pod backup 2026-11-07: e48/S1-E45-SHR-ts2-syn (0-11)

e48/S1-E45-SHR-ts2-syn/DONE

@@ -0,0 +1 @@
+2026-11-08 13:47:06

e48/S1-E45-SHR-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

e48/S1-E45-SHR-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": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "out_proj",
+    "gate_proj",
+    "in_proj_z",
+    "up_proj",
+    "v_proj",
+    "in_proj_qkv"
+  ],
+  "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-E45-SHR-ts2-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6344158a974a8aca43e9377f9152efc1c30f744bdba93b67a1dcf7de3304a3
+size 160486456

e48/S1-E45-SHR-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": "0.21.0",
+  "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-E45-SHR-ts2-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586095e250e5d541c96c43c11453335d94c035fe330ab4899d398409698f4358
+size 176641832

e48/S1-E45-SHR-ts2-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0003226109256502241,
+  -0.0003228721325285733,
+  -0.002549648517742753,
+  -0.001649458077736199,
+  -0.00045402516843751073,
+  0.0019588693976402283,
+  0.0013414487475529313,
+  -0.002581274136900902,
+  -0.0005953078507445753,
+  -0.00044696227996610105,
+  0.00018099023145623505,
+  0.0006968982052057981,
+  0.0001654758962104097,
+  -0.0038800914771854877,
+  -0.004674598574638367,
+  -0.0051280427724123,
+  -0.005878433585166931,
+  -0.004407898988574743,
+  -0.004958983510732651,
+  -0.005060262978076935,
+  -0.004094369243830442,
+  -0.0034768215846270323,
+  -0.0056503876112401485,
+  -0.0035318390000611544
+ ],
+ "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-E45-SHR-ts2-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.977145938661508,
+  "choice": 1.0341424290580548,
+  "score": 1.017104685022851
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.977145938661508,
+   "ce_before": 0.5502278804779053,
+   "ce_after": 0.5501790046691895
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0341424290580548,
+   "ce_before": 0.6674243807792664,
+   "ce_after": 0.6671715974807739
+  },
+  "score": {
+   "n": 53,
+   "T": 1.017104685022851,
+   "ce_before": 1.049790620803833,
+   "ce_after": 1.049707055091858
+  }
+ },
+ "source": "models/e48/S1-E45-SHR-ts2-syn/ckpt-16000"
+}

e48/S1-E45-SHR-ts2-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b67a2f81f1a5fe81c104c8cbbb6a0452eb99c98b4b57980f52dcd46305b45e
+size 393464

e48/S1-E45-SHR-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/e48/S1-E45-SHR-ts2-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e45/E45-SHR",
+  "data_manifest": {
+   "arm": "E45-SHR",
+   "name": null,
+   "train_sha256": "cfe452b00b8ac702c42580427823a8e4bf112271713c1fea190e1f3214bb6fbf",
+   "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": 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": 9113125,
+  "tok_per_s": 1248.6584813521679,
+  "rows_per_s": 2.3076503546395166,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5502278804779053,
+   "noul_T": 0.977145938661508,
+   "choice_ce": 0.6674243807792664,
+   "choice_T": 1.0341424290580548,
+   "score_ce": 1.049790620803833,
+   "score_T": 1.017104685022851,
+   "noul_auc": 0.74624,
+   "noul_acc": 0.703,
+   "noul_f1": 0.7778608825729244,
+   "noul_nll": 0.5659570508361794,
+   "noul_ece": 0.028464608892798424,
+   "noul_brier": 0.1935996919007017,
+   "noul_sharp": 0.20450927317142487,
+   "entropy": 0.5633537173271179
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.284047603607178
+ }
+}

e48/S1-E45-SHR-ts2-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "11:45:28", "event": "start", "data": "data/e45/E45-SHR", "data_manifest": {"arm": "E45-SHR", "name": null, "train_sha256": "cfe452b00b8ac702c42580427823a8e4bf112271713c1fea190e1f3214bb6fbf", "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": 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": 5.489486217498779}
+{"time": "11:47:36", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 1306.2827371079818, "loss": 0.5779560226947069, "entropy": 0.5972211211919785, "sharp": 0.1828789236024022}
+{"time": "11:49:53", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 1309.562776589739, "loss": 0.5918976962566376, "entropy": 0.5128966942429543, "sharp": 0.25373134203255177}
+{"time": "11:52:11", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 1314.0902283430964, "loss": 0.6611015200614929, "entropy": 0.502440445125103, "sharp": 0.26034892350435257}
+{"time": "11:54:29", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 1313.8959236032015, "loss": 0.6087837256491184, "entropy": 0.6435384526848793, "sharp": 0.12757657002657652}
+{"time": "11:56:47", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 1317.3852409472577, "loss": 0.6958373007364571, "entropy": 0.5702852681279182, "sharp": 0.20004544779658318}
+{"time": "11:59:08", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 1318.0716528937783, "loss": 0.5564008429646492, "entropy": 0.5703400559723377, "sharp": 0.2149465624243021}
+{"time": "12:01:29", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 1318.1805184424024, "loss": 0.6478497236967087, "entropy": 0.5994223803281784, "sharp": 0.17759130150079727}
+{"time": "12:03:41", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 1317.1128034225085, "loss": 0.6200725436210632, "entropy": 0.5929625295102596, "sharp": 0.17519820667803288}
+{"time": "12:05:57", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 1317.839328884959, "loss": 0.5843910463154316, "entropy": 0.5426483005285263, "sharp": 0.22236247174441814}
+{"time": "12:08:15", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 1317.5688821316226, "loss": 0.6754228733479977, "entropy": 0.587371077388525, "sharp": 0.1956010553985834}
+{"time": "12:09:08", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5838049650192261, "noul_T": 1.0244516738090506, "noul_auc": 0.7472954042969738, "noul_acc": 0.668, "noul_f1": 0.7756756756756756, "noul_nll": 0.5895267758518458, "noul_ece": 0.08451174271106718, "noul_brier": 0.2034480588256419, "noul_sharp": 0.19818678498268127, "entropy": 0.579684853553772}
+{"time": "12:11:25", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 1273.0896953609245, "loss": 0.5590550377964973, "entropy": 0.5524555929005146, "sharp": 0.23047280311584473}
+{"time": "12:13:43", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 1276.3894330450237, "loss": 0.5630269907414913, "entropy": 0.5767222158610821, "sharp": 0.20284084044396877}
+{"time": "12:15:59", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 1279.2339459639434, "loss": 0.5625507161021233, "entropy": 0.5688758529722691, "sharp": 0.19719396345317364}
+{"time": "12:18:18", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 1282.5268826674514, "loss": 0.5531667629256845, "entropy": 0.5754088200628757, "sharp": 0.20005045272409916}
+{"time": "12:20:35", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 1284.538539277265, "loss": 0.6243442259728909, "entropy": 0.6261199116706848, "sharp": 0.15190929174423218}
+{"time": "12:22:48", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 1286.344228329461, "loss": 0.6510811150074005, "entropy": 0.5487701259553432, "sharp": 0.22318689711391926}
+{"time": "12:25:03", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 1288.3871538899552, "loss": 0.6068466678261757, "entropy": 0.5941141545772552, "sharp": 0.18092134408652782}
+{"time": "12:27:27", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 1290.5511868140325, "loss": 0.5454539582133293, "entropy": 0.5546750780194998, "sharp": 0.22009551525115967}
+{"time": "12:29:51", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 1291.4951174430118, "loss": 0.5393228009343147, "entropy": 0.5668078847229481, "sharp": 0.21086471527814865}
+{"time": "12:32:06", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 1292.9359173950409, "loss": 0.6118870540522039, "entropy": 0.5173011834267527, "sharp": 0.24216154869645834}
+{"time": "12:32:59", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.571336567401886, "noul_T": 1.0335329184654503, "noul_auc": 0.7439536885453409, "noul_acc": 0.694, "noul_f1": 0.7719821162444114, "noul_nll": 0.5767605068534613, "noul_ece": 0.0390326148867607, "noul_brier": 0.1971811237513062, "noul_sharp": 0.20874381065368652, "entropy": 0.565443754196167}
+{"time": "12:35:17", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 1271.6137458629787, "loss": 0.5891436645761132, "entropy": 0.59375811368227, "sharp": 0.1867652665823698}
+{"time": "12:37:37", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 1273.5017448144852, "loss": 0.5690224505960941, "entropy": 0.5516878850758076, "sharp": 0.21881656162440777}
+{"time": "12:39:48", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 1274.5940695229333, "loss": 0.5640614870935678, "entropy": 0.6094758715480566, "sharp": 0.17661143094301224}
+{"time": "12:42:04", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 1276.2085135795119, "loss": 0.6162640228867531, "entropy": 0.5513066239655018, "sharp": 0.2124958299100399}
+{"time": "12:44:22", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 1277.9027385875318, "loss": 0.5994530264288187, "entropy": 0.583844717592001, "sharp": 0.1956328246742487}
+{"time": "12:46:41", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 1279.736829116702, "loss": 0.6147327506914735, "entropy": 0.6382472366094589, "sharp": 0.14364170655608177}
+{"time": "12:49:04", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 1281.8505013085016, "loss": 0.5796574652194977, "entropy": 0.5921352449804544, "sharp": 0.1908828178420663}
+{"time": "12:51:21", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 1282.8471816882616, "loss": 0.6017404831945896, "entropy": 0.527816092595458, "sharp": 0.21937421709299088}
+{"time": "12:53:42", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 1283.9423899598246, "loss": 0.5982999168336391, "entropy": 0.5612997710704803, "sharp": 0.19851733092218637}
+{"time": "12:56:10", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 1285.6515037666884, "loss": 0.5708698891103268, "entropy": 0.5469984337687492, "sharp": 0.2222980447113514}
+{"time": "12:57:03", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5716783404350281, "noul_T": 1.017674384216196, "noul_auc": 0.7481561492633035, "noul_acc": 0.688, "noul_f1": 0.745928338762215, "noul_nll": 0.5771844801884145, "noul_ece": 0.047513586461544036, "noul_brier": 0.19775144040382964, "noul_sharp": 0.19858571887016296, "entropy": 0.5688638091087341}
+{"time": "12:59:19", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 1270.8255721281541, "loss": 0.6173609122633934, "entropy": 0.6071245893836021, "sharp": 0.17640941217541695}
+{"time": "13:01:43", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 1272.1875810950687, "loss": 0.6403572987765074, "entropy": 0.6369378212839365, "sharp": 0.14248894155025482}
+{"time": "13:03:56", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 1273.1355539426188, "loss": 0.625283433124423, "entropy": 0.6183253601193428, "sharp": 0.16555840708315372}
+{"time": "13:06:18", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 1274.1082448976085, "loss": 0.5698150284588337, "entropy": 0.5783747173845768, "sharp": 0.17898514866828918}
+{"time": "13:08:31", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 1274.9387818234386, "loss": 0.5766518097370863, "entropy": 0.5393787436187267, "sharp": 0.22143486235290766}
+{"time": "13:10:57", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 1275.902789764707, "loss": 0.5711328368633986, "entropy": 0.5702307522296906, "sharp": 0.19998709950596094}
+{"time": "13:13:21", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 1277.1973745189155, "loss": 0.6025883704423904, "entropy": 0.6228478439152241, "sharp": 0.1554734194651246}
+{"time": "13:15:37", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 1278.0114418941494, "loss": 0.6166631206870079, "entropy": 0.5907093212008476, "sharp": 0.1834904095157981}
+{"time": "13:17:58", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 1278.9247871999264, "loss": 0.5425717998296022, "entropy": 0.5875661000609398, "sharp": 0.19636143185198307}
+{"time": "13:20:13", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 1280.019621739366, "loss": 0.575111510232091, "entropy": 0.584935562685132, "sharp": 0.18327482603490353}
+{"time": "13:21:06", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5638988018035889, "noul_T": 1.009535014513792, "noul_auc": 0.7477004607517173, "noul_acc": 0.696, "noul_f1": 0.7625, "noul_nll": 0.5705434475280344, "noul_ece": 0.04709856867790221, "noul_brier": 0.19543233860588935, "noul_sharp": 0.20624502003192902, "entropy": 0.5623263716697693}
+{"time": "13:23:27", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 1269.5501086348586, "loss": 0.5826502544805408, "entropy": 0.5819834508001804, "sharp": 0.18406200967729092}
+{"time": "13:25:42", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 1270.5193371771106, "loss": 0.5525868572294712, "entropy": 0.5684127807617188, "sharp": 0.21896393597126007}
+{"time": "13:27:57", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 1271.5724026145767, "loss": 0.5775307267904282, "entropy": 0.570567287504673, "sharp": 0.20518899336457253}
+{"time": "13:30:16", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 1272.5617415701804, "loss": 0.5894519214052707, "entropy": 0.5678984858095646, "sharp": 0.19475631415843964}
+{"time": "13:32:29", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 1273.8112268266827, "loss": 0.5118877794593573, "entropy": 0.5373466685414314, "sharp": 0.22928067669272423}
+{"time": "13:34:52", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 1274.9436606566185, "loss": 0.6018953584134579, "entropy": 0.5395802855491638, "sharp": 0.2370236162096262}
+{"time": "13:37:11", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 1275.5460107896547, "loss": 0.5929131973534822, "entropy": 0.5676108151674271, "sharp": 0.2165010180324316}
+{"time": "13:39:29", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 1276.064174087411, "loss": 0.5673181749880314, "entropy": 0.588447205722332, "sharp": 0.18172448873519897}
+{"time": "13:41:57", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 1277.1354154015114, "loss": 0.5596493054181337, "entropy": 0.5981283858418465, "sharp": 0.18586417101323605}
+{"time": "13:44:20", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 1277.7148366530178, "loss": 0.5292575061321259, "entropy": 0.549072815105319, "sharp": 0.20398984849452972}
+{"time": "13:45:13", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5635631084442139, "noul_T": 0.9971384652650569, "noul_auc": 0.7471266307741641, "noul_acc": 0.698, "noul_f1": 0.7651632970451011, "noul_nll": 0.5705361589984969, "noul_ece": 0.041285112082958215, "noul_brier": 0.19551043057396186, "noul_sharp": 0.20273691415786743, "entropy": 0.5641064643859863}
+{"time": "13:47:06", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9113125, "tok_per_s": 1248.6584813521679, "rows_per_s": 2.3076503546395166, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5502278804779053, "noul_T": 0.977145938661508, "choice_ce": 0.6674243807792664, "choice_T": 1.0341424290580548, "score_ce": 1.049790620803833, "score_T": 1.017104685022851, "noul_auc": 0.74624, "noul_acc": 0.703, "noul_f1": 0.7778608825729244, "noul_nll": 0.5659570508361794, "noul_ece": 0.028464608892798424, "noul_brier": 0.1935996919007017, "noul_sharp": 0.20450927317142487, "entropy": 0.5633537173271179}, "dropped_long": 0, "peak_gib": 18.284047603607178}