Unggi commited on
Commit
f52249e
·
verified ·
1 Parent(s): a0c90b4

backup e16/S1-SS-hlr-n16k-syn (Pod B)

Browse files
e16/S1-SS-hlr-n16k-syn/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/S1-SS-hlr-n16k-syn/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
+ "down_proj",
39
+ "up_proj",
40
+ "q_proj",
41
+ "out_proj",
42
+ "in_proj_z",
43
+ "o_proj",
44
+ "v_proj",
45
+ "gate_proj",
46
+ "in_proj_qkv",
47
+ "k_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/S1-SS-hlr-n16k-syn/ckpt-16000/adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d21215eaac6c2c031c28f7f38ddc6057837257afa5ee9a913c658bb102b502a
3
+ size 160486456
e16/S1-SS-hlr-n16k-syn/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/S1-SS-hlr-n16k-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718f42d3ce6ea9048195a79e7b3bf640ac8643940f61f46b4c8befa74a8ac6ed
3
+ size 176641832
e16/S1-SS-hlr-n16k-syn/ckpt-16000/adapter_vllm/decision_head.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bias": [
3
+ 0.0004003714711870998,
4
+ -0.00040063413325697184,
5
+ -0.0023977782111614943,
6
+ -0.0015707695856690407,
7
+ -0.00043568204273469746,
8
+ 0.002126764738932252,
9
+ 0.0014182031154632568,
10
+ -0.002619077917188406,
11
+ -0.0006855888641439378,
12
+ -0.0005341079668141901,
13
+ -0.00030957936542108655,
14
+ 0.00034006338682956994,
15
+ -0.00029873676248826087,
16
+ -0.0037704920396208763,
17
+ -0.0045829517766833305,
18
+ -0.005388528108596802,
19
+ -0.005830902606248856,
20
+ -0.004458731040358543,
21
+ -0.004960083402693272,
22
+ -0.005081012845039368,
23
+ -0.004104054532945156,
24
+ -0.003483549691736698,
25
+ -0.005650845821946859,
26
+ -0.0035311561077833176
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/S1-SS-hlr-n16k-syn/ckpt-16000/calibration.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "per_kind": {
4
+ "noul": 0.8435191174895403,
5
+ "choice": 1.0507546040503266,
6
+ "score": 0.995887067643377
7
+ },
8
+ "fit": {
9
+ "noul": {
10
+ "n": 1087,
11
+ "T": 0.8435191174895403,
12
+ "ce_before": 0.5604627132415771,
13
+ "ce_after": 0.5581470727920532
14
+ },
15
+ "choice": {
16
+ "n": 60,
17
+ "T": 1.0507546040503266,
18
+ "ce_before": 0.6713417768478394,
19
+ "ce_after": 0.6708076596260071
20
+ },
21
+ "score": {
22
+ "n": 53,
23
+ "T": 0.995887067643377,
24
+ "ce_before": 1.063907265663147,
25
+ "ce_after": 1.0639015436172485
26
+ }
27
+ },
28
+ "source": "models/e16/S1-SS-hlr-n16k-syn/ckpt-16000"
29
+ }
e16/S1-SS-hlr-n16k-syn/ckpt-16000/head.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd33e3d2daf02b66d384e8e466df5c958809ae66459d94a2abe2656304c7faf
3
+ size 393464
e16/S1-SS-hlr-n16k-syn/ckpt-16000/judge_config.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/S1-SS-hlr-n16k-syn/ckpt-16000",
103
+ "softcap": null,
104
+ "e16": {
105
+ "data": "data/e18/SS-hlr-n16k",
106
+ "data_manifest": {
107
+ "arm": "SS-hlr-n16k",
108
+ "name": null,
109
+ "train_sha256": "f7366875817c3627e5d24c64a8ae81765bd6dfc81fa729b5c4cd87c77f6f2823",
110
+ "n_train": 16000
111
+ },
112
+ "init": "released",
113
+ "objective": "s-log",
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": "data/e16/replay/train.jsonl",
124
+ "replay_frac": 0.05,
125
+ "replay_sha256": "9dd2df19851678750cf79d2fdb47581720930ef2f0c6e18e6fbe23ef2181847e",
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": 842,
139
+ "step": 500,
140
+ "tokens": 8732071,
141
+ "tok_per_s": 788.6198733006973,
142
+ "rows_per_s": 1.5210522108815354,
143
+ "val": {
144
+ "n": 1200,
145
+ "dropped_long": 0,
146
+ "noul_ce": 0.5604627132415771,
147
+ "noul_T": 0.8435191174895403,
148
+ "choice_ce": 0.6713417768478394,
149
+ "choice_T": 1.0507546040503266,
150
+ "score_ce": 1.063907265663147,
151
+ "score_T": 0.995887067643377,
152
+ "noul_auc": 0.7387050666666667,
153
+ "noul_acc": 0.689,
154
+ "noul_f1": 0.7645722937168812,
155
+ "noul_nll": 0.5747933953106403,
156
+ "noul_ece": 0.05640242668986321,
157
+ "noul_brier": 0.196318222722157,
158
+ "noul_sharp": 0.17765387892723083,
159
+ "entropy": 0.5968260765075684
160
+ },
161
+ "dropped_long": 0,
162
+ "peak_gib": 18.236003875732422
163
+ }
164
+ }
e16/S1-SS-hlr-n16k-syn/train_log.jsonl ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time": "08:33:27", "event": "start", "data": "data/e18/SS-hlr-n16k", "data_manifest": {"arm": "SS-hlr-n16k", "name": null, "train_sha256": "f7366875817c3627e5d24c64a8ae81765bd6dfc81fa729b5c4cd87c77f6f2823", "n_train": 16000}, "init": "released", "objective": "s-log", "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": "data/e16/replay/train.jsonl", "replay_frac": 0.05, "replay_sha256": "9dd2df19851678750cf79d2fdb47581720930ef2f0c6e18e6fbe23ef2181847e", "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": 86.32591581344604}
2
+ {"time": "08:37:01", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 827.400691489781, "loss": 0.6076363250613213, "entropy": 0.6345702446997166, "sharp": 0.14524811878800392}
3
+ {"time": "08:40:26", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 831.4292489152335, "loss": 0.577735859900713, "entropy": 0.576833937317133, "sharp": 0.19781471975147724}
4
+ {"time": "08:43:56", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 832.3036552880284, "loss": 0.6420671371743083, "entropy": 0.6370985368266702, "sharp": 0.11918610334396362}
5
+ {"time": "08:47:25", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 833.519177798232, "loss": 0.5874182600528002, "entropy": 0.605562124401331, "sharp": 0.15751689486205578}
6
+ {"time": "08:50:57", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 835.3554502664573, "loss": 0.5852723084390163, "entropy": 0.5690760277211666, "sharp": 0.19979502074420452}
7
+ {"time": "08:54:25", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 835.7991226770059, "loss": 0.5637301504611969, "entropy": 0.5841790549457073, "sharp": 0.19560966454446316}
8
+ {"time": "08:57:57", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 835.9328789186362, "loss": 0.539107870310545, "entropy": 0.5638023987412453, "sharp": 0.2118494249880314}
9
+ {"time": "09:01:23", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 836.8017979254865, "loss": 0.5676501244306564, "entropy": 0.5667039453983307, "sharp": 0.2098743710666895}
10
+ {"time": "09:04:57", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 836.9223540729581, "loss": 0.522164897993207, "entropy": 0.523216400295496, "sharp": 0.2613844182342291}
11
+ {"time": "09:08:29", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 836.4748713209932, "loss": 0.5405332930386066, "entropy": 0.6068024411797523, "sharp": 0.17234522104263306}
12
+ {"time": "09:09:58", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.582358181476593, "noul_T": 0.6771775790462065, "noul_auc": 0.7427722738856728, "noul_acc": 0.698, "noul_f1": 0.7687595712098009, "noul_nll": 0.5847234340012073, "noul_ece": 0.0676120891571045, "noul_brier": 0.20005073664276635, "noul_sharp": 0.14156629145145416, "entropy": 0.6254839897155762}
13
+ {"time": "09:13:25", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 804.9961723731193, "loss": 0.57862932048738, "entropy": 0.5214932118542492, "sharp": 0.24552543088793755}
14
+ {"time": "09:16:47", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 807.6081204496581, "loss": 0.5374317020177841, "entropy": 0.5778878070414066, "sharp": 0.21145328041166067}
15
+ {"time": "09:20:16", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 809.5763680020584, "loss": 0.5415645251050591, "entropy": 0.5926582366228104, "sharp": 0.17765362933278084}
16
+ {"time": "09:23:47", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 811.3271886268961, "loss": 0.6022903248667717, "entropy": 0.5768240466713905, "sharp": 0.1798888687044382}
17
+ {"time": "09:27:10", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 812.4973545748195, "loss": 0.5953593552112579, "entropy": 0.5600479617714882, "sharp": 0.23043405637145042}
18
+ {"time": "09:30:33", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 813.7333815436638, "loss": 0.6341837178915739, "entropy": 0.5304378010332584, "sharp": 0.2400818783789873}
19
+ {"time": "09:34:04", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 814.5757899856069, "loss": 0.6216345056891441, "entropy": 0.5758001245558262, "sharp": 0.1881841029971838}
20
+ {"time": "09:37:30", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 815.9582206518949, "loss": 0.548107597976923, "entropy": 0.5597832128405571, "sharp": 0.2032258678227663}
21
+ {"time": "09:40:55", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 816.8623277624475, "loss": 0.629347488284111, "entropy": 0.6221974045038223, "sharp": 0.15545026026666164}
22
+ {"time": "09:44:23", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 818.350224352774, "loss": 0.5965647250413895, "entropy": 0.5734423957765102, "sharp": 0.19943880662322044}
23
+ {"time": "09:45:51", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5709351301193237, "noul_T": 0.9054920920785222, "noul_auc": 0.7553459013349985, "noul_acc": 0.708, "noul_f1": 0.771875, "noul_nll": 0.5682911076322198, "noul_ece": 0.05305527031421663, "noul_brier": 0.19310725983670293, "noul_sharp": 0.1847848743200302, "entropy": 0.5866526961326599}
24
+ {"time": "09:49:15", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 803.6253983378049, "loss": 0.5758592654019594, "entropy": 0.5610290504992008, "sharp": 0.21150867827236652}
25
+ {"time": "09:52:39", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 805.1141639326146, "loss": 0.5877367667853832, "entropy": 0.5988655090332031, "sharp": 0.17781024612486362}
26
+ {"time": "09:56:05", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 806.7762471768453, "loss": 0.5611191019415855, "entropy": 0.5529461167752743, "sharp": 0.21740258112549782}
27
+ {"time": "09:59:42", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 807.8523899124829, "loss": 0.5064211338758469, "entropy": 0.46510100178420544, "sharp": 0.28999529778957367}
28
+ {"time": "10:03:06", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 808.7339204868856, "loss": 0.5799861662089825, "entropy": 0.5978606194257736, "sharp": 0.17922717705368996}
29
+ {"time": "10:06:29", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 809.7028802800344, "loss": 0.5561951957643032, "entropy": 0.5571439638733864, "sharp": 0.2102230992168188}
30
+ {"time": "10:10:01", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 810.7794624624289, "loss": 0.5507177505642176, "entropy": 0.5507388822734356, "sharp": 0.22063623555004597}
31
+ {"time": "10:13:27", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 811.8539501790132, "loss": 0.61417574621737, "entropy": 0.5640500783920288, "sharp": 0.21359632723033428}
32
+ {"time": "10:16:55", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 812.665923146238, "loss": 0.6132056564092636, "entropy": 0.5555628947913647, "sharp": 0.20448759943246841}
33
+ {"time": "10:20:29", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 813.4748938403405, "loss": 0.5756874978542328, "entropy": 0.5813103020191193, "sharp": 0.18778837844729424}
34
+ {"time": "10:21:58", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.574192225933075, "noul_T": 0.824062551711107, "noul_auc": 0.7487974886499806, "noul_acc": 0.702, "noul_f1": 0.7799113737075333, "noul_nll": 0.5750610038936138, "noul_ece": 0.06447341871261597, "noul_brier": 0.1959945816033789, "noul_sharp": 0.17014318704605103, "entropy": 0.6017271280288696}
35
+ {"time": "10:25:33", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 803.4989472569401, "loss": 0.5397192351520061, "entropy": 0.5600378327071667, "sharp": 0.2120770439505577}
36
+ {"time": "10:29:07", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 804.5192141025964, "loss": 0.591511832550168, "entropy": 0.549209825694561, "sharp": 0.2188182696700096}
37
+ {"time": "10:32:47", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 805.5812247484572, "loss": 0.5198701284825802, "entropy": 0.5457031093537807, "sharp": 0.2327425517141819}
38
+ {"time": "10:36:21", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 806.7955881308642, "loss": 0.587141327559948, "entropy": 0.5754033550620079, "sharp": 0.19428355619311333}
39
+ {"time": "10:39:50", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 807.3175243507479, "loss": 0.6173012033104897, "entropy": 0.6045400276780128, "sharp": 0.16853387095034122}
40
+ {"time": "10:43:18", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 807.8738739686282, "loss": 0.5972716733813286, "entropy": 0.5475169904530048, "sharp": 0.20599391963332891}
41
+ {"time": "10:46:48", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 808.7174946640904, "loss": 0.5553336068987846, "entropy": 0.5477232821285725, "sharp": 0.20929709263145924}
42
+ {"time": "10:50:09", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 809.5900252601398, "loss": 0.5059430198743939, "entropy": 0.499704048037529, "sharp": 0.2582879774272442}
43
+ {"time": "10:53:26", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 809.990853488293, "loss": 0.5753580592572689, "entropy": 0.5226968601346016, "sharp": 0.25239879451692104}
44
+ {"time": "10:56:59", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 810.9080710734625, "loss": 0.605243619531393, "entropy": 0.6162682697176933, "sharp": 0.16592716239392757}
45
+ {"time": "10:58:27", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5797415375709534, "noul_T": 0.8320449295134763, "noul_auc": 0.7505527332872018, "noul_acc": 0.692, "noul_f1": 0.749185667752443, "noul_nll": 0.5784027663320302, "noul_ece": 0.05704875254631045, "noul_brier": 0.19731251626702134, "noul_sharp": 0.16823415458202362, "entropy": 0.6055822968482971}
46
+ {"time": "11:01:49", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 803.4916945625112, "loss": 0.5515014622360468, "entropy": 0.5408761017024517, "sharp": 0.23052178509533405}
47
+ {"time": "11:05:22", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 804.1361700311124, "loss": 0.5371130406856537, "entropy": 0.5283180512487888, "sharp": 0.24967902526259422}
48
+ {"time": "11:08:51", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 804.9387593347993, "loss": 0.5655963644385338, "entropy": 0.5708638802170753, "sharp": 0.21697641164064407}
49
+ {"time": "11:12:21", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 805.6998806657394, "loss": 0.554718628525734, "entropy": 0.5287636704742908, "sharp": 0.23746475018560886}
50
+ {"time": "11:15:50", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 806.2114189014137, "loss": 0.5904020331799984, "entropy": 0.6006583571434021, "sharp": 0.17355942726135254}
51
+ {"time": "11:19:33", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 807.1484862299014, "loss": 0.5470876283943653, "entropy": 0.5555767863988876, "sharp": 0.21666290238499641}
52
+ {"time": "11:23:01", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 807.6344437285674, "loss": 0.5776568613946438, "entropy": 0.5303117372095585, "sharp": 0.23848036117851734}
53
+ {"time": "11:26:29", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 808.2080507464154, "loss": 0.5980146545916796, "entropy": 0.5864263856783509, "sharp": 0.1802331954240799}
54
+ {"time": "11:29:56", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 808.5204472945927, "loss": 0.6027636639773846, "entropy": 0.5958365425467491, "sharp": 0.191914152354002}
55
+ {"time": "11:33:21", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 808.951385924234, "loss": 0.5951005592942238, "entropy": 0.6039759181439877, "sharp": 0.17472452390938997}
56
+ {"time": "11:34:50", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5740304589271545, "noul_T": 0.8335255655714962, "noul_auc": 0.7505358559349209, "noul_acc": 0.7, "noul_f1": 0.7648902821316614, "noul_nll": 0.5738693396300077, "noul_ece": 0.05790331822633744, "noul_brier": 0.195371765743936, "noul_sharp": 0.17256996035575867, "entropy": 0.6003800630569458}
57
+ {"time": "11:38:01", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 8732071, "tok_per_s": 788.6198733006973, "rows_per_s": 1.5210522108815354, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5604627132415771, "noul_T": 0.8435191174895403, "choice_ce": 0.6713417768478394, "choice_T": 1.0507546040503266, "score_ce": 1.063907265663147, "score_T": 0.995887067643377, "noul_auc": 0.7387050666666667, "noul_acc": 0.689, "noul_f1": 0.7645722937168812, "noul_nll": 0.5747933953106403, "noul_ece": 0.05640242668986321, "noul_brier": 0.196318222722157, "noul_sharp": 0.17765387892723083, "entropy": 0.5968260765075684}, "dropped_long": 0, "peak_gib": 18.236003875732422}