adapter_vllm/adapter_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen3_5ForCausalLM",
7
+ "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
8
+ },
9
+ "base_model_name_or_path": null,
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "kasa_config": null,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 64.0,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.21.0",
33
+ "qalora_group_size": 16,
34
+ "r": 32,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": [
38
+ "down_proj",
39
+ "gate_proj",
40
+ "in_proj_qkv",
41
+ "in_proj_z",
42
+ "k_proj",
43
+ "lm_head",
44
+ "o_proj",
45
+ "out_proj",
46
+ "q_proj",
47
+ "up_proj",
48
+ "v_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": null,
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false,
57
+ "velora_config": null
58
+ }
e16/S2-grpo/ckpt-16000/adapter_vllm/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d0e3aca135691c7727ab9d833fcb2cda57c76dfd416a737e3c16ed2c373caad
3
+ size 176641832
e16/S2-grpo/ckpt-16000/adapter_vllm/decision_head.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bias": [
3
+ 0.0011923718266189098,
4
+ 0.0019085280364379287,
5
+ -0.0025878134183585644,
6
+ -0.0012615364976227283,
7
+ -0.00025007399381138384,
8
+ 0.0019558551721274853,
9
+ 0.0013559526996687055,
10
+ -0.0023348911199718714,
11
+ -0.0004082925443071872,
12
+ -0.0002078723773593083,
13
+ -1.2957353646925185e-05,
14
+ 0.0001676026004133746,
15
+ 0.0005569425993598998,
16
+ -0.001412136247381568,
17
+ -0.0028663526754826307,
18
+ -0.005061559844762087,
19
+ -0.00593328895047307,
20
+ -0.004319756291806698,
21
+ -0.004922541789710522,
22
+ -0.0049067651852965355,
23
+ -0.003943523392081261,
24
+ -0.003319827374070883,
25
+ -0.005581587553024292,
26
+ -0.0034480984322726727
27
+ ],
28
+ "verbalizer_ids": [
29
+ 3721,
30
+ 1802,
31
+ 15,
32
+ 16,
33
+ 17,
34
+ 18,
35
+ 19,
36
+ 20,
37
+ 32,
38
+ 33,
39
+ 34,
40
+ 35,
41
+ 36,
42
+ 37,
43
+ 38,
44
+ 39,
45
+ 40,
46
+ 41,
47
+ 42,
48
+ 43,
49
+ 44,
50
+ 45,
51
+ 46,
52
+ 47
53
+ ],
54
+ "slots": {
55
+ "num_slots": 24,
56
+ "ranges": {
57
+ "noul": [
58
+ 0,
59
+ 2
60
+ ],
61
+ "score": [
62
+ 2,
63
+ 8
64
+ ],
65
+ "choice": [
66
+ 8,
67
+ 24
68
+ ]
69
+ },
70
+ "verbalizers": [
71
+ "false",
72
+ "true",
73
+ "0",
74
+ "1",
75
+ "2",
76
+ "3",
77
+ "4",
78
+ "5",
79
+ "A",
80
+ "B",
81
+ "C",
82
+ "D",
83
+ "E",
84
+ "F",
85
+ "G",
86
+ "H",
87
+ "I",
88
+ "J",
89
+ "K",
90
+ "L",
91
+ "M",
92
+ "N",
93
+ "O",
94
+ "P"
95
+ ],
96
+ "template_version": "bare-v1"
97
+ },
98
+ "note": "decision logits = lm_head-LoRA logprobs of verbalizer ids + bias, then per-kind temperature"
99
+ }
e16/S2-grpo/ckpt-16000/calibration.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "per_kind": {
4
+ "noul": 3.999999975766852,
5
+ "choice": 1.0,
6
+ "score": 1.0
7
+ },
8
+ "fit": {
9
+ "noul": {
10
+ "n": 2000,
11
+ "T": 3.999999975766852,
12
+ "ce_before": 1.2534629106521606,
13
+ "ce_after": 0.5559723973274231
14
+ }
15
+ },
16
+ "source": "models/e16/S2-grpo/ckpt-16000"
17
+ }
e16/S2-grpo/ckpt-16000/head.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f361466bf2fe79c496465e950ca6b0e83f032eeebc266de35bde0827daa2e26
3
+ size 393464
e16/S2-grpo/ckpt-16000/judge_config.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_path": "/root/models/Qwen3.5-9B",
3
+ "hidden_size": 4096,
4
+ "slots": {
5
+ "num_slots": 24,
6
+ "ranges": {
7
+ "noul": [
8
+ 0,
9
+ 2
10
+ ],
11
+ "score": [
12
+ 2,
13
+ 8
14
+ ],
15
+ "choice": [
16
+ 8,
17
+ 24
18
+ ]
19
+ },
20
+ "verbalizers": [
21
+ "false",
22
+ "true",
23
+ "0",
24
+ "1",
25
+ "2",
26
+ "3",
27
+ "4",
28
+ "5",
29
+ "A",
30
+ "B",
31
+ "C",
32
+ "D",
33
+ "E",
34
+ "F",
35
+ "G",
36
+ "H",
37
+ "I",
38
+ "J",
39
+ "K",
40
+ "L",
41
+ "M",
42
+ "N",
43
+ "O",
44
+ "P"
45
+ ],
46
+ "template_version": "bare-v1"
47
+ },
48
+ "verbalizer_ids": [
49
+ 3721,
50
+ 1802,
51
+ 15,
52
+ 16,
53
+ 17,
54
+ 18,
55
+ 19,
56
+ 20,
57
+ 32,
58
+ 33,
59
+ 34,
60
+ 35,
61
+ 36,
62
+ 37,
63
+ 38,
64
+ 39,
65
+ 40,
66
+ 41,
67
+ 42,
68
+ 43,
69
+ 44,
70
+ 45,
71
+ 46,
72
+ 47
73
+ ],
74
+ "kinds": [
75
+ "noul",
76
+ "choice",
77
+ "score"
78
+ ],
79
+ "model_name": "jev-judge-qwen35-9b",
80
+ "model_version": "0.8.0",
81
+ "lm_head_included": true,
82
+ "weights_mode": "unmerged",
83
+ "adapter_subfolder": "adapter",
84
+ "lora": {
85
+ "r": 16,
86
+ "lora_alpha": 32,
87
+ "lora_dropout": 0.05,
88
+ "target_modules": [
89
+ "down_proj",
90
+ "gate_proj",
91
+ "in_proj_qkv",
92
+ "in_proj_z",
93
+ "k_proj",
94
+ "o_proj",
95
+ "out_proj",
96
+ "q_proj",
97
+ "up_proj",
98
+ "v_proj"
99
+ ]
100
+ },
101
+ "trained_stage": "e16",
102
+ "source_checkpoint": "models/e16/S2-grpo/ckpt-16000",
103
+ "softcap": null,
104
+ "e16": {
105
+ "data": "data/e15/F1-pool",
106
+ "data_manifest": {
107
+ "arm": "F1-pool",
108
+ "name": "F1-pool",
109
+ "train_sha256": "dad16f94a5659768b254a6c12538c01f9c64cd43d574a3435bcc70c9c1bac130",
110
+ "n_train": 64000
111
+ },
112
+ "init": "released",
113
+ "objective": "grpo",
114
+ "sigma": 0.5,
115
+ "K": 8,
116
+ "reward": "brier",
117
+ "clip": 0.2,
118
+ "passes": 1,
119
+ "lr": 0.0001,
120
+ "lr_head": 0.0002,
121
+ "rows_per_step": 32,
122
+ "train_seed": 0,
123
+ "replay": null,
124
+ "replay_frac": 0.0,
125
+ "replay_sha256": null,
126
+ "max_len": 3072,
127
+ "schedule": "warmup 0.03 + cosine to x0.05 over 500 steps",
128
+ "total_rows": 16000,
129
+ "lora": {
130
+ "r": 16,
131
+ "lora_alpha": 32,
132
+ "lora_dropout": 0.05
133
+ },
134
+ "trainer_sha256": "bc7c08e836bd99bb2665b02903cd41404ea029ecfa9b68a9ec1a7cda96958ba4",
135
+ "event": "ckpt",
136
+ "tag": "ckpt-16000",
137
+ "rows_seen": 16000,
138
+ "replay_seen": 0,
139
+ "step": 500,
140
+ "tokens": 10544036,
141
+ "tok_per_s": 801.4457102658002,
142
+ "rows_per_s": 1.2161501875255025,
143
+ "val": {
144
+ "n": 2000,
145
+ "dropped_long": 0,
146
+ "noul_ce": 1.2534629106521606,
147
+ "noul_T": 3.999999975766852,
148
+ "noul_auc": 0.7711860716714061,
149
+ "noul_acc": 0.7325,
150
+ "noul_f1": 0.8025101513473607,
151
+ "noul_nll": 1.2534631492147454,
152
+ "noul_ece": 0.2311101165637374,
153
+ "noul_brier": 0.24887562559128235,
154
+ "noul_sharp": 0.47496092319488525,
155
+ "entropy": 0.07330752909183502
156
+ },
157
+ "dropped_long": 0,
158
+ "peak_gib": 18.236032962799072
159
+ }
160
+ }
e16/S2-grpo/ckpt-4000/adapter/README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /workspace/jev_kt/models/hf/JEV-9B
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:/workspace/jev_kt/models/hf/JEV-9B
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.21.2
e16/S2-grpo/ckpt-4000/adapter/adapter_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen3_5ForCausalLM",
7
+ "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
8
+ },
9
+ "base_model_name_or_path": "/workspace/jev_kt/models/hf/JEV-9B",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "kasa_config": null,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.05,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.21.0",
33
+ "qalora_group_size": 16,
34
+ "r": 16,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": [
38
+ "q_proj",
39
+ "o_proj",
40
+ "up_proj",
41
+ "in_proj_z",
42
+ "k_proj",
43
+ "out_proj",
44
+ "gate_proj",
45
+ "v_proj",
46
+ "in_proj_qkv",
47
+ "down_proj"
48
+ ],
49
+ "target_parameters": null,
50
+ "task_type": null,
51
+ "trainable_token_indices": null,
52
+ "use_bdlora": null,
53
+ "use_dora": false,
54
+ "use_qalora": false,
55
+ "use_rslora": false,
56
+ "velora_config": null
57
+ }
e16/S2-grpo/ckpt-4000/adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe7582344ad1de45522a138d4da0b78220fbc18211e45b015e3e88623e9d2e2e
3
+ size 160486456
e16/S2-grpo/ckpt-4000/adapter_vllm/adapter_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen3_5ForCausalLM",
7
+ "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
8
+ },
9
+ "base_model_name_or_path": null,
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "kasa_config": null,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 64.0,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.21.0",
33
+ "qalora_group_size": 16,
34
+ "r": 32,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": [
38
+ "down_proj",
39
+ "gate_proj",
40
+ "in_proj_qkv",
41
+ "in_proj_z",
42
+ "k_proj",
43
+ "lm_head",
44
+ "o_proj",
45
+ "out_proj",
46
+ "q_proj",
47
+ "up_proj",
48
+ "v_proj"
49
+ ],
50
+ "target_parameters": null,
51
+ "task_type": null,
52
+ "trainable_token_indices": null,
53
+ "use_bdlora": null,
54
+ "use_dora": false,
55
+ "use_qalora": false,
56
+ "use_rslora": false,
57
+ "velora_config": null
58
+ }
e16/S2-grpo/ckpt-4000/adapter_vllm/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42ce81ed202216a8c58bb21c2f1fa5405d8846483d94621d4ea3b4509d2c9fa6
3
+ size 176641832
e16/S2-grpo/ckpt-4000/adapter_vllm/decision_head.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bias": [
3
+ 0.0009142130147665739,
4
+ 0.001469273236580193,
5
+ -0.0025878134183585644,
6
+ -0.0012615364976227283,
7
+ -0.00025007399381138384,
8
+ 0.0019558551721274853,
9
+ 0.0013559526996687055,
10
+ -0.0023348911199718714,
11
+ -0.0004082925443071872,
12
+ -0.0002078723773593083,
13
+ -1.2957353646925185e-05,
14
+ 0.0001676026004133746,
15
+ 0.0005569425993598998,
16
+ -0.001412136247381568,
17
+ -0.0028663526754826307,
18
+ -0.005061559844762087,
19
+ -0.00593328895047307,
20
+ -0.004319756291806698,
21
+ -0.004922541789710522,
22
+ -0.0049067651852965355,
23
+ -0.003943523392081261,
24
+ -0.003319827374070883,
25
+ -0.005581587553024292,
26
+ -0.0034480984322726727
27
+ ],
28
+ "verbalizer_ids": [
29
+ 3721,
30
+ 1802,
31
+ 15,
32
+ 16,
33
+ 17,
34
+ 18,
35
+ 19,
36
+ 20,
37
+ 32,
38
+ 33,
39
+ 34,
40
+ 35,
41
+ 36,
42
+ 37,
43
+ 38,
44
+ 39,
45
+ 40,
46
+ 41,
47
+ 42,
48
+ 43,
49
+ 44,
50
+ 45,
51
+ 46,
52
+ 47
53
+ ],
54
+ "slots": {
55
+ "num_slots": 24,
56
+ "ranges": {
57
+ "noul": [
58
+ 0,
59
+ 2
60
+ ],
61
+ "score": [
62
+ 2,
63
+ 8
64
+ ],
65
+ "choice": [
66
+ 8,
67
+ 24
68
+ ]
69
+ },
70
+ "verbalizers": [
71
+ "false",
72
+ "true",
73
+ "0",
74
+ "1",
75
+ "2",
76
+ "3",
77
+ "4",
78
+ "5",
79
+ "A",
80
+ "B",
81
+ "C",
82
+ "D",
83
+ "E",
84
+ "F",
85
+ "G",
86
+ "H",
87
+ "I",
88
+ "J",
89
+ "K",
90
+ "L",
91
+ "M",
92
+ "N",
93
+ "O",
94
+ "P"
95
+ ],
96
+ "template_version": "bare-v1"
97
+ },
98
+ "note": "decision logits = lm_head-LoRA logprobs of verbalizer ids + bias, then per-kind temperature"
99
+ }
e16/S2-grpo/ckpt-4000/calibration.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "per_kind": {
4
+ "noul": 3.9999998673929205,
5
+ "choice": 1.0,
6
+ "score": 1.0
7
+ },
8
+ "fit": {
9
+ "noul": {
10
+ "n": 2000,
11
+ "T": 3.9999998673929205,
12
+ "ce_before": 1.399613380432129,
13
+ "ce_after": 0.5718698501586914
14
+ }
15
+ },
16
+ "source": "models/e16/S2-grpo/ckpt-4000"
17
+ }
e16/S2-grpo/ckpt-4000/head.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936fd54b2900281dca6570c062e9f13bdc17fa9deea95f3c3c4ed26c2a917ff3
3
+ size 393464
e16/S2-grpo/ckpt-4000/judge_config.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_path": "/root/models/Qwen3.5-9B",
3
+ "hidden_size": 4096,
4
+ "slots": {
5
+ "num_slots": 24,
6
+ "ranges": {
7
+ "noul": [
8
+ 0,
9
+ 2
10
+ ],
11
+ "score": [
12
+ 2,
13
+ 8
14
+ ],
15
+ "choice": [
16
+ 8,
17
+ 24
18
+ ]
19
+ },
20
+ "verbalizers": [
21
+ "false",
22
+ "true",
23
+ "0",
24
+ "1",
25
+ "2",
26
+ "3",
27
+ "4",
28
+ "5",
29
+ "A",
30
+ "B",
31
+ "C",
32
+ "D",
33
+ "E",
34
+ "F",
35
+ "G",
36
+ "H",
37
+ "I",
38
+ "J",
39
+ "K",
40
+ "L",
41
+ "M",
42
+ "N",
43
+ "O",
44
+ "P"
45
+ ],
46
+ "template_version": "bare-v1"
47
+ },
48
+ "verbalizer_ids": [
49
+ 3721,
50
+ 1802,
51
+ 15,
52
+ 16,
53
+ 17,
54
+ 18,
55
+ 19,
56
+ 20,
57
+ 32,
58
+ 33,
59
+ 34,
60
+ 35,
61
+ 36,
62
+ 37,
63
+ 38,
64
+ 39,
65
+ 40,
66
+ 41,
67
+ 42,
68
+ 43,
69
+ 44,
70
+ 45,
71
+ 46,
72
+ 47
73
+ ],
74
+ "kinds": [
75
+ "noul",
76
+ "choice",
77
+ "score"
78
+ ],
79
+ "model_name": "jev-judge-qwen35-9b",
80
+ "model_version": "0.8.0",
81
+ "lm_head_included": true,
82
+ "weights_mode": "unmerged",
83
+ "adapter_subfolder": "adapter",
84
+ "lora": {
85
+ "r": 16,
86
+ "lora_alpha": 32,
87
+ "lora_dropout": 0.05,
88
+ "target_modules": [
89
+ "down_proj",
90
+ "gate_proj",
91
+ "in_proj_qkv",
92
+ "in_proj_z",
93
+ "k_proj",
94
+ "o_proj",
95
+ "out_proj",
96
+ "q_proj",
97
+ "up_proj",
98
+ "v_proj"
99
+ ]
100
+ },
101
+ "trained_stage": "e16",
102
+ "source_checkpoint": "models/e16/S2-grpo/ckpt-4000",
103
+ "softcap": null,
104
+ "e16": {
105
+ "data": "data/e15/F1-pool",
106
+ "data_manifest": {
107
+ "arm": "F1-pool",
108
+ "name": "F1-pool",
109
+ "train_sha256": "dad16f94a5659768b254a6c12538c01f9c64cd43d574a3435bcc70c9c1bac130",
110
+ "n_train": 64000
111
+ },
112
+ "init": "released",
113
+ "objective": "grpo",
114
+ "sigma": 0.5,
115
+ "K": 8,
116
+ "reward": "brier",
117
+ "clip": 0.2,
118
+ "passes": 1,
119
+ "lr": 0.0001,
120
+ "lr_head": 0.0002,
121
+ "rows_per_step": 32,
122
+ "train_seed": 0,
123
+ "replay": null,
124
+ "replay_frac": 0.0,
125
+ "replay_sha256": null,
126
+ "max_len": 3072,
127
+ "schedule": "warmup 0.03 + cosine to x0.05 over 500 steps",
128
+ "total_rows": 16000,
129
+ "lora": {
130
+ "r": 16,
131
+ "lora_alpha": 32,
132
+ "lora_dropout": 0.05
133
+ },
134
+ "trainer_sha256": "bc7c08e836bd99bb2665b02903cd41404ea029ecfa9b68a9ec1a7cda96958ba4",
135
+ "event": "ckpt",
136
+ "tag": "ckpt-4000",
137
+ "rows_seen": 4000,
138
+ "replay_seen": 0,
139
+ "step": 125,
140
+ "tokens": 2631181,
141
+ "tok_per_s": 756.4806477399412,
142
+ "rows_per_s": 1.150024489218687,
143
+ "val": {
144
+ "n": 2000,
145
+ "dropped_long": 0,
146
+ "noul_ce": 1.399613380432129,
147
+ "noul_T": 3.9999998673929205,
148
+ "noul_auc": 0.7699651992751803,
149
+ "noul_acc": 0.735,
150
+ "noul_f1": 0.822028206850235,
151
+ "noul_nll": 1.3996135839489872,
152
+ "noul_ece": 0.23450430658389818,
153
+ "noul_brier": 0.2597876962428795,
154
+ "noul_sharp": 0.49290764331817627,
155
+ "entropy": 0.033249858766794205
156
+ },
157
+ "dropped_long": 0,
158
+ "peak_gib": 18.23348903656006
159
+ }
160
+ }
e16/S2-grpo/train_log.jsonl ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time": "15:24:54", "event": "start", "data": "data/e15/F1-pool", "data_manifest": {"arm": "F1-pool", "name": "F1-pool", "train_sha256": "dad16f94a5659768b254a6c12538c01f9c64cd43d574a3435bcc70c9c1bac130", "n_train": 64000}, "init": "released", "objective": "grpo", "sigma": 0.5, "K": 8, "reward": "brier", "clip": 0.2, "passes": 1, "lr": 0.0001, "lr_head": 0.0002, "rows_per_step": 32, "train_seed": 0, "replay": null, "replay_frac": 0.0, "replay_sha256": null, "max_len": 3072, "schedule": "warmup 0.03 + cosine to x0.05 over 500 steps", "total_rows": 16000, "lora": {"r": 16, "lora_alpha": 32, "lora_dropout": 0.05}, "trainer_sha256": "bc7c08e836bd99bb2665b02903cd41404ea029ecfa9b68a9ec1a7cda96958ba4", "device": "cuda", "load_s": 99.16184043884277}
2
+ {"time": "15:28:54", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 880.5599762725326, "loss": -2.1602903871098533e-05, "entropy": 0.17954703024588525, "sharp": 0.4280797280371189, "r_mean": 0.4932403912146886, "r_std": 0.07639228762066826, "adv_abs": 0.4227892855803172, "frac_lowstd": 0.5571428686380386}
3
+ {"time": "15:32:56", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 885.1126155012205, "loss": -1.8029415514320135e-05, "entropy": 0.15207510348409414, "sharp": 0.4450413640588522, "r_mean": 0.45163627341389656, "r_std": 0.06255301240889821, "adv_abs": 0.5292791128158569, "frac_lowstd": 0.4785714362348829}
4
+ {"time": "15:36:54", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 883.9224289595453, "loss": -6.558561290148646e-05, "entropy": 0.022264694096520543, "sharp": 0.4964387472718954, "r_mean": 0.536490872502327, "r_std": 0.0027449813325282385, "adv_abs": 0.320110773401601, "frac_lowstd": 0.7190476315362113}
5
+ {"time": "15:40:56", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 885.6987989442212, "loss": -4.6015797124709934e-05, "entropy": 0.0159460384020349, "sharp": 0.49763374775648117, "r_mean": 0.1982834497134068, "r_std": 0.002493456991422655, "adv_abs": 0.3838029908282416, "frac_lowstd": 0.5972789185387748}
6
+ {"time": "15:44:53", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 887.1883959721638, "loss": -3.341851697769016e-05, "entropy": 0.04712672640744131, "sharp": 0.4856144730001688, "r_mean": 0.2974011796925749, "r_std": 0.011281551332721003, "adv_abs": 0.4078288567917688, "frac_lowstd": 0.6316326643739428}
7
+ {"time": "15:48:51", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 887.4540678236641, "loss": -2.1793312043882906e-06, "entropy": 0.06611943594180048, "sharp": 0.4845804516226053, "r_mean": 0.5632238776556083, "r_std": 0.005683614232111722, "adv_abs": 0.4900165796279907, "frac_lowstd": 0.6673469458307538}
8
+ {"time": "15:52:47", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 886.7102807006875, "loss": -2.1714484319090843e-05, "entropy": 0.06125492780120112, "sharp": 0.4811213295906782, "r_mean": 0.43375802545675207, "r_std": 0.02329143105037344, "adv_abs": 0.4298074522188732, "frac_lowstd": 0.6340136123555047}
9
+ {"time": "15:56:44", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 887.5037282951871, "loss": -1.6039830370573327e-06, "entropy": 0.05153768828313332, "sharp": 0.4803267624229193, "r_mean": 0.6195520673479352, "r_std": 0.02083593368498831, "adv_abs": 0.25460885731237276, "frac_lowstd": 0.767346944127764}
10
+ {"time": "16:00:43", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 887.0215973535417, "loss": 4.938716301694512e-06, "entropy": 0.03992753347847611, "sharp": 0.4926407113671303, "r_mean": 0.6422836759260723, "r_std": 0.0061087812264304375, "adv_abs": 0.3960026704839298, "frac_lowstd": 0.7107142891202655}
11
+ {"time": "16:04:40", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 887.543413197256, "loss": 1.801641337806359e-05, "entropy": 0.055555723258294165, "sharp": 0.4792850110679865, "r_mean": 0.5438898381377969, "r_std": 0.015091959049511518, "adv_abs": 0.3439763230936868, "frac_lowstd": 0.6425170132092067}
12
+ {"time": "16:06:25", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 1.3246959447860718, "noul_T": 3.9999967807251866, "noul_auc": 0.7712899269450222, "noul_acc": 0.74, "noul_f1": 0.821917808219178, "noul_nll": 1.3246960213478887, "noul_ece": 0.23161752957850693, "noul_brier": 0.2410960253191141, "noul_sharp": 0.4781842827796936, "entropy": 0.05787966400384903}
13
+ {"time": "16:10:23", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 854.5815442943873, "loss": 2.2748528863303363e-05, "entropy": 0.06137893290724605, "sharp": 0.47893231362104416, "r_mean": 0.5822181964426169, "r_std": 0.009184003399825866, "adv_abs": 0.39429474834884914, "frac_lowstd": 0.7492063535111291}
14
+ {"time": "16:14:11", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 857.1336791943443, "loss": 1.08750828076154e-05, "entropy": 0.049872154064360075, "sharp": 0.4808507412672043, "r_mean": 0.3489990990076746, "r_std": 0.018111463079971406, "adv_abs": 0.37259638256260325, "frac_lowstd": 0.6071428677865437}
15
+ {"time": "16:22:54", "event": "ckpt", "tag": "ckpt-4000", "rows_seen": 4000, "replay_seen": 0, "step": 125, "tokens": 2631181, "tok_per_s": 756.4806477399412, "rows_per_s": 1.150024489218687, "val": {"n": 2000, "dropped_long": 0, "noul_ce": 1.399613380432129, "noul_T": 3.9999998673929205, "noul_auc": 0.7699651992751803, "noul_acc": 0.735, "noul_f1": 0.822028206850235, "noul_nll": 1.3996135839489872, "noul_ece": 0.23450430658389818, "noul_brier": 0.2597876962428795, "noul_sharp": 0.49290764331817627, "entropy": 0.033249858766794205}, "dropped_long": 0, "peak_gib": 18.23348903656006}
16
+ {"time": "16:24:54", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 760.9768082995668, "loss": 1.1585361789911985e-06, "entropy": 0.039943965850397944, "sharp": 0.49309252575039864, "r_mean": 0.5804076178797654, "r_std": 0.006846234989227794, "adv_abs": 0.48080380473818096, "frac_lowstd": 0.765986408506121}
17
+ {"time": "16:28:51", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 768.6833122093764, "loss": 9.57622251007706e-06, "entropy": 0.05569167766952887, "sharp": 0.4830008130520582, "r_mean": 0.5736915767192841, "r_std": 0.010747411503741335, "adv_abs": 0.3248362871153014, "frac_lowstd": 0.7226190567016602}
18
+ {"time": "16:32:49", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 775.904372063157, "loss": -4.3206211557844654e-05, "entropy": 0.0723518543964019, "sharp": 0.4809146970510483, "r_mean": 0.7011737312589373, "r_std": 0.012437618747201538, "adv_abs": 0.39551409067852156, "frac_lowstd": 0.5904761978558132}
19
+ {"time": "16:36:48", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 782.6024831389017, "loss": 2.9404509405139834e-05, "entropy": 0.05263749184086919, "sharp": 0.48551630042493343, "r_mean": 0.4321810280283292, "r_std": 0.014013914973475039, "adv_abs": 0.43710334102312726, "frac_lowstd": 0.6375000129143397}
20
+ {"time": "16:40:47", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 788.1171757297309, "loss": 1.6745350876590237e-05, "entropy": 0.04043652296240907, "sharp": 0.4919905811548233, "r_mean": 0.648976308958871, "r_std": 0.01322172230558343, "adv_abs": 0.28130216524004936, "frac_lowstd": 0.7282312980719975}
21
+ {"time": "16:44:35", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 793.1539797430057, "loss": -4.255562089383602e-06, "entropy": 0.1670025633648038, "sharp": 0.4533815048635006, "r_mean": 0.5175616374860207, "r_std": 0.03697421595764657, "adv_abs": 0.6612813870112101, "frac_lowstd": 0.33650794128576916}
22
+ {"time": "16:48:28", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 798.0645956801397, "loss": -1.0286084943800233e-05, "entropy": 0.0771065273147542, "sharp": 0.47715260088443756, "r_mean": 0.4147901577608926, "r_std": 0.03454553452268426, "adv_abs": 0.4011195972561836, "frac_lowstd": 0.5500000076634544}
23
+ {"time": "16:52:35", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 802.2258410146269, "loss": 3.079816815443337e-05, "entropy": 0.07629824813921005, "sharp": 0.48070562444627285, "r_mean": 0.5705961734056473, "r_std": 0.029844648469796602, "adv_abs": 0.4150735799755369, "frac_lowstd": 0.6506802780287606}
24
+ {"time": "16:54:19", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 1.190072774887085, "noul_T": 3.9999974935768465, "noul_auc": 0.7655486233313782, "noul_acc": 0.74, "noul_f1": 0.8121387283236994, "noul_nll": 1.1900727936534676, "noul_ece": 0.23655395176634195, "noul_brier": 0.24333977409494495, "noul_sharp": 0.47907018661499023, "entropy": 0.0728389248251915}
25
+ {"time": "16:58:17", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 791.0634253415183, "loss": 1.896614776342176e-07, "entropy": 0.07087115742615424, "sharp": 0.4719528891146183, "r_mean": 0.31330824749810354, "r_std": 0.02910847691600793, "adv_abs": 0.39482200677905765, "frac_lowstd": 0.6250000042574746}
26
+ {"time": "17:02:07", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 795.1133295616611, "loss": 3.459088475210592e-06, "entropy": 0.03182779182679951, "sharp": 0.4938550814986229, "r_mean": 0.5416245510180792, "r_std": 0.011134934859910572, "adv_abs": 0.3255190836886565, "frac_lowstd": 0.7453703830639521}
27
+ {"time": "17:06:04", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 799.2961418382588, "loss": -1.2125266948714852e-05, "entropy": 0.025844433723250404, "sharp": 0.49581719376146793, "r_mean": 0.22483581810125283, "r_std": 0.00712468715833633, "adv_abs": 0.4416103724922453, "frac_lowstd": 0.5877551095826286}
28
+ {"time": "17:09:51", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 802.8439444144769, "loss": -4.615139914676547e-06, "entropy": 0.07238097340450622, "sharp": 0.48119354993104935, "r_mean": 0.4847051464021206, "r_std": 0.018754740379595854, "adv_abs": 0.41333211958408356, "frac_lowstd": 0.6340136187417167}
29
+ {"time": "17:13:47", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 806.042499193646, "loss": -3.2798525353427976e-05, "entropy": 0.05929261667188257, "sharp": 0.4845128171145916, "r_mean": 0.7879819018500192, "r_std": 0.01360927120510626, "adv_abs": 0.24402707016893796, "frac_lowstd": 0.7988095283508301}
30
+ {"time": "17:17:35", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 808.964700217502, "loss": -2.42550449911505e-05, "entropy": 0.07299397862516344, "sharp": 0.4767618402838707, "r_mean": 0.6156176416469472, "r_std": 0.016564707169891335, "adv_abs": 0.5191141537257603, "frac_lowstd": 0.6380952511514936}
31
+ {"time": "17:21:31", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 811.673261694746, "loss": 3.279043630755041e-05, "entropy": 0.05348705709911883, "sharp": 0.4846506826579571, "r_mean": 0.6403960287570953, "r_std": 0.01371961337281391, "adv_abs": 0.3971443126598994, "frac_lowstd": 0.7563492258389791}
32
+ {"time": "17:25:27", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 814.4680990909707, "loss": 4.0424245526082814e-05, "entropy": 0.05082430399488658, "sharp": 0.48734417371451855, "r_mean": 0.3237729673939092, "r_std": 0.019946893922419155, "adv_abs": 0.40073312393256594, "frac_lowstd": 0.6244898055280957}
33
+ {"time": "17:29:27", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 817.1160457179567, "loss": 4.3615285903797485e-05, "entropy": 0.09372308565070853, "sharp": 0.46199851855635643, "r_mean": 0.7434181294270924, "r_std": 0.041173511713428264, "adv_abs": 0.3145948105624744, "frac_lowstd": 0.6673469543457031}
34
+ {"time": "17:33:21", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 819.3081385473265, "loss": -3.7265705032041296e-05, "entropy": 0.08547615341376513, "sharp": 0.4731642995029688, "r_mean": 0.6116756323192801, "r_std": 0.014203807053036144, "adv_abs": 0.4128896934645517, "frac_lowstd": 0.6244898097855704}
35
+ {"time": "17:35:06", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 1.2130420207977295, "noul_T": 3.999999389801139, "noul_auc": 0.7634778435450327, "noul_acc": 0.748, "noul_f1": 0.8210227272727273, "noul_nll": 1.2130420056421427, "noul_ece": 0.22305091735860333, "noul_brier": 0.23862539107401595, "noul_sharp": 0.4775664806365967, "entropy": 0.07222945243120193}
36
+ {"time": "17:39:08", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 810.8121120428872, "loss": -1.8560385797172785e-05, "entropy": 0.09856282809050754, "sharp": 0.4674478992819786, "r_mean": 0.2029345700783389, "r_std": 0.09255526786936182, "adv_abs": 0.5156243443489075, "frac_lowstd": 0.4387755181108202}
37
+ {"time": "17:43:03", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 813.154398761464, "loss": -2.761186897259904e-05, "entropy": 0.08205707703018561, "sharp": 0.4692401085048914, "r_mean": 0.671226326908384, "r_std": 0.02707774315370313, "adv_abs": 0.3790753356048039, "frac_lowstd": 0.6850340323788779}
38
+ {"time": "17:46:57", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 815.2633053356752, "loss": -1.6104782844195142e-05, "entropy": 0.12470954889431596, "sharp": 0.4588946271687746, "r_mean": 0.24305319661895433, "r_std": 0.04318998117620746, "adv_abs": 0.5485504567623138, "frac_lowstd": 0.33789682885011035}
39
+ {"time": "17:50:58", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 817.5512903963272, "loss": 8.579008863307536e-06, "entropy": 0.08768337732180953, "sharp": 0.47437295131385326, "r_mean": 0.3601582241909845, "r_std": 0.04040779273782391, "adv_abs": 0.4690316319465637, "frac_lowstd": 0.6142857266323907}
40
+ {"time": "17:54:54", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 819.6391258495277, "loss": 3.825245858024573e-05, "entropy": 0.08115656103473157, "sharp": 0.47294664569199085, "r_mean": 0.5205034676473588, "r_std": 0.02021044810510375, "adv_abs": 0.3170366206904873, "frac_lowstd": 0.6389881055802107}
41
+ {"time": "17:58:46", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 821.4948366608735, "loss": -5.45298771612579e-05, "entropy": 0.05199561861809343, "sharp": 0.4869217090308666, "r_mean": 0.7629188299179077, "r_std": 0.00966548374240769, "adv_abs": 0.3318754753896168, "frac_lowstd": 0.8345238140651158}
42
+ {"time": "18:02:38", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 823.4501892666466, "loss": -2.4070151994237676e-05, "entropy": 0.04840043222066015, "sharp": 0.4880789536982775, "r_mean": 0.6204094865492412, "r_std": 0.009955628109829766, "adv_abs": 0.4268896622317178, "frac_lowstd": 0.7591836878231594}
43
+ {"time": "18:06:34", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 825.2285638997962, "loss": -1.0919105989160016e-05, "entropy": 0.059535356354899704, "sharp": 0.479431277140975, "r_mean": 0.44135468027421404, "r_std": 0.017992469026450766, "adv_abs": 0.37705701629498173, "frac_lowstd": 0.6802721193858555}
44
+ {"time": "18:10:29", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 826.9121076744069, "loss": -6.0027123254258186e-06, "entropy": 0.04785946774063632, "sharp": 0.4886986128985882, "r_mean": 0.7434959965092796, "r_std": 0.009193275505172746, "adv_abs": 0.28499765587704523, "frac_lowstd": 0.7809523854936872}
45
+ {"time": "18:14:25", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 828.4138915122695, "loss": 2.7647363822325133e-05, "entropy": 0.05180231046688277, "sharp": 0.48227465711534023, "r_mean": 0.8742884397506714, "r_std": 0.011267128127371961, "adv_abs": 0.21720907324925065, "frac_lowstd": 0.8364583402872086}
46
+ {"time": "18:16:10", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 1.3036595582962036, "noul_T": 3.9999979526559337, "noul_auc": 0.7659574468085107, "noul_acc": 0.738, "noul_f1": 0.8087591240875912, "noul_nll": 1.3036600294368108, "noul_ece": 0.2328607510225848, "noul_brier": 0.2455846856435424, "noul_sharp": 0.4779588580131531, "entropy": 0.06396006047725677}
47
+ {"time": "18:20:11", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 821.5894744296438, "loss": -3.1236090762831736e-05, "entropy": 0.026258574449457228, "sharp": 0.49509422108531, "r_mean": 0.5624358964463075, "r_std": 0.006536100480540578, "adv_abs": 0.27142785986264545, "frac_lowstd": 0.7484127183755239}
48
+ {"time": "18:24:06", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 823.3147186408559, "loss": 2.5352339434903115e-05, "entropy": 0.09377965098246932, "sharp": 0.4692817311733961, "r_mean": 0.3726150707474777, "r_std": 0.042536486023371775, "adv_abs": 0.42088076046534945, "frac_lowstd": 0.5479591872010913}
49
+ {"time": "18:28:07", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 824.754393283413, "loss": -1.4475393982138485e-05, "entropy": 0.04403313936199993, "sharp": 0.49013304710388184, "r_mean": 0.15155341156891414, "r_std": 0.024024356630564268, "adv_abs": 0.5124919797692981, "frac_lowstd": 0.45714286821229116}
50
+ {"time": "18:31:57", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 826.2372884605462, "loss": -8.466506187687628e-06, "entropy": 0.0709599363617599, "sharp": 0.4747455231845379, "r_mean": 0.5824030886093775, "r_std": 0.023646748768442194, "adv_abs": 0.3403257926305135, "frac_lowstd": 0.7063492288192114}
51
+ {"time": "18:35:56", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 827.595094621429, "loss": -1.6146848793141544e-05, "entropy": 0.041178965533617884, "sharp": 0.49187013134360313, "r_mean": 0.5654972919395992, "r_std": 0.015872996041707665, "adv_abs": 0.3655240908265114, "frac_lowstd": 0.7071428660835538}
52
+ {"time": "18:39:51", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 828.9625534356655, "loss": -3.172290598740801e-05, "entropy": 0.030840684776194394, "sharp": 0.49334643594920635, "r_mean": 0.424633123512779, "r_std": 0.011087944477042453, "adv_abs": 0.3108556770852634, "frac_lowstd": 0.6602040912423816}
53
+ {"time": "18:43:51", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 830.3830425451758, "loss": 1.9191918909200467e-05, "entropy": 0.1086652792582754, "sharp": 0.45950234681367874, "r_mean": 0.5872775380100522, "r_std": 0.0397040487778213, "adv_abs": 0.39873469301632475, "frac_lowstd": 0.6530612409114838}
54
+ {"time": "18:47:44", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 831.5061575237388, "loss": -1.5772537153679878e-05, "entropy": 0.06150114198680967, "sharp": 0.47981075197458267, "r_mean": 0.5115832614246756, "r_std": 0.020491423771394086, "adv_abs": 0.3575795404613018, "frac_lowstd": 0.6763888945182165}
55
+ {"time": "18:51:39", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 832.8581788189437, "loss": -5.596179107669741e-06, "entropy": 0.08114325813949108, "sharp": 0.4668322429060936, "r_mean": 0.5734975854200977, "r_std": 0.023319742874524048, "adv_abs": 0.35571443076644627, "frac_lowstd": 0.6938775607517788}
56
+ {"time": "18:55:36", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 834.02418048871, "loss": 4.566251300275326e-05, "entropy": 0.09839034173637629, "sharp": 0.46735306829214096, "r_mean": 0.7180471867322922, "r_std": 0.04190077539533377, "adv_abs": 0.3476768334706624, "frac_lowstd": 0.6896825631459554}
57
+ {"time": "18:57:21", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 1.2733814716339111, "noul_T": 3.999999975766852, "noul_auc": 0.7676638404521944, "noul_acc": 0.736, "noul_f1": 0.8023952095808383, "noul_nll": 1.2733821992945158, "noul_ece": 0.24372001121006906, "noul_brier": 0.2518450354880547, "noul_sharp": 0.4781883656978607, "entropy": 0.06955970823764801}
58
+ {"time": "19:04:12", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 0, "step": 500, "tokens": 10544036, "tok_per_s": 801.4457102658002, "rows_per_s": 1.2161501875255025, "val": {"n": 2000, "dropped_long": 0, "noul_ce": 1.2534629106521606, "noul_T": 3.999999975766852, "noul_auc": 0.7711860716714061, "noul_acc": 0.7325, "noul_f1": 0.8025101513473607, "noul_nll": 1.2534631492147454, "noul_ece": 0.2311101165637374, "noul_brier": 0.24887562559128235, "noul_sharp": 0.47496092319488525, "entropy": 0.07330752909183502}, "dropped_long": 0, "peak_gib": 18.236032962799072}