E39 train-seed checkpoint E39-E18A050-ts2

e39/S1-E39-E18A050-ts2-syn/DONE

@@ -0,0 +1 @@
+2026-10-29 02:02:16

e39/S1-E39-E18A050-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

e39/S1-E39-E18A050-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",
+    "v_proj",
+    "out_proj",
+    "k_proj",
+    "up_proj",
+    "in_proj_qkv",
+    "o_proj",
+    "gate_proj",
+    "in_proj_z",
+    "down_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
+}

e39/S1-E39-E18A050-ts2-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c2b2dfbcd53e15503281221aed328ab15a32825ad92c9698089e3e6cd23319
+size 160486456

e39/S1-E39-E18A050-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
+}

e39/S1-E39-E18A050-ts2-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d114a93d4579339889a17b9b3ce34a7c9c0c925fe54707c58655a8474e0c4f
+size 176641832

e39/S1-E39-E18A050-ts2-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0004128327709622681,
+  -0.0004130994202569127,
+  -0.0024704940151423216,
+  -0.0015079453587532043,
+  -0.0005252839182503521,
+  0.00215359590947628,
+  0.001593436929397285,
+  -0.002544607035815716,
+  -0.00026619917480275035,
+  -0.00017142751312348992,
+  0.0003160844789817929,
+  0.0009166523814201355,
+  0.00017276803555432707,
+  -0.00422685919329524,
+  -0.004658072255551815,
+  -0.005299881100654602,
+  -0.0060327257961034775,
+  -0.00466901296749711,
+  -0.005042471922934055,
+  -0.005305462516844273,
+  -0.004279137123376131,
+  -0.0037368182092905045,
+  -0.00586526608094573,
+  -0.0037092422135174274
+ ],
+ "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"
+}

e39/S1-E39-E18A050-ts2-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8870731843876342,
+  "choice": 1.0079246145468457,
+  "score": 0.9792157687406504
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.8870731843876342,
+   "ce_before": 0.5569424033164978,
+   "ce_after": 0.555738091468811
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0079246145468457,
+   "ce_before": 0.6776580214500427,
+   "ce_after": 0.6776456832885742
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9792157687406504,
+   "ce_before": 1.0686098337173462,
+   "ce_after": 1.0684807300567627
+  }
+ },
+ "source": "models/e39/S1-E39-E18A050-ts2-syn/ckpt-16000"
+}

e39/S1-E39-E18A050-ts2-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2052ef1e09c9d54f49ea1feb92f548e3f138cc158d19848a6cbf2949c122d3
+size 393464

e39/S1-E39-E18A050-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/e39/S1-E39-E18A050-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": "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": 9113372,
+  "tok_per_s": 829.8867287165389,
+  "rows_per_s": 1.5336751620558093,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5569424033164978,
+   "noul_T": 0.8870731843876342,
+   "choice_ce": 0.6776580214500427,
+   "choice_T": 1.0079246145468457,
+   "score_ce": 1.0686098337173462,
+   "score_T": 0.9792157687406504,
+   "noul_auc": 0.7438336,
+   "noul_acc": 0.697,
+   "noul_f1": 0.7720090293453724,
+   "noul_nll": 0.5707269300818443,
+   "noul_ece": 0.044440267279744164,
+   "noul_brier": 0.1946282054827753,
+   "noul_sharp": 0.18865033984184265,
+   "entropy": 0.5869244337081909
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.237416744232178
+ }
+}

e39/S1-E39-E18A050-ts2-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "22:59:13", "event": "start", "data": "data/e18/G-d512-n16k", "data_manifest": {"arm": "G-d512-n16k", "name": null, "train_sha256": "ef94315960694ce58bdc6d61b8665b7bf46f4e2996b9e82503e1d17bb87a14b7", "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": 85.772381067276}
+{"time": "23:02:28", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 860.2784959802675, "loss": 0.5904065705835819, "entropy": 0.6001457683742046, "sharp": 0.18779580015689135}
+{"time": "23:05:54", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 867.3516792898545, "loss": 0.5521498546004295, "entropy": 0.584347315132618, "sharp": 0.2060392200946808}
+{"time": "23:09:22", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 871.3157858625857, "loss": 0.662376169115305, "entropy": 0.6502273976802826, "sharp": 0.12386206537485123}
+{"time": "23:12:48", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 872.822873228751, "loss": 0.6343653425574303, "entropy": 0.5889230296015739, "sharp": 0.19543178100138903}
+{"time": "23:16:16", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 875.6225903936627, "loss": 0.6376594258472323, "entropy": 0.6097306087613106, "sharp": 0.17115321848541498}
+{"time": "23:19:46", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 876.5897099402144, "loss": 0.5787627920508385, "entropy": 0.5766279362142086, "sharp": 0.2136928951367736}
+{"time": "23:23:18", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 876.5900683120467, "loss": 0.6105487048625946, "entropy": 0.6012848764657974, "sharp": 0.18073905818164349}
+{"time": "23:26:35", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 876.5294602251818, "loss": 0.6257423460483551, "entropy": 0.5802933052182198, "sharp": 0.18724028952419758}
+{"time": "23:30:01", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 876.6471180241434, "loss": 0.6091659180819988, "entropy": 0.5959296450018883, "sharp": 0.17678788118064404}
+{"time": "23:33:29", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 876.147248444777, "loss": 0.6346150673925877, "entropy": 0.5998903885483742, "sharp": 0.18167925626039505}
+{"time": "23:34:53", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5733268857002258, "noul_T": 0.9105950250484209, "noul_auc": 0.7484430642520802, "noul_acc": 0.702, "noul_f1": 0.7697063369397218, "noul_nll": 0.5752068930268288, "noul_ece": 0.0685704733133316, "noul_brier": 0.1961616981141351, "noul_sharp": 0.1874876469373703, "entropy": 0.5885365009307861}
+{"time": "23:38:19", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 845.1213307703058, "loss": 0.5950800683349371, "entropy": 0.5766593161970377, "sharp": 0.20460340194404125}
+{"time": "23:41:46", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 847.3569179231279, "loss": 0.5786507073789835, "entropy": 0.5824175886809826, "sharp": 0.19662327878177166}
+{"time": "23:45:11", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 849.4201817954273, "loss": 0.5841627717018127, "entropy": 0.6037322729825974, "sharp": 0.17615177296102047}
+{"time": "23:48:40", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 851.8291431835145, "loss": 0.5882671168074012, "entropy": 0.5692335749045014, "sharp": 0.2015597727149725}
+{"time": "23:52:07", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 853.1491821377567, "loss": 0.6240521837025881, "entropy": 0.6446029879152775, "sharp": 0.1278233900666237}
+{"time": "23:55:25", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 854.5960578068845, "loss": 0.6582621783018112, "entropy": 0.6051281727850437, "sharp": 0.17218546848744154}
+{"time": "23:58:48", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 856.0090497340198, "loss": 0.6041105911135674, "entropy": 0.6029052622616291, "sharp": 0.17953670024871826}
+{"time": "00:02:26", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 857.3834238518513, "loss": 0.5703251250088215, "entropy": 0.5674278289079666, "sharp": 0.2148398719727993}
+{"time": "00:06:00", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 858.3462167370604, "loss": 0.5800369568169117, "entropy": 0.5962209887802601, "sharp": 0.18607338517904282}
+{"time": "00:09:23", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 859.4436749539161, "loss": 0.5975378807634115, "entropy": 0.5896017458289862, "sharp": 0.18879827577620745}
+{"time": "00:10:46", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5801999568939209, "noul_T": 0.8487316041861377, "noul_auc": 0.7415908592260047, "noul_acc": 0.706, "noul_f1": 0.7727975270479135, "noul_nll": 0.5825040051341057, "noul_ece": 0.05490169394016268, "noul_brier": 0.19891301566451444, "noul_sharp": 0.17344988882541656, "entropy": 0.6039418578147888}
+{"time": "00:14:14", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 844.7200969583955, "loss": 0.6182886529713869, "entropy": 0.5532101020216942, "sharp": 0.21661977842450142}
+{"time": "00:17:44", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 845.9779097875746, "loss": 0.5966133009642363, "entropy": 0.5950200036168098, "sharp": 0.1748067606240511}
+{"time": "00:21:00", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 846.8536770085713, "loss": 0.6056977473199368, "entropy": 0.5987323485314846, "sharp": 0.18132195807993412}
+{"time": "00:24:24", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 848.099809081951, "loss": 0.622867040336132, "entropy": 0.5909343846142292, "sharp": 0.18540575727820396}
+{"time": "00:27:50", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 849.4089155100663, "loss": 0.6139448545873165, "entropy": 0.6059908773750067, "sharp": 0.18122399412095547}
+{"time": "00:31:20", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 850.651579620442, "loss": 0.6189445974305272, "entropy": 0.6223938055336475, "sharp": 0.1595883946865797}
+{"time": "00:34:54", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 852.0516484975356, "loss": 0.5909499190747738, "entropy": 0.6187450848519802, "sharp": 0.1667074840515852}
+{"time": "00:38:20", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 852.8232361698856, "loss": 0.6240835469216108, "entropy": 0.5628483965992928, "sharp": 0.20912742242217064}
+{"time": "00:41:51", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 853.6633478749179, "loss": 0.6155784428119659, "entropy": 0.5916723310947418, "sharp": 0.18296675756573677}
+{"time": "00:45:33", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 854.9389191960755, "loss": 0.5917891524732113, "entropy": 0.5432752296328545, "sharp": 0.2357009444385767}
+{"time": "00:46:56", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.57025545835495, "noul_T": 0.9690943048792074, "noul_auc": 0.7486793471840137, "noul_acc": 0.704, "noul_f1": 0.7708978328173375, "noul_nll": 0.5732704076394439, "noul_ece": 0.041020455360412614, "noul_brier": 0.19543132962905407, "noul_sharp": 0.19814172387123108, "entropy": 0.575679361820221}
+{"time": "00:50:19", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 844.8249379133094, "loss": 0.6119859702885151, "entropy": 0.6363243572413921, "sharp": 0.13968249317258596}
+{"time": "00:53:55", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 845.816096542659, "loss": 0.6553883664309978, "entropy": 0.631926292553544, "sharp": 0.14935292396694422}
+{"time": "00:57:15", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 846.5576862144552, "loss": 0.6358033120632172, "entropy": 0.6445981897413731, "sharp": 0.13239913992583752}
+{"time": "01:00:48", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 847.193144092736, "loss": 0.6122714914381504, "entropy": 0.6060046181082726, "sharp": 0.1621042676270008}
+{"time": "01:04:08", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 847.8075429058913, "loss": 0.6026419177651405, "entropy": 0.5717063806951046, "sharp": 0.20349664613604546}
+{"time": "01:07:46", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 848.585421086018, "loss": 0.5967589318752289, "entropy": 0.5978830121457577, "sharp": 0.18065611831843853}
+{"time": "01:11:21", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 849.5256804547968, "loss": 0.6255998909473419, "entropy": 0.6308816224336624, "sharp": 0.14216842222958803}
+{"time": "01:14:44", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 850.1998818803195, "loss": 0.6312067732214928, "entropy": 0.6062726639211178, "sharp": 0.1699300715699792}
+{"time": "01:18:15", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 850.8603980425981, "loss": 0.5874543786048889, "entropy": 0.606404535472393, "sharp": 0.18429170176386833}
+{"time": "01:21:40", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 851.5712003253174, "loss": 0.5979329328984022, "entropy": 0.5932168737053871, "sharp": 0.17839252203702927}
+{"time": "01:23:03", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5684962272644043, "noul_T": 0.9132828415235538, "noul_auc": 0.7502658182984254, "noul_acc": 0.7, "noul_f1": 0.7713414634146342, "noul_nll": 0.5714154194742441, "noul_ece": 0.042865205347538, "noul_brier": 0.19462698160123496, "noul_sharp": 0.19235500693321228, "entropy": 0.583593487739563}
+{"time": "01:26:34", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 844.3198920216105, "loss": 0.6071807295084, "entropy": 0.6119209341704845, "sharp": 0.15702117327600718}
+{"time": "01:29:57", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 844.953877353298, "loss": 0.5853054448962212, "entropy": 0.5977483503520489, "sharp": 0.18742433190345764}
+{"time": "01:33:20", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 845.6147680143254, "loss": 0.5953792221844196, "entropy": 0.5812115296721458, "sharp": 0.20000283978879452}
+{"time": "01:36:50", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 846.2875864420955, "loss": 0.6152813471853733, "entropy": 0.6036562183871865, "sharp": 0.16495558340102434}
+{"time": "01:40:08", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 847.171201957997, "loss": 0.5533651784062386, "entropy": 0.5729457587003708, "sharp": 0.2042957805097103}
+{"time": "01:43:43", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 847.9477469863457, "loss": 0.5966353118419647, "entropy": 0.57181491330266, "sharp": 0.21303782984614372}
+{"time": "01:47:12", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 848.4098408799634, "loss": 0.6178200785070658, "entropy": 0.5907506495714188, "sharp": 0.1975764213129878}
+{"time": "01:50:38", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 848.8593935220003, "loss": 0.5984763763844967, "entropy": 0.6100232377648354, "sharp": 0.16376746632158756}
+{"time": "01:54:20", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 849.5728836753635, "loss": 0.5813979618251324, "entropy": 0.6033659875392914, "sharp": 0.1856688242405653}
+{"time": "01:57:54", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 850.0551374641742, "loss": 0.565053591504693, "entropy": 0.5739997830241919, "sharp": 0.1982389148324728}
+{"time": "01:59:18", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5703473687171936, "noul_T": 0.8895948803445588, "noul_auc": 0.7495738468549055, "noul_acc": 0.696, "noul_f1": 0.7617554858934169, "noul_nll": 0.573013239055872, "noul_ece": 0.05378362423181533, "noul_brier": 0.19531775836527096, "noul_sharp": 0.18609628081321716, "entropy": 0.5888926386833191}
+{"time": "02:02:16", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9113372, "tok_per_s": 829.8867287165389, "rows_per_s": 1.5336751620558093, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5569424033164978, "noul_T": 0.8870731843876342, "choice_ce": 0.6776580214500427, "choice_T": 1.0079246145468457, "score_ce": 1.0686098337173462, "score_T": 0.9792157687406504, "noul_auc": 0.7438336, "noul_acc": 0.697, "noul_f1": 0.7720090293453724, "noul_nll": 0.5707269300818443, "noul_ece": 0.044440267279744164, "noul_brier": 0.1946282054827753, "noul_sharp": 0.18865033984184265, "entropy": 0.5869244337081909}, "dropped_long": 0, "peak_gib": 18.237416744232178}