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
45a3d9b
·
verified ·
1 Parent(s): e6b444c

backup e16/S2-ppo4 (Pod B)

Browse files
Files changed (21) hide show
  1. e16/S2-ppo4/ckpt-16000/adapter/README.md +206 -0
  2. e16/S2-ppo4/ckpt-16000/adapter/adapter_config.json +57 -0
  3. e16/S2-ppo4/ckpt-16000/adapter/adapter_model.safetensors +3 -0
  4. e16/S2-ppo4/ckpt-16000/adapter_vllm/adapter_config.json +58 -0
  5. e16/S2-ppo4/ckpt-16000/adapter_vllm/adapter_model.safetensors +3 -0
  6. e16/S2-ppo4/ckpt-16000/adapter_vllm/decision_head.json +99 -0
  7. e16/S2-ppo4/ckpt-16000/calibration.json +17 -0
  8. e16/S2-ppo4/ckpt-16000/head.safetensors +3 -0
  9. e16/S2-ppo4/ckpt-16000/judge_config.json +160 -0
  10. e16/S2-ppo4/ckpt-16000/value_head.safetensors +3 -0
  11. e16/S2-ppo4/ckpt-4000/adapter/README.md +206 -0
  12. e16/S2-ppo4/ckpt-4000/adapter/adapter_config.json +57 -0
  13. e16/S2-ppo4/ckpt-4000/adapter/adapter_model.safetensors +3 -0
  14. e16/S2-ppo4/ckpt-4000/adapter_vllm/adapter_config.json +58 -0
  15. e16/S2-ppo4/ckpt-4000/adapter_vllm/adapter_model.safetensors +3 -0
  16. e16/S2-ppo4/ckpt-4000/adapter_vllm/decision_head.json +99 -0
  17. e16/S2-ppo4/ckpt-4000/calibration.json +17 -0
  18. e16/S2-ppo4/ckpt-4000/head.safetensors +3 -0
  19. e16/S2-ppo4/ckpt-4000/judge_config.json +160 -0
  20. e16/S2-ppo4/ckpt-4000/value_head.safetensors +3 -0
  21. e16/S2-ppo4/train_log.jsonl +58 -0
e16/S2-ppo4/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-ppo4/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
+ "up_proj",
39
+ "k_proj",
40
+ "in_proj_z",
41
+ "out_proj",
42
+ "gate_proj",
43
+ "in_proj_qkv",
44
+ "o_proj",
45
+ "down_proj",
46
+ "v_proj",
47
+ "q_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-ppo4/ckpt-16000/adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06acdecd6636e7527c5de08f98e5411b12f228b33a6773e91ec2e31d8006b0a3
3
+ size 160486456
e16/S2-ppo4/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-ppo4/ckpt-16000/adapter_vllm/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc02f1ed9bc58bc77e65e78ee66cddaba43533c94dd978eb1b3840d9b85ac45f
3
+ size 176641832
e16/S2-ppo4/ckpt-16000/adapter_vllm/decision_head.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bias": [
3
+ 0.0002581758890300989,
4
+ 0.00035731674870476127,
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-ppo4/ckpt-16000/calibration.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "per_kind": {
4
+ "noul": 1.2953209251532816,
5
+ "choice": 1.0,
6
+ "score": 1.0
7
+ },
8
+ "fit": {
9
+ "noul": {
10
+ "n": 2000,
11
+ "T": 1.2953209251532816,
12
+ "ce_before": 0.5472821593284607,
13
+ "ce_after": 0.5383816957473755
14
+ }
15
+ },
16
+ "source": "models/e16/S2-ppo4/ckpt-16000"
17
+ }
e16/S2-ppo4/ckpt-16000/head.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc5fed7d1fff253bbeddec587e747f5c44208e298d2a915acc13f65c66c8d941
3
+ size 393464
e16/S2-ppo4/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-ppo4/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": "ppo",
114
+ "sigma": 0.5,
115
+ "K": 8,
116
+ "reward": "brier",
117
+ "clip": 0.2,
118
+ "passes": 4,
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": 223.63027065198688,
142
+ "rows_per_s": 0.33934674826570954,
143
+ "val": {
144
+ "n": 2000,
145
+ "dropped_long": 0,
146
+ "noul_ce": 0.5472821593284607,
147
+ "noul_T": 1.2953209251532816,
148
+ "noul_auc": 0.770643461717528,
149
+ "noul_acc": 0.727,
150
+ "noul_f1": 0.7927107061503417,
151
+ "noul_nll": 0.547282186601311,
152
+ "noul_ece": 0.07019711908698081,
153
+ "noul_brier": 0.18281499320956085,
154
+ "noul_sharp": 0.28277942538261414,
155
+ "entropy": 0.4731370508670807
156
+ },
157
+ "dropped_long": 0,
158
+ "peak_gib": 18.23610210418701
159
+ }
160
+ }
e16/S2-ppo4/ckpt-16000/value_head.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d37854e9e5e035edc57b560e4629de574cd50eb7e59ec2b3d0ffb30b3996434
3
+ size 16524
e16/S2-ppo4/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-ppo4/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
+ "up_proj",
39
+ "k_proj",
40
+ "in_proj_z",
41
+ "out_proj",
42
+ "gate_proj",
43
+ "in_proj_qkv",
44
+ "o_proj",
45
+ "down_proj",
46
+ "v_proj",
47
+ "q_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-ppo4/ckpt-4000/adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab3478dfbc943b5781b26442397a70d2c58d652ccacf0b7f0f67ca820b9cbb5
3
+ size 160486456
e16/S2-ppo4/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-ppo4/ckpt-4000/adapter_vllm/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba8e727a13d7604be17fa5c818e54df598b5f7d3d4cbd2d2dc1e2a6bd66f22de
3
+ size 176641832
e16/S2-ppo4/ckpt-4000/adapter_vllm/decision_head.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bias": [
3
+ 0.0003766273148357868,
4
+ 0.00011558916594367474,
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-ppo4/ckpt-4000/calibration.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "per_kind": {
4
+ "noul": 1.3528392844642585,
5
+ "choice": 1.0,
6
+ "score": 1.0
7
+ },
8
+ "fit": {
9
+ "noul": {
10
+ "n": 2000,
11
+ "T": 1.3528392844642585,
12
+ "ce_before": 0.555921196937561,
13
+ "ce_after": 0.5424610376358032
14
+ }
15
+ },
16
+ "source": "models/e16/S2-ppo4/ckpt-4000"
17
+ }
e16/S2-ppo4/ckpt-4000/head.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:299860e98ffa78869729bc5e4d4317871b8990f4b504f32579cbb7c54726e7a3
3
+ size 393464
e16/S2-ppo4/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-ppo4/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": "ppo",
114
+ "sigma": 0.5,
115
+ "K": 8,
116
+ "reward": "brier",
117
+ "clip": 0.2,
118
+ "passes": 4,
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": 219.82480366306137,
142
+ "rows_per_s": 0.3341842367151173,
143
+ "val": {
144
+ "n": 2000,
145
+ "dropped_long": 0,
146
+ "noul_ce": 0.555921196937561,
147
+ "noul_T": 1.3528392844642585,
148
+ "noul_auc": 0.7661546483027808,
149
+ "noul_acc": 0.735,
150
+ "noul_f1": 0.8144257703081232,
151
+ "noul_nll": 0.5559212014190853,
152
+ "noul_ece": 0.07694640575349332,
153
+ "noul_brier": 0.18584675931802327,
154
+ "noul_sharp": 0.3085011839866638,
155
+ "entropy": 0.4579586386680603
156
+ },
157
+ "dropped_long": 0,
158
+ "peak_gib": 18.233563899993896
159
+ }
160
+ }
e16/S2-ppo4/ckpt-4000/value_head.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e0ee53be893a2e0006ee7ddb7af6739190bf70e57c396df86c762a59cfa682c
3
+ size 16524
e16/S2-ppo4/train_log.jsonl ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time": "17:29:07", "event": "start", "data": "data/e15/F1-pool", "data_manifest": {"arm": "F1-pool", "name": "F1-pool", "train_sha256": "dad16f94a5659768b254a6c12538c01f9c64cd43d574a3435bcc70c9c1bac130", "n_train": 64000}, "init": "released", "objective": "ppo", "sigma": 0.5, "K": 8, "reward": "brier", "clip": 0.2, "passes": 4, "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": 79.5163369178772}
2
+ {"time": "17:44:46", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 225.11199059329164, "loss": 0.06535853445529938, "entropy": 0.449349582195282, "sharp": 0.30453435331583023, "r_mean": 0.6299777179956436, "r_std": 0.15533316632111868, "adv_abs": 0.3983115553855896, "frac_lowstd": 0.033333333830038704}
3
+ {"time": "18:00:22", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 227.3923079050491, "loss": 0.039139955304563046, "entropy": 0.45015501976013184, "sharp": 0.3014124035835266, "r_mean": 0.5899364735398974, "r_std": 0.16194531960146769, "adv_abs": 0.43123763373919893, "frac_lowstd": 0.0}
4
+ {"time": "18:15:42", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 227.50484531682793, "loss": 0.38560111698461697, "entropy": 0.3731286972761154, "sharp": 0.35009969770908356, "r_mean": 0.5233380262340818, "r_std": 0.1382820068725518, "adv_abs": 0.4346477133887155, "frac_lowstd": 0.0}
5
+ {"time": "18:31:16", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 228.4347759027119, "loss": 0.22992060612887144, "entropy": 0.40658188611268997, "sharp": 0.3338388428092003, "r_mean": 0.3195145917790277, "r_std": 0.14872234740427562, "adv_abs": 0.6215505855424064, "frac_lowstd": 0.0}
6
+ {"time": "18:46:37", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 228.82489271660293, "loss": 0.17759945010766387, "entropy": 0.4929338460788131, "sharp": 0.2683673296123743, "r_mean": 0.5365624810968127, "r_std": 0.17068862994866713, "adv_abs": 0.41000063717365265, "frac_lowstd": 0.0}
7
+ {"time": "19:02:00", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 228.90691606863163, "loss": -0.06148801860399544, "entropy": 0.48536211252212524, "sharp": 0.2708188947290182, "r_mean": 0.5996127639498029, "r_std": 0.134284035967929, "adv_abs": 0.41649054629462107, "frac_lowstd": 0.0}
8
+ {"time": "19:17:09", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 228.82405814858882, "loss": 0.15942902059759945, "entropy": 0.3700484905857593, "sharp": 0.3544373717159033, "r_mean": 0.5911425309521812, "r_std": 0.12620808343802178, "adv_abs": 0.44541572353669573, "frac_lowstd": 0.0}
9
+ {"time": "19:32:29", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 229.0077203905566, "loss": -0.021279165637679398, "entropy": 0.42388426698744297, "sharp": 0.29050580598413944, "r_mean": 0.7178291593279157, "r_std": 0.13173930932368552, "adv_abs": 0.2706436216831207, "frac_lowstd": 0.0}
10
+ {"time": "19:47:55", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 228.91796808609078, "loss": 0.17394201585557312, "entropy": 0.4754671771079302, "sharp": 0.27319373562932014, "r_mean": 0.6450750040156501, "r_std": 0.1532583742269448, "adv_abs": 0.32518890712942394, "frac_lowstd": 0.0}
11
+ {"time": "20:03:11", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 229.08321689119853, "loss": 0.18873027508379892, "entropy": 0.4304962530732155, "sharp": 0.29486941173672676, "r_mean": 0.6323341823049954, "r_std": 0.14741378383977072, "adv_abs": 0.281963763492448, "frac_lowstd": 0.0}
12
+ {"time": "20:04:53", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.589661717414856, "noul_T": 1.6356503384087844, "noul_auc": 0.7501022058692832, "noul_acc": 0.718, "noul_f1": 0.7886056971514243, "noul_nll": 0.5896617078110575, "noul_ece": 0.10279168200492861, "noul_brier": 0.19508821432647444, "noul_sharp": 0.30131471157073975, "entropy": 0.4308304786682129}
13
+ {"time": "20:20:15", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 227.11794168622797, "loss": 0.21594017720781267, "entropy": 0.4489279817789793, "sharp": 0.2779719214886427, "r_mean": 0.613895622747285, "r_std": 0.13824512343853712, "adv_abs": 0.3715951272419521, "frac_lowstd": 0.0}
14
+ {"time": "20:34:58", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 227.31187470825907, "loss": 0.19302046264056116, "entropy": 0.4674037043005228, "sharp": 0.2916873786598444, "r_mean": 0.5417350344359875, "r_std": 0.146726894857628, "adv_abs": 0.4532313879047121, "frac_lowstd": 0.0}
15
+ {"time": "20:48:38", "event": "ckpt", "tag": "ckpt-4000", "rows_seen": 4000, "replay_seen": 0, "step": 125, "tokens": 2631181, "tok_per_s": 219.82480366306137, "rows_per_s": 0.3341842367151173, "val": {"n": 2000, "dropped_long": 0, "noul_ce": 0.555921196937561, "noul_T": 1.3528392844642585, "noul_auc": 0.7661546483027808, "noul_acc": 0.735, "noul_f1": 0.8144257703081232, "noul_nll": 0.5559212014190853, "noul_ece": 0.07694640575349332, "noul_brier": 0.18584675931802327, "noul_sharp": 0.3085011839866638, "entropy": 0.4579586386680603}, "dropped_long": 0, "peak_gib": 18.233563899993896}
16
+ {"time": "20:56:21", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 220.2954058498303, "loss": 0.08337040315382183, "entropy": 0.5067588621750474, "sharp": 0.26661745086312294, "r_mean": 0.6215336216347558, "r_std": 0.17105663647609098, "adv_abs": 0.3377623749630792, "frac_lowstd": 0.0}
17
+ {"time": "21:11:39", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 220.89931190954508, "loss": 0.2408637383050518, "entropy": 0.4188347738236189, "sharp": 0.31999554857611656, "r_mean": 0.5921943954059056, "r_std": 0.13249748423030333, "adv_abs": 0.36788213572331835, "frac_lowstd": 0.0}
18
+ {"time": "21:27:02", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 221.4916305891741, "loss": -0.11784577940125018, "entropy": 0.4503553444519639, "sharp": 0.2855610027909279, "r_mean": 0.7388140303747994, "r_std": 0.1409844654346151, "adv_abs": 0.3270989315850394, "frac_lowstd": 0.0}
19
+ {"time": "21:42:29", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 222.0883724595999, "loss": -0.10310685576405376, "entropy": 0.43443626910448074, "sharp": 0.3117653355002403, "r_mean": 0.6598150680462519, "r_std": 0.1784596269329389, "adv_abs": 0.38644807537396747, "frac_lowstd": 0.027777778605620067}
20
+ {"time": "21:57:52", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 222.52041181410573, "loss": -0.0010863845818676054, "entropy": 0.4252767083235085, "sharp": 0.310781205072999, "r_mean": 0.7076548848833356, "r_std": 0.11837184402559485, "adv_abs": 0.3405528025967734, "frac_lowstd": 0.0}
21
+ {"time": "22:12:37", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 222.9203279375572, "loss": 0.03169035993050784, "entropy": 0.47102541849017143, "sharp": 0.27498924918472767, "r_mean": 0.66158327460289, "r_std": 0.134760652979215, "adv_abs": 0.30523285269737244, "frac_lowstd": 0.0}
22
+ {"time": "22:27:40", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 223.38377367645876, "loss": 0.16879162256373093, "entropy": 0.4415250141173601, "sharp": 0.29361570440232754, "r_mean": 0.6046035800661359, "r_std": 0.14599873657737458, "adv_abs": 0.3463944579873766, "frac_lowstd": 0.028571428997176036}
23
+ {"time": "22:43:32", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 223.71158890018302, "loss": 0.24291066313162446, "entropy": 0.4554558089002967, "sharp": 0.2617504019290209, "r_mean": 0.5735107617718833, "r_std": 0.16147915380341665, "adv_abs": 0.4215015641280583, "frac_lowstd": 0.11700680639062609}
24
+ {"time": "22:45:13", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.558680534362793, "noul_T": 1.5708200302292021, "noul_auc": 0.7738850672781242, "noul_acc": 0.742, "noul_f1": 0.8195804195804196, "noul_nll": 0.5586805587112904, "noul_ece": 0.08768709516525268, "noul_brier": 0.18428975662613203, "noul_sharp": 0.2903660237789154, "entropy": 0.43402794003486633}
25
+ {"time": "23:00:35", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 222.87078883275638, "loss": 0.13415538368280977, "entropy": 0.4086040360853076, "sharp": 0.3210318274796009, "r_mean": 0.4925294263022287, "r_std": 0.14431308768689632, "adv_abs": 0.49345276185444426, "frac_lowstd": 0.0}
26
+ {"time": "23:15:22", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 223.22372846020994, "loss": 0.27098718605702743, "entropy": 0.3687797822058201, "sharp": 0.3378716167062521, "r_mean": 0.6529691567023596, "r_std": 0.1302606211975217, "adv_abs": 0.31708350280920666, "frac_lowstd": 0.079629631092151}
27
+ {"time": "23:30:45", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 223.59235392619905, "loss": 0.03564804990310222, "entropy": 0.3927034083753824, "sharp": 0.3243628293275833, "r_mean": 0.4467085770198277, "r_std": 0.17935143943343843, "adv_abs": 0.5277072829859597, "frac_lowstd": 0.14285714498588017}
28
+ {"time": "23:45:28", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 223.86612039865875, "loss": -0.12874532211571932, "entropy": 0.43782298918813467, "sharp": 0.27987813018262386, "r_mean": 0.6665886768272945, "r_std": 0.17483147446598327, "adv_abs": 0.39653316140174866, "frac_lowstd": 0.21360544860363007}
29
+ {"time": "00:00:45", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 224.0967491706488, "loss": -0.0028470716206356883, "entropy": 0.3855725056491792, "sharp": 0.3158331662416458, "r_mean": 0.8186272382736206, "r_std": 0.09551783511415124, "adv_abs": 0.18526955481086457, "frac_lowstd": 0.023809524519102915}
30
+ {"time": "00:15:30", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 224.31198630503266, "loss": 0.04125273402314633, "entropy": 0.36828607390634716, "sharp": 0.3347015716135502, "r_mean": 0.6621414577322347, "r_std": 0.11245295528455504, "adv_abs": 0.40598405471869875, "frac_lowstd": 0.0}
31
+ {"time": "00:30:47", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 224.46483160934076, "loss": 0.10372213018126786, "entropy": 0.38720618933439255, "sharp": 0.318428099155426, "r_mean": 0.5834969480832418, "r_std": 0.11274138217171033, "adv_abs": 0.4225843970974286, "frac_lowstd": 0.0}
32
+ {"time": "00:46:02", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 224.71641509399566, "loss": 0.08387894579209387, "entropy": 0.28523391182534397, "sharp": 0.3842022530734539, "r_mean": 0.48399815814835684, "r_std": 0.08700957801192999, "adv_abs": 0.5615820203508649, "frac_lowstd": 0.028571428997176036}
33
+ {"time": "01:01:32", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 224.9416719240615, "loss": -0.14832813362590969, "entropy": 0.29794058529660106, "sharp": 0.35915934294462204, "r_mean": 0.7603923720972878, "r_std": 0.09363974211737514, "adv_abs": 0.42874028853007723, "frac_lowstd": 0.1476190494639533}
34
+ {"time": "01:16:44", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 225.06153477087014, "loss": 0.131603765883483, "entropy": 0.33327560080215335, "sharp": 0.36375777423381805, "r_mean": 0.5714495629072189, "r_std": 0.08993966252143894, "adv_abs": 0.5211205525057656, "frac_lowstd": 0.0}
35
+ {"time": "01:18:25", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.6739518046379089, "noul_T": 2.263586637537502, "noul_auc": 0.7491423594447111, "noul_acc": 0.744, "noul_f1": 0.8100890207715133, "noul_nll": 0.6739517694562673, "noul_ece": 0.14502023485302926, "noul_brier": 0.2020462973387851, "noul_sharp": 0.3812732994556427, "entropy": 0.2997937798500061}
36
+ {"time": "01:34:10", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 224.3947284653839, "loss": 0.1169803369557485, "entropy": 0.3682461157441139, "sharp": 0.3365198504179716, "r_mean": 0.5125314492200103, "r_std": 0.17210995086601802, "adv_abs": 0.5385478436946869, "frac_lowstd": 0.023809524519102915}
37
+ {"time": "01:49:21", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 224.56470346470385, "loss": -0.2158594410866499, "entropy": 0.3795975772663951, "sharp": 0.3240540996193886, "r_mean": 0.7501427062920162, "r_std": 0.10221169356788908, "adv_abs": 0.47126532026699613, "frac_lowstd": 0.0}
38
+ {"time": "02:04:33", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 224.68784032964487, "loss": 0.27050922135822475, "entropy": 0.45984791219234467, "sharp": 0.25361233577132225, "r_mean": 0.4085637979830305, "r_std": 0.1971543754140536, "adv_abs": 0.48178956906000775, "frac_lowstd": 0.0}
39
+ {"time": "02:20:08", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 224.8699074148447, "loss": 0.23846320156008005, "entropy": 0.40900190616957843, "sharp": 0.3108659293502569, "r_mean": 0.5129253225667136, "r_std": 0.1400241340244455, "adv_abs": 0.4725651868752071, "frac_lowstd": 0.023809524519102915}
40
+ {"time": "02:35:29", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 225.03489015757842, "loss": 0.182478231145069, "entropy": 0.4010110991075635, "sharp": 0.3178358804434538, "r_mean": 0.638191182166338, "r_std": 0.12471302668564022, "adv_abs": 0.3730744756758213, "frac_lowstd": 0.0}
41
+ {"time": "02:50:30", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 225.15357684628648, "loss": -0.12390111363492906, "entropy": 0.47085915319621563, "sharp": 0.28660829551517963, "r_mean": 0.7675796917506627, "r_std": 0.14412586124879972, "adv_abs": 0.32321420311927795, "frac_lowstd": 0.0}
42
+ {"time": "03:05:35", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 225.3106333399186, "loss": 0.10388290567789227, "entropy": 0.4250987209379673, "sharp": 0.32737585343420506, "r_mean": 0.6217228301933834, "r_std": 0.09906348958611488, "adv_abs": 0.4313078948429653, "frac_lowstd": 0.0}
43
+ {"time": "03:20:49", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 225.4591518781343, "loss": -0.01963916444219649, "entropy": 0.4962599463760853, "sharp": 0.26773427054286003, "r_mean": 0.6561646716935294, "r_std": 0.15687129313924483, "adv_abs": 0.3388702230794089, "frac_lowstd": 0.0}
44
+ {"time": "03:36:02", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 225.59185001105953, "loss": 0.010901044821366668, "entropy": 0.4146195175126195, "sharp": 0.31088668666779995, "r_mean": 0.7562298348971775, "r_std": 0.10745048150420189, "adv_abs": 0.2968634707587106, "frac_lowstd": 0.0}
45
+ {"time": "03:51:24", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 225.67950627177098, "loss": -0.07340640347683802, "entropy": 0.45740482583642006, "sharp": 0.2876929435878992, "r_mean": 0.7990668341517448, "r_std": 0.11795479553984478, "adv_abs": 0.24762078188359737, "frac_lowstd": 0.0}
46
+ {"time": "03:53:05", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5430698990821838, "noul_T": 1.290968479219666, "noul_auc": 0.7728718960521872, "noul_acc": 0.748, "noul_f1": 0.8225352112676056, "noul_nll": 0.5430698912665248, "noul_ece": 0.07003546953201295, "noul_brier": 0.18063548376059982, "noul_sharp": 0.28351256251335144, "entropy": 0.4701160490512848}
47
+ {"time": "04:08:39", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 225.17035350016616, "loss": -0.09734993940219283, "entropy": 0.43148707784712315, "sharp": 0.3164347857236862, "r_mean": 0.777671088774999, "r_std": 0.12812661503752074, "adv_abs": 0.24334975332021713, "frac_lowstd": 0.0}
48
+ {"time": "04:23:55", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 225.3227589402587, "loss": 0.007306596904527396, "entropy": 0.49354909360408783, "sharp": 0.26461372151970863, "r_mean": 0.579751271222319, "r_std": 0.18098335713148117, "adv_abs": 0.37740881528173176, "frac_lowstd": 0.0}
49
+ {"time": "04:39:32", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 225.39516780788946, "loss": 0.157030442613177, "entropy": 0.42760763317346573, "sharp": 0.31659630313515663, "r_mean": 0.5106124260595867, "r_std": 0.21838918434722082, "adv_abs": 0.4021593907049724, "frac_lowstd": 0.0}
50
+ {"time": "04:54:31", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 225.49183213067786, "loss": -0.03281613625586033, "entropy": 0.38355443999171257, "sharp": 0.33896592259407043, "r_mean": 0.7359624058008194, "r_std": 0.10662197570006053, "adv_abs": 0.3109716276327769, "frac_lowstd": 0.0}
51
+ {"time": "05:10:00", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 225.56619611831977, "loss": -0.07136643584817648, "entropy": 0.4453885890543461, "sharp": 0.2974743898957968, "r_mean": 0.6889185117823737, "r_std": 0.13354252238890954, "adv_abs": 0.3630311574254717, "frac_lowstd": 0.0}
52
+ {"time": "05:25:14", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 225.66835021432325, "loss": 0.26051825867034495, "entropy": 0.3696577064692974, "sharp": 0.3537525739520788, "r_mean": 0.5106517516874841, "r_std": 0.11906880173566085, "adv_abs": 0.4913572839328221, "frac_lowstd": 0.0}
53
+ {"time": "05:40:49", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 225.77237744702393, "loss": -0.028851363735157065, "entropy": 0.49310085037723184, "sharp": 0.2499922215938568, "r_mean": 0.6976074320929391, "r_std": 0.15548785642853805, "adv_abs": 0.23208342066832952, "frac_lowstd": 0.0}
54
+ {"time": "05:55:59", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 225.82231911168742, "loss": 0.033234670059755445, "entropy": 0.45038881711661816, "sharp": 0.3013238161802292, "r_mean": 0.650485930343469, "r_std": 0.14918992761522532, "adv_abs": 0.3554127862056096, "frac_lowstd": 0.0}
55
+ {"time": "06:11:15", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 225.9425212191678, "loss": 0.06106817559339106, "entropy": 0.4573683347553015, "sharp": 0.2909969724714756, "r_mean": 0.6234750194208962, "r_std": 0.13774608128837176, "adv_abs": 0.4047883983169283, "frac_lowstd": 0.0}
56
+ {"time": "06:26:38", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 226.0213287172706, "loss": -0.04653845727443695, "entropy": 0.4437675178050995, "sharp": 0.3003118857741356, "r_mean": 0.7205192546049753, "r_std": 0.15184261401494345, "adv_abs": 0.28735137234131497, "frac_lowstd": 0.0}
57
+ {"time": "06:28:19", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5483077168464661, "noul_T": 1.2915776362580458, "noul_auc": 0.7740272667484314, "noul_acc": 0.726, "noul_f1": 0.7908396946564885, "noul_nll": 0.5483076895475387, "noul_ece": 0.07837464743852615, "noul_brier": 0.18310062183532394, "noul_sharp": 0.2816276252269745, "entropy": 0.4761306047439575}
58
+ {"time": "06:34:58", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 0, "step": 500, "tokens": 10544036, "tok_per_s": 223.63027065198688, "rows_per_s": 0.33934674826570954, "val": {"n": 2000, "dropped_long": 0, "noul_ce": 0.5472821593284607, "noul_T": 1.2953209251532816, "noul_auc": 0.770643461717528, "noul_acc": 0.727, "noul_f1": 0.7927107061503417, "noul_nll": 0.547282186601311, "noul_ece": 0.07019711908698081, "noul_brier": 0.18281499320956085, "noul_sharp": 0.28277942538261414, "entropy": 0.4731370508670807}, "dropped_long": 0, "peak_gib": 18.23610210418701}