Unggi commited on
Commit
8abe344
·
verified ·
1 Parent(s): 302cadb

backup e16/S1-ABCLODO16-assist2017 (Pod B)

Browse files
e16/S1-ABCLODO16-assist2017/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-ABCLODO16-assist2017/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
+ "in_proj_qkv",
40
+ "o_proj",
41
+ "out_proj",
42
+ "in_proj_z",
43
+ "v_proj",
44
+ "gate_proj",
45
+ "up_proj",
46
+ "q_proj",
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-ABCLODO16-assist2017/ckpt-16000/adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2954183a2cb7ac6e7929c0686a7df644c07af64a269754853f9235d5124affc3
3
+ size 160486456
e16/S1-ABCLODO16-assist2017/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-ABCLODO16-assist2017/ckpt-16000/adapter_vllm/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b093ff7d7632d45c897a7a1abecd2cc03642433ee10af92f242c02a0ce359810
3
+ size 176641832
e16/S1-ABCLODO16-assist2017/ckpt-16000/adapter_vllm/decision_head.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bias": [
3
+ 0.00040927628288045526,
4
+ -0.00040953492862172425,
5
+ -0.0024623821955174208,
6
+ -0.0019520617788657546,
7
+ -0.0010230536572635174,
8
+ 0.0018311906605958939,
9
+ 0.001235047122463584,
10
+ -0.002641854342073202,
11
+ -0.0002051556366495788,
12
+ 0.00014161158469505608,
13
+ 0.0003639915958046913,
14
+ 0.0007218548562377691,
15
+ 6.321677210507914e-05,
16
+ -0.004243035335093737,
17
+ -0.005185945425182581,
18
+ -0.00532513065263629,
19
+ -0.005824134219437838,
20
+ -0.00498935068026185,
21
+ -0.00509135564789176,
22
+ -0.005322540178894997,
23
+ -0.004213305190205574,
24
+ -0.0038200432900339365,
25
+ -0.006074630655348301,
26
+ -0.0038122667465358973
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-ABCLODO16-assist2017/ckpt-16000/calibration.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "per_kind": {
4
+ "noul": 0.8779658930896813,
5
+ "choice": 1.0586153851274778,
6
+ "score": 0.999463883122129
7
+ },
8
+ "fit": {
9
+ "noul": {
10
+ "n": 1802,
11
+ "T": 0.8779658930896813,
12
+ "ce_before": 0.5096359252929688,
13
+ "ce_after": 0.5077041983604431
14
+ },
15
+ "choice": {
16
+ "n": 60,
17
+ "T": 1.0586153851274778,
18
+ "ce_before": 0.6665715575218201,
19
+ "ce_after": 0.6658780574798584
20
+ },
21
+ "score": {
22
+ "n": 53,
23
+ "T": 0.999463883122129,
24
+ "ce_before": 1.0604978799819946,
25
+ "ce_after": 1.0604976415634155
26
+ }
27
+ },
28
+ "source": "models/e16/S1-ABCLODO16-assist2017/ckpt-16000"
29
+ }
e16/S1-ABCLODO16-assist2017/ckpt-16000/head.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba91fa20c474b069dd4856f0e908b038cfeb6973cc0eecf2f9b2c634da8e05a
3
+ size 393464
e16/S1-ABCLODO16-assist2017/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-ABCLODO16-assist2017/ckpt-16000",
103
+ "softcap": null,
104
+ "e16": {
105
+ "data": "data/e15/F1-pool-jev-LODO-assist2017",
106
+ "data_manifest": {
107
+ "arm": "F1-pool-jev-LODO-assist2017",
108
+ "name": "F1-pool-jev-LODO-assist2017",
109
+ "train_sha256": "9dbf42b1808e6e30e25cb683e9af5d16a00e01a73e276ab15caf322e8d5658fe",
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": 10933920,
141
+ "tok_per_s": 806.5213094628934,
142
+ "rows_per_s": 1.2423204018759684,
143
+ "val": {
144
+ "n": 1915,
145
+ "dropped_long": 0,
146
+ "noul_ce": 0.5096359252929688,
147
+ "noul_T": 0.8779658930896813,
148
+ "choice_ce": 0.6665715575218201,
149
+ "choice_T": 1.0586153851274778,
150
+ "score_ce": 1.0604978799819946,
151
+ "score_T": 0.999463883122129,
152
+ "noul_auc": 0.7646995791770573,
153
+ "noul_acc": 0.7457725947521866,
154
+ "noul_f1": 0.8302180685358256,
155
+ "noul_nll": 0.513827748088378,
156
+ "noul_ece": 0.029651220095053357,
157
+ "noul_brier": 0.1699452421449938,
158
+ "noul_sharp": 0.23468017578125,
159
+ "entropy": 0.5424526929855347
160
+ },
161
+ "dropped_long": 0,
162
+ "peak_gib": 18.23796796798706
163
+ }
164
+ }
e16/S1-ABCLODO16-assist2017/train_log.jsonl ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time": "08:15:10", "event": "start", "data": "data/e15/F1-pool-jev-LODO-assist2017", "data_manifest": {"arm": "F1-pool-jev-LODO-assist2017", "name": "F1-pool-jev-LODO-assist2017", "train_sha256": "9dbf42b1808e6e30e25cb683e9af5d16a00e01a73e276ab15caf322e8d5658fe", "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": 78.4912600517273}
2
+ {"time": "08:19:26", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 857.1289302096058, "loss": 0.5972497425973415, "entropy": 0.5818394273519516, "sharp": 0.1991501022130251}
3
+ {"time": "08:23:43", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 861.7242938345466, "loss": 0.5753555502742529, "entropy": 0.5526528283953667, "sharp": 0.22482357546687126}
4
+ {"time": "08:28:01", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 861.4053125776298, "loss": 0.5489222034811974, "entropy": 0.527637654915452, "sharp": 0.2435856182128191}
5
+ {"time": "08:32:12", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 863.5683553791118, "loss": 0.5504921209067106, "entropy": 0.5790511593222618, "sharp": 0.21567639894783497}
6
+ {"time": "08:36:27", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 863.9049372023181, "loss": 0.6193182533606887, "entropy": 0.5932723991572857, "sharp": 0.1961939986795187}
7
+ {"time": "08:40:36", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 863.998219035659, "loss": 0.5490664709359407, "entropy": 0.539305267855525, "sharp": 0.2464555874466896}
8
+ {"time": "08:44:49", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 864.3475492841758, "loss": 0.5705515723675489, "entropy": 0.5266973711550236, "sharp": 0.2287063840776682}
9
+ {"time": "08:49:05", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 863.7324740618906, "loss": 0.5888552432879806, "entropy": 0.5955713856965303, "sharp": 0.19920486770570278}
10
+ {"time": "08:53:20", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 864.6517126375479, "loss": 0.649688120931387, "entropy": 0.5487383231520653, "sharp": 0.24057279527187347}
11
+ {"time": "08:57:21", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 864.8533437528803, "loss": 0.5543805956840515, "entropy": 0.5379879996180534, "sharp": 0.22912908904254436}
12
+ {"time": "08:59:09", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5447214841842651, "noul_T": 1.010942757298706, "noul_auc": 0.720961887477314, "noul_acc": 0.74, "noul_f1": 0.8293963254593176, "noul_nll": 0.5447215413600206, "noul_ece": 0.06271952831745149, "noul_brier": 0.1826785045385255, "noul_sharp": 0.23350830376148224, "entropy": 0.5422672033309937}
13
+ {"time": "09:03:12", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 832.5929058338788, "loss": 0.5198168708011508, "entropy": 0.583518335595727, "sharp": 0.20403067581355572}
14
+ {"time": "09:07:25", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 835.3913515211327, "loss": 0.5692883087322116, "entropy": 0.5416508764028549, "sharp": 0.24099773354828358}
15
+ {"time": "09:11:39", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 837.838495531447, "loss": 0.5808135261759162, "entropy": 0.5520810205489397, "sharp": 0.22950002178549767}
16
+ {"time": "09:15:56", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 840.0299657388381, "loss": 0.5038412632420659, "entropy": 0.5463015008717775, "sharp": 0.23311700113117695}
17
+ {"time": "09:20:06", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 841.4853376148454, "loss": 0.6135150948539376, "entropy": 0.5864709988236427, "sharp": 0.2038662899285555}
18
+ {"time": "09:24:06", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 843.4663393708789, "loss": 0.6521173701621592, "entropy": 0.5274120466783643, "sharp": 0.23028940707445145}
19
+ {"time": "09:28:26", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 845.3255509694329, "loss": 0.587873812764883, "entropy": 0.6114490106701851, "sharp": 0.17347712628543377}
20
+ {"time": "09:32:42", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 846.3762021506666, "loss": 0.5290134139358997, "entropy": 0.551151180639863, "sharp": 0.22589223459362984}
21
+ {"time": "09:36:47", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 847.3723515162699, "loss": 0.5159809133037925, "entropy": 0.4723542872816324, "sharp": 0.2958002034574747}
22
+ {"time": "09:41:00", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 848.6801337058213, "loss": 0.5487458370625973, "entropy": 0.5574409607797861, "sharp": 0.22517722472548485}
23
+ {"time": "09:42:47", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5355785489082336, "noul_T": 0.855424966053002, "noul_auc": 0.7373525408348457, "noul_acc": 0.742, "noul_f1": 0.8244897959183674, "noul_nll": 0.5355785605534911, "noul_ece": 0.07825727796554566, "noul_brier": 0.17878716227722624, "noul_sharp": 0.21318088471889496, "entropy": 0.565828800201416}
24
+ {"time": "09:46:57", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 832.9634694254396, "loss": 0.5891058454290032, "entropy": 0.5587287321686745, "sharp": 0.23191190510988235}
25
+ {"time": "09:50:59", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 834.4557903491468, "loss": 0.5071025919169188, "entropy": 0.5242788624018431, "sharp": 0.2508408911526203}
26
+ {"time": "09:55:12", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 835.4611930555102, "loss": 0.48438416607677937, "entropy": 0.4720079153776169, "sharp": 0.28471007756888866}
27
+ {"time": "09:59:25", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 836.6753104772931, "loss": 0.5067836008965969, "entropy": 0.5417653359472752, "sharp": 0.24569746479392052}
28
+ {"time": "10:03:41", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 837.8071336926274, "loss": 0.5816275216639042, "entropy": 0.586901493370533, "sharp": 0.1935853771865368}
29
+ {"time": "10:07:54", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 838.7144744349388, "loss": 0.541350657120347, "entropy": 0.5213802717626095, "sharp": 0.2686269339174032}
30
+ {"time": "10:12:11", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 839.7335900218127, "loss": 0.5233259927481413, "entropy": 0.568665437400341, "sharp": 0.21889268048107624}
31
+ {"time": "10:16:24", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 840.5885320442309, "loss": 0.5846356004476547, "entropy": 0.5742264240980148, "sharp": 0.20898466743528843}
32
+ {"time": "10:20:37", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 841.4273700844282, "loss": 0.5683433338999748, "entropy": 0.5564332902431488, "sharp": 0.22886591590940952}
33
+ {"time": "10:24:52", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 842.4500385823402, "loss": 0.5947871319949627, "entropy": 0.5176953850314021, "sharp": 0.24002568237483501}
34
+ {"time": "10:26:40", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5305177569389343, "noul_T": 0.9946390652247512, "noul_auc": 0.7402828191167574, "noul_acc": 0.746, "noul_f1": 0.8286099865047234, "noul_nll": 0.5305177900642156, "noul_ece": 0.05592792248725892, "noul_brier": 0.17729678068589094, "noul_sharp": 0.2355841100215912, "entropy": 0.531838595867157}
35
+ {"time": "10:30:47", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 831.8405745758618, "loss": 0.5485512278974056, "entropy": 0.5893426220864058, "sharp": 0.18830912467092276}
36
+ {"time": "10:34:57", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 832.751232139624, "loss": 0.5457311058416963, "entropy": 0.5252990275621414, "sharp": 0.24732360802590847}
37
+ {"time": "10:39:18", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 833.903225202841, "loss": 0.5291090197861195, "entropy": 0.5594097152352333, "sharp": 0.21454769279807806}
38
+ {"time": "10:43:26", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 834.7195688512558, "loss": 0.6017689406871796, "entropy": 0.5646613873541355, "sharp": 0.20475484244525433}
39
+ {"time": "10:47:42", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 835.7222806653384, "loss": 0.5914549510926008, "entropy": 0.6018632259219885, "sharp": 0.18413380160927773}
40
+ {"time": "10:51:56", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 836.3564033534601, "loss": 0.637239433825016, "entropy": 0.5725442403927445, "sharp": 0.2001000875607133}
41
+ {"time": "10:56:11", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 837.1148614515313, "loss": 0.5318860178813338, "entropy": 0.5404505394399166, "sharp": 0.24232733808457851}
42
+ {"time": "11:00:25", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 837.6508674831142, "loss": 0.6337099391967058, "entropy": 0.5457093277946115, "sharp": 0.21399748139083385}
43
+ {"time": "11:04:36", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 838.423754766101, "loss": 0.5544848050922155, "entropy": 0.562541551887989, "sharp": 0.22451280429959297}
44
+ {"time": "11:08:54", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 839.0193218492931, "loss": 0.5480520110577345, "entropy": 0.5417163521051407, "sharp": 0.23495346121490002}
45
+ {"time": "11:10:42", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5328932404518127, "noul_T": 0.9741612969911708, "noul_auc": 0.7364640048396853, "noul_acc": 0.746, "noul_f1": 0.8286099865047234, "noul_nll": 0.5328932885825634, "noul_ece": 0.075112099647522, "noul_brier": 0.17784292068092836, "noul_sharp": 0.23480987548828125, "entropy": 0.5388015508651733}
46
+ {"time": "11:14:55", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 831.1755516521906, "loss": 0.570873312652111, "entropy": 0.5456271469593048, "sharp": 0.22485392168164253}
47
+ {"time": "11:19:10", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 831.9124535352613, "loss": 0.5761410528793931, "entropy": 0.5480227395892143, "sharp": 0.2292386256158352}
48
+ {"time": "11:23:23", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 832.634992386149, "loss": 0.600891238078475, "entropy": 0.5589494183659554, "sharp": 0.22292004711925983}
49
+ {"time": "11:27:40", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 833.1199999657058, "loss": 0.6150478608906269, "entropy": 0.609391875565052, "sharp": 0.166204534471035}
50
+ {"time": "11:31:56", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 833.8161484427995, "loss": 0.5990298725664616, "entropy": 0.5943930521607399, "sharp": 0.17246167920529842}
51
+ {"time": "11:36:11", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 834.3489036408395, "loss": 0.5956465639173985, "entropy": 0.5381777063012123, "sharp": 0.23462899029254913}
52
+ {"time": "11:40:26", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 834.9719476958718, "loss": 0.586854811757803, "entropy": 0.5768598094582558, "sharp": 0.19583198800683022}
53
+ {"time": "11:44:39", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 835.5414997342917, "loss": 0.5626069903373718, "entropy": 0.5784194376319647, "sharp": 0.20383292622864246}
54
+ {"time": "11:48:47", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 836.0607420506733, "loss": 0.5550620807334781, "entropy": 0.5657355478033423, "sharp": 0.20575360022485256}
55
+ {"time": "11:53:00", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 836.544555763203, "loss": 0.5895328857004642, "entropy": 0.5650578998029232, "sharp": 0.21742793917655945}
56
+ {"time": "11:54:48", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5312949419021606, "noul_T": 0.9299107466306102, "noul_auc": 0.7401315789473684, "noul_acc": 0.748, "noul_f1": 0.8297297297297297, "noul_nll": 0.5312949609681964, "noul_ece": 0.05102215397357942, "noul_brier": 0.17722524817939156, "noul_sharp": 0.2297707200050354, "entropy": 0.5469624400138855}
57
+ {"time": "12:01:45", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 10933920, "tok_per_s": 806.5213094628934, "rows_per_s": 1.2423204018759684, "val": {"n": 1915, "dropped_long": 0, "noul_ce": 0.5096359252929688, "noul_T": 0.8779658930896813, "choice_ce": 0.6665715575218201, "choice_T": 1.0586153851274778, "score_ce": 1.0604978799819946, "score_T": 0.999463883122129, "noul_auc": 0.7646995791770573, "noul_acc": 0.7457725947521866, "noul_f1": 0.8302180685358256, "noul_nll": 0.513827748088378, "noul_ece": 0.029651220095053357, "noul_brier": 0.1699452421449938, "noul_sharp": 0.23468017578125, "entropy": 0.5424526929855347}, "dropped_long": 0, "peak_gib": 18.23796796798706}