pod backup 2026-11-07: e48/S1-E48-SHRA050-ts0-syn (0-11)

e48/S1-E48-SHRA050-ts0-syn/DONE

@@ -0,0 +1 @@
+2026-11-08 04:30:22

e48/S1-E48-SHRA050-ts0-syn/ckpt-16000/adapter/README.md

@@ -0,0 +1,206 @@
+---
+base_model: /workspace/jev_kt/models/hf/JEV-9B
+library_name: peft
+tags:
+- base_model:adapter:/workspace/jev_kt/models/hf/JEV-9B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.21.2

e48/S1-E48-SHRA050-ts0-syn/ckpt-16000/adapter/adapter_config.json

@@ -0,0 +1,57 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForCausalLM",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
+  },
+  "base_model_name_or_path": "/workspace/jev_kt/models/hf/JEV-9B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "out_proj",
+    "in_proj_qkv",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "in_proj_z"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

e48/S1-E48-SHRA050-ts0-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c59cdf7ed1a97f847e38ec189bc732f9fb05bf4ce11bbb97b919e19503e4770
+size 160486456

e48/S1-E48-SHRA050-ts0-syn/ckpt-16000/adapter_vllm/adapter_config.json

@@ -0,0 +1,58 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForCausalLM",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64.0,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "in_proj_qkv",
+    "in_proj_z",
+    "k_proj",
+    "lm_head",
+    "o_proj",
+    "out_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

e48/S1-E48-SHRA050-ts0-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbcf56bf5c249ccbe8ce3436cdebed98f45d9789214ac68fc6168fdfa2d63c1a
+size 176641832

e48/S1-E48-SHRA050-ts0-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00040509452810510993,
+  -0.0004053584998473525,
+  -0.0027677789330482483,
+  -0.0017022074898704886,
+  -0.0002430155873298645,
+  0.0022081511560827494,
+  0.0014918235829100013,
+  -0.002684249309822917,
+  -0.0007026426028460264,
+  -0.0005835061892867088,
+  -0.0003670124860946089,
+  0.0002840521920006722,
+  -0.0002437919465592131,
+  -0.0038237464614212513,
+  -0.004169325344264507,
+  -0.005198883358389139,
+  -0.006016193889081478,
+  -0.0044691311195492744,
+  -0.0049585034139454365,
+  -0.005063971970230341,
+  -0.00398055138066411,
+  -0.003465659450739622,
+  -0.0057609970681369305,
+  -0.0035279567819088697
+ ],
+ "verbalizer_ids": [
+  3721,
+  1802,
+  15,
+  16,
+  17,
+  18,
+  19,
+  20,
+  32,
+  33,
+  34,
+  35,
+  36,
+  37,
+  38,
+  39,
+  40,
+  41,
+  42,
+  43,
+  44,
+  45,
+  46,
+  47
+ ],
+ "slots": {
+  "num_slots": 24,
+  "ranges": {
+   "noul": [
+    0,
+    2
+   ],
+   "score": [
+    2,
+    8
+   ],
+   "choice": [
+    8,
+    24
+   ]
+  },
+  "verbalizers": [
+   "false",
+   "true",
+   "0",
+   "1",
+   "2",
+   "3",
+   "4",
+   "5",
+   "A",
+   "B",
+   "C",
+   "D",
+   "E",
+   "F",
+   "G",
+   "H",
+   "I",
+   "J",
+   "K",
+   "L",
+   "M",
+   "N",
+   "O",
+   "P"
+  ],
+  "template_version": "bare-v1"
+ },
+ "note": "decision logits = lm_head-LoRA logprobs of verbalizer ids + bias, then per-kind temperature"
+}

e48/S1-E48-SHRA050-ts0-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8511702130407988,
+  "choice": 0.9945666463705635,
+  "score": 0.9779444604595182
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.8511702130407988,
+   "ce_before": 0.5585967302322388,
+   "ce_after": 0.5564779043197632
+  },
+  "choice": {
+   "n": 60,
+   "T": 0.9945666463705635,
+   "ce_before": 0.6835176944732666,
+   "ce_after": 0.6835108399391174
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9779444604595182,
+   "ce_before": 1.0753581523895264,
+   "ce_after": 1.0752049684524536
+  }
+ },
+ "source": "models/e48/S1-E48-SHRA050-ts0-syn/ckpt-16000"
+}

e48/S1-E48-SHRA050-ts0-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e13fdb486f57fa5213fe4c5fb265a9e07c9eea3d3333170c9c09750a9a1353d
+size 393464

e48/S1-E48-SHRA050-ts0-syn/ckpt-16000/judge_config.json

@@ -0,0 +1,164 @@
+{
+ "base_model_path": "/root/models/Qwen3.5-9B",
+ "hidden_size": 4096,
+ "slots": {
+  "num_slots": 24,
+  "ranges": {
+   "noul": [
+    0,
+    2
+   ],
+   "score": [
+    2,
+    8
+   ],
+   "choice": [
+    8,
+    24
+   ]
+  },
+  "verbalizers": [
+   "false",
+   "true",
+   "0",
+   "1",
+   "2",
+   "3",
+   "4",
+   "5",
+   "A",
+   "B",
+   "C",
+   "D",
+   "E",
+   "F",
+   "G",
+   "H",
+   "I",
+   "J",
+   "K",
+   "L",
+   "M",
+   "N",
+   "O",
+   "P"
+  ],
+  "template_version": "bare-v1"
+ },
+ "verbalizer_ids": [
+  3721,
+  1802,
+  15,
+  16,
+  17,
+  18,
+  19,
+  20,
+  32,
+  33,
+  34,
+  35,
+  36,
+  37,
+  38,
+  39,
+  40,
+  41,
+  42,
+  43,
+  44,
+  45,
+  46,
+  47
+ ],
+ "kinds": [
+  "noul",
+  "choice",
+  "score"
+ ],
+ "model_name": "jev-judge-qwen35-9b",
+ "model_version": "0.8.0",
+ "lm_head_included": true,
+ "weights_mode": "unmerged",
+ "adapter_subfolder": "adapter",
+ "lora": {
+  "r": 16,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "target_modules": [
+   "down_proj",
+   "gate_proj",
+   "in_proj_qkv",
+   "in_proj_z",
+   "k_proj",
+   "o_proj",
+   "out_proj",
+   "q_proj",
+   "up_proj",
+   "v_proj"
+  ]
+ },
+ "trained_stage": "e16",
+ "source_checkpoint": "models/e48/S1-E48-SHRA050-ts0-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e48/E48-SHR-A050",
+  "data_manifest": {
+   "arm": "E48-SHR-A050",
+   "name": null,
+   "train_sha256": "62ace86bbc110367950b57ff804cc82fa35dd319890d7e5dfc6187d218314782",
+   "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": "a0b9d7552588ffb068565686509162a4f122f6f03392e693fa20088493e2a4f3",
+  "event": "ckpt",
+  "tag": "ckpt-16000",
+  "rows_seen": 16000,
+  "replay_seen": 842,
+  "step": 500,
+  "tokens": 9113125,
+  "tok_per_s": 1251.748332314299,
+  "rows_per_s": 2.313360719470415,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5585967302322388,
+   "noul_T": 0.8511702130407988,
+   "choice_ce": 0.6835176944732666,
+   "choice_T": 0.9945666463705635,
+   "score_ce": 1.0753581523895264,
+   "score_T": 0.9779444604595182,
+   "noul_auc": 0.7462698666666667,
+   "noul_acc": 0.704,
+   "noul_f1": 0.7754172989377845,
+   "noul_nll": 0.5703666204027832,
+   "noul_ece": 0.04340002651512624,
+   "noul_brier": 0.19438204629516412,
+   "noul_sharp": 0.18136291205883026,
+   "entropy": 0.5943158864974976
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.284047603607178
+ }
+}

e48/S1-E48-SHRA050-ts0-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "02:29:01", "event": "start", "data": "data/e48/E48-SHR-A050", "data_manifest": {"arm": "E48-SHR-A050", "name": null, "train_sha256": "62ace86bbc110367950b57ff804cc82fa35dd319890d7e5dfc6187d218314782", "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": "a0b9d7552588ffb068565686509162a4f122f6f03392e693fa20088493e2a4f3", "device": "cuda", "load_s": 5.365743160247803}
+{"time": "02:31:19", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 1307.7264658082295, "loss": 0.5976642370223999, "entropy": 0.5954950861632824, "sharp": 0.19248798675835133}
+{"time": "02:33:38", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 1309.0346966095624, "loss": 0.6068046130239964, "entropy": 0.617702554911375, "sharp": 0.1731541147455573}
+{"time": "02:35:58", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 1310.1331222062254, "loss": 0.6117159239947796, "entropy": 0.5357620865106583, "sharp": 0.24037800636142492}
+{"time": "02:38:14", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 1310.918907671213, "loss": 0.5811467058956623, "entropy": 0.6167394779622555, "sharp": 0.167637187987566}
+{"time": "02:40:35", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 1313.3175053609186, "loss": 0.559920696541667, "entropy": 0.5735882110893726, "sharp": 0.2035163827240467}
+{"time": "02:42:50", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 1315.5798197855722, "loss": 0.5898825936019421, "entropy": 0.6238793358206749, "sharp": 0.16156574618071318}
+{"time": "02:45:10", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 1315.7350725171066, "loss": 0.5818422958254814, "entropy": 0.5908481180667877, "sharp": 0.18846516124904156}
+{"time": "02:47:27", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 1316.3165559021786, "loss": 0.6154877673834562, "entropy": 0.6081247963011265, "sharp": 0.18164896313101053}
+{"time": "02:49:48", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 1318.2925537599533, "loss": 0.6338950414210558, "entropy": 0.6201141085475683, "sharp": 0.15101863630115986}
+{"time": "02:52:07", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 1318.492111373945, "loss": 0.5678734332323074, "entropy": 0.5887243263423443, "sharp": 0.1944686509668827}
+{"time": "02:53:00", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5793788433074951, "noul_T": 0.9689176332324136, "noul_auc": 0.7421140571467149, "noul_acc": 0.696, "noul_f1": 0.7516339869281046, "noul_nll": 0.5849899276569486, "noul_ece": 0.08184943324327472, "noul_brier": 0.20025479492805304, "noul_sharp": 0.1918403059244156, "entropy": 0.5846610069274902}
+{"time": "02:55:15", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 1275.959904564322, "loss": 0.6121588945388794, "entropy": 0.6133464723825455, "sharp": 0.16676657646894455}
+{"time": "02:57:41", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 1280.4449771082711, "loss": 0.5816125515848398, "entropy": 0.584588386118412, "sharp": 0.19105196185410023}
+{"time": "03:00:06", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 1284.2578537729864, "loss": 0.5725985020399094, "entropy": 0.5535742491483688, "sharp": 0.222604276612401}
+{"time": "03:02:24", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 1286.403751107998, "loss": 0.6147027127444744, "entropy": 0.6144458688795567, "sharp": 0.16882180981338024}
+{"time": "03:04:45", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 1288.4931016474804, "loss": 0.6429688110947609, "entropy": 0.6339177899062634, "sharp": 0.14608903229236603}
+{"time": "03:07:01", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 1290.186757429098, "loss": 0.6301140915602446, "entropy": 0.5502193700522184, "sharp": 0.2215726636350155}
+{"time": "03:09:21", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 1292.2219468910605, "loss": 0.6098628211766481, "entropy": 0.6227544844150543, "sharp": 0.15162650402635336}
+{"time": "03:11:39", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 1294.0508841782719, "loss": 0.5923351868987083, "entropy": 0.6098104864358902, "sharp": 0.17440761625766754}
+{"time": "03:13:58", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 1294.9051658329029, "loss": 0.6321669928729534, "entropy": 0.6040636003017426, "sharp": 0.17190536856651306}
+{"time": "03:16:17", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 1296.3011406967792, "loss": 0.5881068166345358, "entropy": 0.6085112206637859, "sharp": 0.1804777765646577}
+{"time": "03:17:09", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5762492418289185, "noul_T": 0.8095805319546592, "noul_auc": 0.7458270746485294, "noul_acc": 0.706, "noul_f1": 0.766295707472178, "noul_nll": 0.5796876553148032, "noul_ece": 0.06179205048084261, "noul_brier": 0.1974989726519525, "noul_sharp": 0.17394712567329407, "entropy": 0.6068127155303955}
+{"time": "03:19:30", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 1275.2563399064927, "loss": 0.5844452418386936, "entropy": 0.5648749954998493, "sharp": 0.21278484538197517}
+{"time": "03:21:46", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 1277.0713597450858, "loss": 0.6023380383849144, "entropy": 0.5918728485703468, "sharp": 0.18467144388705492}
+{"time": "03:24:00", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 1278.8247267517158, "loss": 0.5890407394617796, "entropy": 0.5927225854247808, "sharp": 0.19988637045025826}
+{"time": "03:26:16", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 1280.3954298535862, "loss": 0.593925055116415, "entropy": 0.5856457613408566, "sharp": 0.19586355425417423}
+{"time": "03:28:44", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 1281.4926903876571, "loss": 0.6196377612650394, "entropy": 0.6086195595562458, "sharp": 0.16690325643867254}
+{"time": "03:30:54", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 1282.5387726572774, "loss": 0.5871985740959644, "entropy": 0.6047235727310181, "sharp": 0.1657487554475665}
+{"time": "03:33:12", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 1283.7923013171674, "loss": 0.6380929360166192, "entropy": 0.6263891970738769, "sharp": 0.14954097475856543}
+{"time": "03:35:29", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 1285.1925405582565, "loss": 0.6355991186574101, "entropy": 0.6045290399342775, "sharp": 0.1769256442785263}
+{"time": "03:37:50", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 1286.4019491733843, "loss": 0.6160958223044872, "entropy": 0.5953326001763344, "sharp": 0.17337027564644814}
+{"time": "03:40:10", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 1287.7553765573105, "loss": 0.5871474295854568, "entropy": 0.5870184935629368, "sharp": 0.17071148939430714}
+{"time": "03:41:03", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5697179436683655, "noul_T": 0.8550837898810005, "noul_auc": 0.7483755548429561, "noul_acc": 0.702, "noul_f1": 0.7697063369397218, "noul_nll": 0.5735357319489122, "noul_ece": 0.05059684062004091, "noul_brier": 0.19568927821762439, "noul_sharp": 0.18049901723861694, "entropy": 0.5936886072158813}
+{"time": "03:43:17", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 1273.3509034003146, "loss": 0.5738721247762442, "entropy": 0.6137784216552973, "sharp": 0.1618794770911336}
+{"time": "03:45:28", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 1274.2213026720206, "loss": 0.6368708284571767, "entropy": 0.6122182570397854, "sharp": 0.1686367243528366}
+{"time": "03:47:46", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 1275.7584350003212, "loss": 0.5812924057245255, "entropy": 0.5880858115851879, "sharp": 0.18606704287230968}
+{"time": "03:50:03", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 1276.9865514370217, "loss": 0.6297401338815689, "entropy": 0.5946385562419891, "sharp": 0.18401191756129265}
+{"time": "03:52:16", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 1278.0700802700308, "loss": 0.6125870794057846, "entropy": 0.6157106384634972, "sharp": 0.14952658116817474}
+{"time": "03:54:31", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 1279.6184827936895, "loss": 0.623608224093914, "entropy": 0.594383742660284, "sharp": 0.18850953225046396}
+{"time": "03:56:46", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 1281.0792507027554, "loss": 0.6017014561221004, "entropy": 0.5775783769786358, "sharp": 0.20045165345072746}
+{"time": "03:59:08", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 1282.0675927843702, "loss": 0.6189353279769421, "entropy": 0.6081398241221905, "sharp": 0.16899381950497627}
+{"time": "04:01:30", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 1283.6240085372626, "loss": 0.6280602365732193, "entropy": 0.6097052302211523, "sharp": 0.16422216314822435}
+{"time": "04:03:43", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 1284.253732257274, "loss": 0.6024149060249329, "entropy": 0.6021302677690983, "sharp": 0.16637047752738}
+{"time": "04:04:36", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5693955421447754, "noul_T": 0.9031781225482219, "noul_auc": 0.7497426203777151, "noul_acc": 0.7, "noul_f1": 0.7685185185185185, "noul_nll": 0.5721986741870642, "noul_ece": 0.04902059733867648, "noul_brier": 0.19518946454796907, "noul_sharp": 0.18840157985687256, "entropy": 0.5858985185623169}
+{"time": "04:06:52", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 1273.4277254809585, "loss": 0.6081468686461449, "entropy": 0.6030836626887321, "sharp": 0.1714553264901042}
+{"time": "04:09:03", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 1274.2342755953164, "loss": 0.6361902579665184, "entropy": 0.6183247994631529, "sharp": 0.15705930069088936}
+{"time": "04:11:24", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 1275.3210109263093, "loss": 0.6110078198835254, "entropy": 0.6007933001965284, "sharp": 0.1700382838025689}
+{"time": "04:13:38", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 1276.1728763473393, "loss": 0.6128862164914608, "entropy": 0.6028715744614601, "sharp": 0.16359547711908817}
+{"time": "04:16:02", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 1277.0091946458595, "loss": 0.5731789954006672, "entropy": 0.6075462065637112, "sharp": 0.17417885921895504}
+{"time": "04:18:14", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 1277.6610304000221, "loss": 0.5954545419663191, "entropy": 0.595540028065443, "sharp": 0.18857285007834435}
+{"time": "04:20:28", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 1278.3415131309332, "loss": 0.6265052482485771, "entropy": 0.6049822978675365, "sharp": 0.17891959846019745}
+{"time": "04:22:51", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 1279.2770644306559, "loss": 0.6025526374578476, "entropy": 0.5867367833852768, "sharp": 0.19739339593797922}
+{"time": "04:25:13", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 1280.0268296185106, "loss": 0.5836260356009007, "entropy": 0.5888068713247776, "sharp": 0.193222438916564}
+{"time": "04:27:36", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 1280.8973223401038, "loss": 0.5622859746217728, "entropy": 0.5566469021141529, "sharp": 0.22921524941921234}
+{"time": "04:28:29", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5718035101890564, "noul_T": 0.8501004252924329, "noul_auc": 0.7516160064809033, "noul_acc": 0.71, "noul_f1": 0.7702060221870047, "noul_nll": 0.5726049681827426, "noul_ece": 0.04939340376853945, "noul_brier": 0.19514887602989786, "noul_sharp": 0.17870931327342987, "entropy": 0.5962087512016296}
+{"time": "04:30:22", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9113125, "tok_per_s": 1251.748332314299, "rows_per_s": 2.313360719470415, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5585967302322388, "noul_T": 0.8511702130407988, "choice_ce": 0.6835176944732666, "choice_T": 0.9945666463705635, "score_ce": 1.0753581523895264, "score_T": 0.9779444604595182, "noul_auc": 0.7462698666666667, "noul_acc": 0.704, "noul_f1": 0.7754172989377845, "noul_nll": 0.5703666204027832, "noul_ece": 0.04340002651512624, "noul_brier": 0.19438204629516412, "noul_sharp": 0.18136291205883026, "entropy": 0.5943158864974976}, "dropped_long": 0, "peak_gib": 18.284047603607178}