pod backup 2026-11-07: e48/S1-E48-SHRA050-ts1-syn (0-11)

e48/S1-E48-SHRA050-ts1-syn/DONE

@@ -0,0 +1 @@
+2026-11-08 13:54:22

e48/S1-E48-SHRA050-ts1-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-ts1-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": [
+    "in_proj_z",
+    "v_proj",
+    "k_proj",
+    "in_proj_qkv",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "out_proj",
+    "q_proj",
+    "gate_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-ts1-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d594818df96139b7bfd7f6e12d8b78d3ec6cff637cdfb3c5ada7a403fbda6fb6
+size 160486456

e48/S1-E48-SHRA050-ts1-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-ts1-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93fcd6ab9e4faab40d3daa1cdd0a6450e30b78fd2c381131f4a95dac211f9fa
+size 176641832

e48/S1-E48-SHRA050-ts1-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00040472298860549927,
+  -0.0004049892886541784,
+  -0.00234150025062263,
+  -0.0020411277655512094,
+  -0.0009532564436085522,
+  0.0018299369839951396,
+  0.0011856455821543932,
+  -0.0028400884475558996,
+  -0.0006695939810015261,
+  -0.0003739208332262933,
+  -3.990880213677883e-05,
+  0.0004845347430091351,
+  -6.229705468285829e-05,
+  -0.0036219635512679815,
+  -0.004178308416157961,
+  -0.005187069997191429,
+  -0.006049076560884714,
+  -0.004360849969089031,
+  -0.004933806136250496,
+  -0.004964523017406464,
+  -0.0038274622056633234,
+  -0.003376124892383814,
+  -0.005670318379998207,
+  -0.003476149868220091
+ ],
+ "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-ts1-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8700627381643509,
+  "choice": 1.0459399832418157,
+  "score": 1.0145719661292092
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.8700627381643509,
+   "ce_before": 0.5587899684906006,
+   "ce_after": 0.557197630405426
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0459399832418157,
+   "ce_before": 0.6794756650924683,
+   "ce_after": 0.6790361404418945
+  },
+  "score": {
+   "n": 53,
+   "T": 1.0145719661292092,
+   "ce_before": 1.0803722143173218,
+   "ce_after": 1.0803149938583374
+  }
+ },
+ "source": "models/e48/S1-E48-SHRA050-ts1-syn/ckpt-16000"
+}

e48/S1-E48-SHRA050-ts1-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1986e5156a7a0c10c9c791eeb4aadcaf36d53605634c073e2e07339d03a8b3c
+size 393464

e48/S1-E48-SHRA050-ts1-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-ts1-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": 1,
+  "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": 1248.655911467973,
+  "rows_per_s": 2.307645605151653,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5587899684906006,
+   "noul_T": 0.8700627381643509,
+   "choice_ce": 0.6794756650924683,
+   "choice_T": 1.0459399832418157,
+   "score_ce": 1.0803722143173218,
+   "score_T": 1.0145719661292092,
+   "noul_auc": 0.7453013333333334,
+   "noul_acc": 0.703,
+   "noul_f1": 0.7751703255109765,
+   "noul_nll": 0.5708677803426981,
+   "noul_ece": 0.04532328684628009,
+   "noul_brier": 0.1945894423967694,
+   "noul_sharp": 0.18444940447807312,
+   "entropy": 0.5912659168243408
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.28459882736206
+ }
+}

e48/S1-E48-SHRA050-ts1-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "11:52:43", "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": 1, "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": 5.294910669326782}
+{"time": "11:54:56", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 1297.1968143260483, "loss": 0.6132648661732674, "entropy": 0.6091234982013702, "sharp": 0.17198468931019306}
+{"time": "11:57:18", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 1305.9829499506836, "loss": 0.5934218624606729, "entropy": 0.5812155622988939, "sharp": 0.19944182969629765}
+{"time": "11:59:38", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 1308.1091723443853, "loss": 0.6368932612240314, "entropy": 0.6070720329880714, "sharp": 0.1639698464423418}
+{"time": "12:02:03", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 1307.7770700803694, "loss": 0.6236539743840694, "entropy": 0.6134937033057213, "sharp": 0.15100612211972475}
+{"time": "12:04:23", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 1312.1095513590476, "loss": 0.6451369635760784, "entropy": 0.6000324077904224, "sharp": 0.1800650618970394}
+{"time": "12:06:45", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 1313.5903430918825, "loss": 0.6183715090155602, "entropy": 0.5779797658324242, "sharp": 0.19272825494408607}
+{"time": "12:08:56", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 1315.1113540949957, "loss": 0.5637726970016956, "entropy": 0.5772505179047585, "sharp": 0.20359830744564533}
+{"time": "12:11:08", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 1312.7090199169872, "loss": 0.6656249836087227, "entropy": 0.6475824527442455, "sharp": 0.13085001707077026}
+{"time": "12:13:31", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 1313.5014864820728, "loss": 0.6153121516108513, "entropy": 0.6068851798772812, "sharp": 0.16325515322387218}
+{"time": "12:15:50", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 1313.0722537153513, "loss": 0.5809856466948986, "entropy": 0.6038184612989426, "sharp": 0.16931664012372494}
+{"time": "12:16:43", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5700802206993103, "noul_T": 0.9145001417414256, "noul_auc": 0.7469578572513543, "noul_acc": 0.694, "noul_f1": 0.7642526964560863, "noul_nll": 0.5735895264297723, "noul_ece": 0.06242147034406662, "noul_brier": 0.19545896894415615, "noul_sharp": 0.19358454644680023, "entropy": 0.585162878036499}
+{"time": "12:19:02", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 1269.7326222338827, "loss": 0.5922955237329006, "entropy": 0.6019277051091194, "sharp": 0.17545010056346655}
+{"time": "12:21:21", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 1272.949747008926, "loss": 0.5848625339567661, "entropy": 0.5985335484147072, "sharp": 0.18487405870109797}
+{"time": "12:23:40", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 1277.2290277865238, "loss": 0.5749471448361874, "entropy": 0.591515839099884, "sharp": 0.1749928705394268}
+{"time": "12:25:49", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 1278.0910662636531, "loss": 0.599458247423172, "entropy": 0.6082198359072208, "sharp": 0.17775972373783588}
+{"time": "12:28:08", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 1280.546862199377, "loss": 0.6038360949605703, "entropy": 0.5877368301153183, "sharp": 0.19369044248014688}
+{"time": "12:30:28", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 1282.203162753927, "loss": 0.645409606397152, "entropy": 0.6004403419792652, "sharp": 0.18148325756192207}
+{"time": "12:32:51", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 1285.3505918594265, "loss": 0.5753859505057335, "entropy": 0.576993253082037, "sharp": 0.2144543007016182}
+{"time": "12:35:07", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 1287.0468314145003, "loss": 0.5862238109111786, "entropy": 0.6166245341300964, "sharp": 0.1595198903232813}
+{"time": "12:37:27", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 1288.21820440087, "loss": 0.6268459744751453, "entropy": 0.6173589117825031, "sharp": 0.1567661315202713}
+{"time": "12:39:48", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 1289.9091529291047, "loss": 0.6058636158704758, "entropy": 0.6206076219677925, "sharp": 0.16394857596606016}
+{"time": "12:40:41", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5796672701835632, "noul_T": 0.8995567264912014, "noul_auc": 0.749219422457005, "noul_acc": 0.694, "noul_f1": 0.7454242928452579, "noul_nll": 0.5819897624403239, "noul_ece": 0.08862157684564591, "noul_brier": 0.19909549326109494, "noul_sharp": 0.17905111610889435, "entropy": 0.5956482887268066}
+{"time": "12:42:57", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 1268.2966307299378, "loss": 0.6467385664582253, "entropy": 0.6225861832499504, "sharp": 0.14206313341856003}
+{"time": "12:45:14", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 1269.7030555548956, "loss": 0.6271861083805561, "entropy": 0.6076256223022938, "sharp": 0.17913943901658058}
+{"time": "12:47:31", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 1272.0026171637273, "loss": 0.6073220744729042, "entropy": 0.5926607809960842, "sharp": 0.199371000751853}
+{"time": "12:49:49", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 1273.38029263258, "loss": 0.6169506534934044, "entropy": 0.6040438748896122, "sharp": 0.17781108245253563}
+{"time": "12:52:09", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 1274.8187357491859, "loss": 0.5909030344337225, "entropy": 0.5713061094284058, "sharp": 0.20890312548726797}
+{"time": "12:54:32", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 1277.0459994772002, "loss": 0.5869572814553976, "entropy": 0.6168596483767033, "sharp": 0.16015547327697277}
+{"time": "12:56:47", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 1277.6730344449584, "loss": 0.5926607884466648, "entropy": 0.5775053165853024, "sharp": 0.19470469281077385}
+{"time": "12:59:06", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 1279.0955113740652, "loss": 0.6546709574759007, "entropy": 0.6002534441649914, "sharp": 0.17784468457102776}
+{"time": "13:01:22", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 1280.4001750616071, "loss": 0.6158428266644478, "entropy": 0.6113555543124676, "sharp": 0.16651077009737492}
+{"time": "13:03:36", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 1281.8567880129572, "loss": 0.6407205201685429, "entropy": 0.5882363393902779, "sharp": 0.18219387996941805}
+{"time": "13:04:29", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5683934092521667, "noul_T": 0.8788392789139723, "noul_auc": 0.7553965333918415, "noul_acc": 0.706, "noul_f1": 0.7692307692307693, "noul_nll": 0.5678886045143008, "noul_ece": 0.03653232032060623, "noul_brier": 0.19312630767614167, "noul_sharp": 0.18715476989746094, "entropy": 0.5891085863113403}
+{"time": "13:06:48", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 1267.4422330052319, "loss": 0.5988676398992538, "entropy": 0.6061885617673397, "sharp": 0.17731985170394182}
+{"time": "13:09:01", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 1269.321684114833, "loss": 0.5831476897001266, "entropy": 0.5741516053676605, "sharp": 0.20122596248984337}
+{"time": "13:11:19", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 1270.8275531290656, "loss": 0.5701592639088631, "entropy": 0.5804743841290474, "sharp": 0.1880504535511136}
+{"time": "13:13:43", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 1272.406778692271, "loss": 0.6197319962084293, "entropy": 0.6133416220545769, "sharp": 0.1621306873857975}
+{"time": "13:16:00", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 1273.8615813211204, "loss": 0.5474453419446945, "entropy": 0.5589129030704498, "sharp": 0.21005635429173708}
+{"time": "13:18:18", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 1275.2687671283823, "loss": 0.6575484871864319, "entropy": 0.6032185703516006, "sharp": 0.17446676269173622}
+{"time": "13:20:30", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 1276.1476546162069, "loss": 0.5686032772064209, "entropy": 0.5904342941939831, "sharp": 0.19201643485575914}
+{"time": "13:22:47", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 1277.3211142867349, "loss": 0.6403821893036366, "entropy": 0.611611682921648, "sharp": 0.16759252920746803}
+{"time": "13:25:02", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 1278.3745444494737, "loss": 0.6526653841137886, "entropy": 0.6186433732509613, "sharp": 0.15411525033414364}
+{"time": "13:27:20", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 1279.2439448150637, "loss": 0.5909474194049835, "entropy": 0.5993344224989414, "sharp": 0.179552199319005}
+{"time": "13:28:13", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5694644451141357, "noul_T": 0.8538208289728361, "noul_auc": 0.7537425528683059, "noul_acc": 0.698, "noul_f1": 0.7687595712098009, "noul_nll": 0.5704586481451989, "noul_ece": 0.04483462238311769, "noul_brier": 0.1941659760132406, "noul_sharp": 0.18182502686977386, "entropy": 0.5938192009925842}
+{"time": "13:30:30", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 1268.4058343882562, "loss": 0.5973102487623692, "entropy": 0.6064901202917099, "sharp": 0.16923790611326694}
+{"time": "13:32:55", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 1269.2945266034542, "loss": 0.5875825807452202, "entropy": 0.6064415648579597, "sharp": 0.1745873698964715}
+{"time": "13:35:14", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 1270.5027817026964, "loss": 0.6105660423636436, "entropy": 0.5940721929073334, "sharp": 0.17803674098104239}
+{"time": "13:37:40", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 1271.8971453346776, "loss": 0.6526661776006222, "entropy": 0.6104995980858803, "sharp": 0.1725141555070877}
+{"time": "13:40:00", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 1273.1568116971928, "loss": 0.5957321273162961, "entropy": 0.6131171192973852, "sharp": 0.16349991783499718}
+{"time": "13:42:19", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 1273.9326583053175, "loss": 0.599273931235075, "entropy": 0.5961533561348915, "sharp": 0.1850678864866495}
+{"time": "13:44:40", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 1274.774862787658, "loss": 0.6307419259101152, "entropy": 0.595065962523222, "sharp": 0.1892723347991705}
+{"time": "13:46:57", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 1275.763680304849, "loss": 0.6189596280455589, "entropy": 0.6077393852174282, "sharp": 0.17388429585844278}
+{"time": "13:49:19", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 1276.6555709587387, "loss": 0.5969740636646748, "entropy": 0.6276695020496845, "sharp": 0.14587684534490108}
+{"time": "13:51:36", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 1277.6853635636423, "loss": 0.5773875750601292, "entropy": 0.5876455307006836, "sharp": 0.18344431929290295}
+{"time": "13:52:29", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5720229148864746, "noul_T": 0.8772237590197743, "noul_auc": 0.7529155626065382, "noul_acc": 0.708, "noul_f1": 0.7697160883280757, "noul_nll": 0.5720939783155918, "noul_ece": 0.04635891366004946, "noul_brier": 0.19484523820571684, "noul_sharp": 0.18249200284481049, "entropy": 0.5923282504081726}
+{"time": "13:54:22", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9113125, "tok_per_s": 1248.655911467973, "rows_per_s": 2.307645605151653, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5587899684906006, "noul_T": 0.8700627381643509, "choice_ce": 0.6794756650924683, "choice_T": 1.0459399832418157, "score_ce": 1.0803722143173218, "score_T": 1.0145719661292092, "noul_auc": 0.7453013333333334, "noul_acc": 0.703, "noul_f1": 0.7751703255109765, "noul_nll": 0.5708677803426981, "noul_ece": 0.04532328684628009, "noul_brier": 0.1945894423967694, "noul_sharp": 0.18444940447807312, "entropy": 0.5912659168243408}, "dropped_long": 0, "peak_gib": 18.28459882736206}