pod backup 2026-11-07: e47/S1-E41-FRESH-A050-ts2-syn (0-11)

e47/S1-E41-FRESH-A050-ts2-syn/DONE

@@ -0,0 +1 @@
+2026-11-07 12:24:33

e47/S1-E41-FRESH-A050-ts2-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

e47/S1-E41-FRESH-A050-ts2-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": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "in_proj_qkv",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "in_proj_z",
+    "k_proj",
+    "down_proj",
+    "out_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
+}

e47/S1-E41-FRESH-A050-ts2-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2a37f6c75db1a750f2ae5cb4fd5bf4d1355f96aeab1e5b6c29f72fd1ab4d6f
+size 160486456

e47/S1-E41-FRESH-A050-ts2-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": "0.21.2",
+  "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
+}

e47/S1-E41-FRESH-A050-ts2-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fb1e2a81f895c6f5e572528dae226aabe9ef2c67b2d2e5bd6fe99bf0ad9308
+size 176641832

e47/S1-E41-FRESH-A050-ts2-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  3.602136712288484e-05,
+  -3.6034656659467146e-05,
+  -0.0005132465739734471,
+  -0.0005000782548449934,
+  0.00023872056044638157,
+  0.0010069668060168624,
+  0.0009039922151714563,
+  -0.0006289554294198751,
+  -0.0001256379473488778,
+  -3.250142253818922e-05,
+  -0.00029668823117390275,
+  -1.5538304069195874e-05,
+  -0.0004167128645349294,
+  -0.0003568152606021613,
+  -0.0030627755913883448,
+  -0.002693692222237587,
+  -0.0006337372469715774,
+  -0.0027622010093182325,
+  -0.002746657934039831,
+  -0.0024210112169384956,
+  -0.002261386951431632,
+  -0.002728155115619302,
+  -0.0027325141709297895,
+  -0.002767263213172555
+ ],
+ "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"
+}

e47/S1-E41-FRESH-A050-ts2-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8294846674180748,
+  "choice": 0.8694860597537201,
+  "score": 1.0101587152647862
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.8294846674180748,
+   "ce_before": 0.5641775727272034,
+   "ce_after": 0.5612772107124329
+  },
+  "choice": {
+   "n": 60,
+   "T": 0.8694860597537201,
+   "ce_before": 0.9122971892356873,
+   "ce_after": 0.90777987241745
+  },
+  "score": {
+   "n": 53,
+   "T": 1.0101587152647862,
+   "ce_before": 1.2643471956253052,
+   "ce_after": 1.264316439628601
+  }
+ },
+ "source": "models/e47/S1-E41-FRESH-A050-ts2-syn/ckpt-16000"
+}

e47/S1-E41-FRESH-A050-ts2-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9572e5fb2be36fae6178e20ad8fbd66cb386620384b60bd62f47303bc2c15e
+size 393464

e47/S1-E41-FRESH-A050-ts2-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/e47/S1-E41-FRESH-A050-ts2-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e18/G-d512-n16k",
+  "data_manifest": {
+   "arm": "G-d512-n16k",
+   "name": null,
+   "train_sha256": "ef94315960694ce58bdc6d61b8665b7bf46f4e2996b9e82503e1d17bb87a14b7",
+   "n_train": 16000
+  },
+  "init": "fresh",
+  "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": 2,
+  "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": 9113372,
+  "tok_per_s": 1247.9872287786327,
+  "rows_per_s": 2.3063472994313834,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5641775727272034,
+   "noul_T": 0.8294846674180748,
+   "choice_ce": 0.9122971892356873,
+   "choice_T": 0.8694860597537201,
+   "score_ce": 1.2643471956253052,
+   "score_T": 1.0101587152647862,
+   "noul_auc": 0.7448234666666667,
+   "noul_acc": 0.703,
+   "noul_f1": 0.7744874715261959,
+   "noul_nll": 0.5722413001284004,
+   "noul_ece": 0.041028261542320255,
+   "noul_brier": 0.19485669011917178,
+   "noul_sharp": 0.18037621676921844,
+   "entropy": 0.5968198776245117
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.284047603607178
+ }
+}

e47/S1-E41-FRESH-A050-ts2-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "10:22:51", "event": "start", "data": "data/e18/G-d512-n16k", "data_manifest": {"arm": "G-d512-n16k", "name": null, "train_sha256": "ef94315960694ce58bdc6d61b8665b7bf46f4e2996b9e82503e1d17bb87a14b7", "n_train": 16000}, "init": "fresh", "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": 2, "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": 5.088741779327393}
+{"time": "10:24:59", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 1305.9018496548188, "loss": 0.691706120967865, "entropy": 0.4663626402616501, "sharp": 0.3057635612785816}
+{"time": "10:27:16", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 1309.2114714669626, "loss": 0.6604111455380917, "entropy": 0.4356331080198288, "sharp": 0.3074595779180527}
+{"time": "10:29:34", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 1314.9559165580172, "loss": 0.7477192878723145, "entropy": 0.49719860777258873, "sharp": 0.26375932432711124}
+{"time": "10:31:52", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 1314.1525975530192, "loss": 0.7266354598104954, "entropy": 0.6049996390938759, "sharp": 0.17815707437694073}
+{"time": "10:34:10", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 1317.510310302489, "loss": 0.6935322536155581, "entropy": 0.5806661583483219, "sharp": 0.1954480092972517}
+{"time": "10:36:31", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 1317.9772349513623, "loss": 0.5804760418832302, "entropy": 0.5803508087992668, "sharp": 0.20583777409046888}
+{"time": "10:38:52", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 1318.1052296468351, "loss": 0.7015810422599316, "entropy": 0.6152294799685478, "sharp": 0.16411852277815342}
+{"time": "10:41:04", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 1316.5610449971068, "loss": 0.6192352697253227, "entropy": 0.6205490827560425, "sharp": 0.1506901253014803}
+{"time": "10:43:20", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 1317.2264140330622, "loss": 0.7256080340594053, "entropy": 0.6686967313289642, "sharp": 0.09402436763048172}
+{"time": "10:45:39", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 1316.7680390885057, "loss": 0.7063114680349827, "entropy": 0.5740459579974413, "sharp": 0.20494293794035912}
+{"time": "10:46:32", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.6168292164802551, "noul_T": 1.2444483601561407, "noul_auc": 0.7548395807665694, "noul_acc": 0.67, "noul_f1": 0.6972477064220184, "noul_nll": 0.6059275898933411, "noul_ece": 0.11881969937682155, "noul_brier": 0.2076691348128449, "noul_sharp": 0.19904856383800507, "entropy": 0.5797173976898193}
+{"time": "10:48:49", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 1272.4448587296363, "loss": 0.6203988045454025, "entropy": 0.6530937347561121, "sharp": 0.11549223214387894}
+{"time": "10:51:06", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 1275.8048729546342, "loss": 0.5733261443674564, "entropy": 0.5655853599309921, "sharp": 0.21513287909328938}
+{"time": "10:53:23", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 1278.265946300589, "loss": 0.596600491553545, "entropy": 0.6105527132749557, "sharp": 0.16364438086748123}
+{"time": "10:55:43", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 1281.519207335054, "loss": 0.5962730050086975, "entropy": 0.6358456164598465, "sharp": 0.1385640799999237}
+{"time": "10:58:00", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 1283.368520027682, "loss": 0.6409892188385129, "entropy": 0.6146462261676788, "sharp": 0.16465539671480656}
+{"time": "11:00:13", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 1285.2022377196838, "loss": 0.6909733079373837, "entropy": 0.6204172447323799, "sharp": 0.15698612108826637}
+{"time": "11:02:28", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 1287.1649021856854, "loss": 0.6437761522829533, "entropy": 0.6009132564067841, "sharp": 0.18615136109292507}
+{"time": "11:04:52", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 1289.3479226218642, "loss": 0.5864197388291359, "entropy": 0.6150875985622406, "sharp": 0.15974565036594868}
+{"time": "11:07:16", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 1290.1480205800763, "loss": 0.6092176996171474, "entropy": 0.6109764762222767, "sharp": 0.1752436412498355}
+{"time": "11:09:32", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 1291.6325559026702, "loss": 0.6033225608989596, "entropy": 0.5651012929156423, "sharp": 0.21083917561918497}
+{"time": "11:10:25", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5766955614089966, "noul_T": 0.8916549931924588, "noul_auc": 0.7452026126141331, "noul_acc": 0.702, "noul_f1": 0.7732115677321156, "noul_nll": 0.5773176449388265, "noul_ece": 0.05424701714515687, "noul_brier": 0.19633235458755677, "noul_sharp": 0.1839640736579895, "entropy": 0.5948827266693115}
+{"time": "11:12:43", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 1270.3639488534002, "loss": 0.6028863172978163, "entropy": 0.5854057222604752, "sharp": 0.1894370038062334}
+{"time": "11:15:03", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 1272.3364830524915, "loss": 0.5932706166058779, "entropy": 0.6114447768777609, "sharp": 0.1621617441996932}
+{"time": "11:17:14", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 1273.425202432867, "loss": 0.5894469507038593, "entropy": 0.6024834625422955, "sharp": 0.18454185128211975}
+{"time": "11:19:30", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 1275.02494408029, "loss": 0.6298753991723061, "entropy": 0.5987283140420914, "sharp": 0.17428869381546974}
+{"time": "11:21:48", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 1276.7119829808487, "loss": 0.6126839444041252, "entropy": 0.6217582076787949, "sharp": 0.16031480859965086}
+{"time": "11:24:08", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 1278.5448131297055, "loss": 0.6190742831677198, "entropy": 0.6168005615472794, "sharp": 0.1634927000850439}
+{"time": "11:26:30", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 1280.6585054226207, "loss": 0.6731875967234373, "entropy": 0.6303763724863529, "sharp": 0.15007005725055933}
+{"time": "11:28:47", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 1281.6822579898785, "loss": 0.6279894951730967, "entropy": 0.5950079653412104, "sharp": 0.18054904229938984}
+{"time": "11:31:08", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 1282.8331050555744, "loss": 0.6211401224136353, "entropy": 0.5918001942336559, "sharp": 0.1826269244775176}
+{"time": "11:33:37", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 1284.5728098910627, "loss": 0.5979489423334599, "entropy": 0.5246087908744812, "sharp": 0.2504173368215561}
+{"time": "11:34:30", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5703650712966919, "noul_T": 0.9659830616308503, "noul_auc": 0.7506371200486068, "noul_acc": 0.712, "noul_f1": 0.7784615384615384, "noul_nll": 0.5721544949784875, "noul_ece": 0.07491285258531571, "noul_brier": 0.19463729382408781, "noul_sharp": 0.1986832618713379, "entropy": 0.576422929763794}
+{"time": "11:36:46", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 1269.8208144691662, "loss": 0.6210905872285366, "entropy": 0.6302880048751831, "sharp": 0.15030592493712902}
+{"time": "11:39:10", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 1271.223104379629, "loss": 0.6646069716662169, "entropy": 0.6269971765577793, "sharp": 0.15442555584013462}
+{"time": "11:41:23", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 1272.1812330552602, "loss": 0.6417521554976702, "entropy": 0.6322660930454731, "sharp": 0.1522840540856123}
+{"time": "11:43:44", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 1273.157469975001, "loss": 0.6164010800421238, "entropy": 0.6080444641411304, "sharp": 0.16508333571255207}
+{"time": "11:45:58", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 1273.9712965046417, "loss": 0.6030489820986986, "entropy": 0.578230481594801, "sharp": 0.19573489110916853}
+{"time": "11:48:24", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 1274.978099152549, "loss": 0.6157488152384758, "entropy": 0.6042980030179024, "sharp": 0.17201352026313543}
+{"time": "11:50:47", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 1276.2983294516266, "loss": 0.636914137750864, "entropy": 0.6263012699782848, "sharp": 0.14841398037970066}
+{"time": "11:53:03", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 1277.1857334532158, "loss": 0.6459007672965527, "entropy": 0.6190751045942307, "sharp": 0.1593244317919016}
+{"time": "11:55:24", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 1278.1222026698956, "loss": 0.5894396491348743, "entropy": 0.5856737121939659, "sharp": 0.2072057444602251}
+{"time": "11:57:40", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 1279.2624579094356, "loss": 0.5993246380239725, "entropy": 0.5895623192191124, "sharp": 0.1793825961649418}
+{"time": "11:58:33", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5687310695648193, "noul_T": 0.9467631253106603, "noul_auc": 0.754485156368669, "noul_acc": 0.704, "noul_f1": 0.7737003058103975, "noul_nll": 0.5690494388490915, "noul_ece": 0.05425523459911348, "noul_brier": 0.19355799000753737, "noul_sharp": 0.1959889829158783, "entropy": 0.5782192349433899}
+{"time": "12:00:53", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 1268.8347003532317, "loss": 0.6095119658857584, "entropy": 0.6195128373801708, "sharp": 0.14916683826595545}
+{"time": "12:03:09", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 1269.808553035712, "loss": 0.6113329380750656, "entropy": 0.5734582915902138, "sharp": 0.21371230483055115}
+{"time": "12:05:24", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 1270.7938156685636, "loss": 0.5981698967516422, "entropy": 0.5934148579835892, "sharp": 0.18334950134158134}
+{"time": "12:07:43", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 1271.7874699159668, "loss": 0.6154446909204125, "entropy": 0.5952338585630059, "sharp": 0.17625275813043118}
+{"time": "12:09:55", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 1273.0469073832555, "loss": 0.5899028182029724, "entropy": 0.5717085301876068, "sharp": 0.20410559885203838}
+{"time": "12:12:19", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 1274.1788336919908, "loss": 0.5968035496771336, "entropy": 0.5745440497994423, "sharp": 0.20884536020457745}
+{"time": "12:14:38", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 1274.795047384468, "loss": 0.6407051030546427, "entropy": 0.5952633768320084, "sharp": 0.1920885592699051}
+{"time": "12:16:56", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 1275.3053846424139, "loss": 0.6084408834576607, "entropy": 0.6005065813660622, "sharp": 0.17681691329926252}
+{"time": "12:19:24", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 1276.3881791791962, "loss": 0.5851560495793819, "entropy": 0.6006535701453686, "sharp": 0.18776865489780903}
+{"time": "12:21:47", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 1276.9966495206265, "loss": 0.5679972302168608, "entropy": 0.5856078639626503, "sharp": 0.1913270791992545}
+{"time": "12:22:40", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5731489658355713, "noul_T": 0.8426611128841509, "noul_auc": 0.7530337040725052, "noul_acc": 0.704, "noul_f1": 0.7665615141955836, "noul_nll": 0.5734056477248669, "noul_ece": 0.0687089194059372, "noul_brier": 0.1950730648234985, "noul_sharp": 0.1774381697177887, "entropy": 0.5987728238105774}
+{"time": "12:24:33", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9113372, "tok_per_s": 1247.9872287786327, "rows_per_s": 2.3063472994313834, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5641775727272034, "noul_T": 0.8294846674180748, "choice_ce": 0.9122971892356873, "choice_T": 0.8694860597537201, "score_ce": 1.2643471956253052, "score_T": 1.0101587152647862, "noul_auc": 0.7448234666666667, "noul_acc": 0.703, "noul_f1": 0.7744874715261959, "noul_nll": 0.5722413001284004, "noul_ece": 0.041028261542320255, "noul_brier": 0.19485669011917178, "noul_sharp": 0.18037621676921844, "entropy": 0.5968198776245117}, "dropped_long": 0, "peak_gib": 18.284047603607178}