E39 train-seed checkpoint E39-E18A100-ts1

e39/S1-E39-E18A100-ts1-syn/DONE

@@ -0,0 +1 @@
+2026-10-27 21:17:36

e39/S1-E39-E18A100-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

e39/S1-E39-E18A100-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": [
+    "q_proj",
+    "in_proj_qkv",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "in_proj_z",
+    "out_proj",
+    "o_proj",
+    "down_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-E18A100-ts1-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff1dd8ec3413e44da3d9a599a4d277448ee5750bcd85603c13d7940193186e5
+size 160486456

e39/S1-E39-E18A100-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
+}

e39/S1-E39-E18A100-ts1-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e088c0a152f356d6fb185b92829ee95321a117904f6d1899bbe892b14e259eba
+size 176641832

e39/S1-E39-E18A100-ts1-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00037086580414325,
+  -0.00037112674908712506,
+  -0.0019014269346371293,
+  -0.0015613341238349676,
+  -0.0005909883766435087,
+  0.001930331694893539,
+  0.0014496369985863566,
+  -0.0026189591735601425,
+  -0.00014390263822861016,
+  -0.00035884269163943827,
+  0.00020864205725956708,
+  0.00024170539109036326,
+  -3.842970545520075e-05,
+  -0.00345805287361145,
+  -0.004069515969604254,
+  -0.005089406855404377,
+  -0.00596114294603467,
+  -0.00435794098302722,
+  -0.0049338010139763355,
+  -0.004981022793799639,
+  -0.003968661185353994,
+  -0.003390820696949959,
+  -0.005691491067409515,
+  -0.00348133547231555
+ ],
+ "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-E18A100-ts1-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.9783217562563435,
+  "choice": 1.1098564219074363,
+  "score": 1.005318578069763
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.9783217562563435,
+   "ce_before": 0.5498384237289429,
+   "ce_after": 0.5497946739196777
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.1098564219074363,
+   "ce_before": 0.6782203316688538,
+   "ce_after": 0.6757283806800842
+  },
+  "score": {
+   "n": 53,
+   "T": 1.005318578069763,
+   "ce_before": 1.054585576057434,
+   "ce_after": 1.0545780658721924
+  }
+ },
+ "source": "models/e39/S1-E39-E18A100-ts1-syn/ckpt-16000"
+}

e39/S1-E39-E18A100-ts1-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e857cd0427e3665d65bbe1e741bbb97afe79d10498a2079e9daed251ab5e8686
+size 393464

e39/S1-E39-E18A100-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/e39/S1-E39-E18A100-ts1-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e18/G-d512-n16k-a100",
+  "data_manifest": {
+   "arm": "G-d512-n16k-a100",
+   "name": null,
+   "train_sha256": "e68e935b88943ba54ed4296ecedd5f5b36a7b9f114cd4d203c4f67b6ff70b912",
+   "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": 9113372,
+  "tok_per_s": 827.6340625625323,
+  "rows_per_s": 1.5295121143466355,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5498384237289429,
+   "noul_T": 0.9783217562563435,
+   "choice_ce": 0.6782203316688538,
+   "choice_T": 1.1098564219074363,
+   "score_ce": 1.054585576057434,
+   "score_T": 1.005318578069763,
+   "noul_auc": 0.7478229333333333,
+   "noul_acc": 0.703,
+   "noul_f1": 0.779510022271715,
+   "noul_nll": 0.5655421125572174,
+   "noul_ece": 0.04479948242008685,
+   "noul_brier": 0.19314745050444793,
+   "noul_sharp": 0.20572781562805176,
+   "entropy": 0.5626664757728577
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.23796796798706
+ }
+}

e39/S1-E39-E18A100-ts1-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "18:14:03", "event": "start", "data": "data/e18/G-d512-n16k-a100", "data_manifest": {"arm": "G-d512-n16k-a100", "name": null, "train_sha256": "e68e935b88943ba54ed4296ecedd5f5b36a7b9f114cd4d203c4f67b6ff70b912", "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": 127.51410341262817}
+{"time": "18:17:53", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 750.719838997514, "loss": 0.6023161076009274, "entropy": 0.5984031707048416, "sharp": 0.1845601536333561}
+{"time": "18:21:25", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 810.9287236806608, "loss": 0.5695023564621806, "entropy": 0.5644015111029148, "sharp": 0.21879029367119074}
+{"time": "18:24:55", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 832.3063598134345, "loss": 0.6198867857456207, "entropy": 0.5584977306425571, "sharp": 0.19812524877488613}
+{"time": "18:28:32", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 842.6705540062467, "loss": 0.5891514085233212, "entropy": 0.6218276061117649, "sharp": 0.14614203572273254}
+{"time": "18:32:03", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 850.877786763488, "loss": 0.6580079440027475, "entropy": 0.6300558894872665, "sharp": 0.14559152629226446}
+{"time": "18:35:35", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 856.1820309020325, "loss": 0.6339094042778015, "entropy": 0.561862550675869, "sharp": 0.2073008008301258}
+{"time": "18:38:51", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 859.911781700058, "loss": 0.5557527989149094, "entropy": 0.5934514366090298, "sharp": 0.1891843630000949}
+{"time": "18:42:09", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 860.7933679637788, "loss": 0.6812712475657463, "entropy": 0.645719837397337, "sharp": 0.1306037027388811}
+{"time": "18:45:42", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 863.2771868413819, "loss": 0.6107982769608498, "entropy": 0.5773956552147865, "sharp": 0.19100264087319374}
+{"time": "18:49:10", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 864.5506159225941, "loss": 0.5733766593039036, "entropy": 0.5968808978796005, "sharp": 0.17819138430058956}
+{"time": "18:50:33", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.571365475654602, "noul_T": 0.9852940103687133, "noul_auc": 0.7424347268400533, "noul_acc": 0.7, "noul_f1": 0.7819767441860465, "noul_nll": 0.5808716639876366, "noul_ece": 0.0879187377691269, "noul_brier": 0.1988580925817995, "noul_sharp": 0.200912743806839, "entropy": 0.5740675926208496}
+{"time": "18:54:02", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 835.7299453159576, "loss": 0.5701996628195047, "entropy": 0.5850622765719891, "sharp": 0.19073969684541225}
+{"time": "18:57:30", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 838.5129596317374, "loss": 0.5814780816435814, "entropy": 0.5942019484937191, "sharp": 0.18845049943774939}
+{"time": "19:01:00", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 841.8535978898258, "loss": 0.5504919169470668, "entropy": 0.6032420452684164, "sharp": 0.15346681606024504}
+{"time": "19:04:13", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 843.0608557530649, "loss": 0.5809876564890146, "entropy": 0.5804935209453106, "sharp": 0.1971818096935749}
+{"time": "19:07:43", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 844.8389064215471, "loss": 0.610666124150157, "entropy": 0.5905049070715904, "sharp": 0.18975581787526608}
+{"time": "19:11:15", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 846.3315645234032, "loss": 0.611492995172739, "entropy": 0.5635202042758465, "sharp": 0.21587246097624302}
+{"time": "19:14:51", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 848.3747071120315, "loss": 0.5349596068263054, "entropy": 0.551909364759922, "sharp": 0.22666879557073116}
+{"time": "19:18:15", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 850.1128032026509, "loss": 0.5889500938355923, "entropy": 0.6140460949391127, "sharp": 0.15293854847550392}
+{"time": "19:21:45", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 851.2074445619955, "loss": 0.6364097259938717, "entropy": 0.5499739516526461, "sharp": 0.22248796932399273}
+{"time": "19:25:15", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 852.8867821844661, "loss": 0.5762711055576801, "entropy": 0.5937438532710075, "sharp": 0.19227267988026142}
+{"time": "19:26:38", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5871204733848572, "noul_T": 1.1306051612418035, "noul_auc": 0.7440718300113078, "noul_acc": 0.696, "noul_f1": 0.7466666666666667, "noul_nll": 0.5915634658411145, "noul_ece": 0.0716569454073906, "noul_brier": 0.2026174958749732, "noul_sharp": 0.2094544917345047, "entropy": 0.5645214915275574}
+{"time": "19:30:03", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 838.2950179022017, "loss": 0.6457127034664154, "entropy": 0.58865000680089, "sharp": 0.18188841454684734}
+{"time": "19:33:28", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 839.6518356609223, "loss": 0.6130643039941788, "entropy": 0.6360563226044178, "sharp": 0.1428264044225216}
+{"time": "19:36:55", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 841.2729653716744, "loss": 0.5954667869955301, "entropy": 0.5820419322699308, "sharp": 0.19625080935657024}
+{"time": "19:40:21", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 842.4718814379167, "loss": 0.6053309962153435, "entropy": 0.5529953520745039, "sharp": 0.2241386454552412}
+{"time": "19:43:51", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 843.6361451555294, "loss": 0.5687351915985346, "entropy": 0.5902106054127216, "sharp": 0.18646744079887867}
+{"time": "19:47:27", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 845.3562481903004, "loss": 0.5684653464704752, "entropy": 0.5711917169392109, "sharp": 0.2010222002863884}
+{"time": "19:50:48", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 846.0016271781798, "loss": 0.560521338135004, "entropy": 0.5800472125411034, "sharp": 0.1898464784026146}
+{"time": "19:54:18", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 847.039253374866, "loss": 0.6474857144057751, "entropy": 0.5904519744217396, "sharp": 0.1822422333061695}
+{"time": "19:57:42", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 847.9882164991952, "loss": 0.5825797859579325, "entropy": 0.5952294655144215, "sharp": 0.17776340804994106}
+{"time": "20:01:05", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 848.8953524830706, "loss": 0.6413857117295265, "entropy": 0.5518455654382706, "sharp": 0.21414082683622837}
+{"time": "20:02:28", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5626042485237122, "noul_T": 1.0754327134618773, "noul_auc": 0.753708798163744, "noul_acc": 0.696, "noul_f1": 0.7744807121661721, "noul_nll": 0.5664122315086424, "noul_ece": 0.03575270175933839, "noul_brier": 0.1937321856736026, "noul_sharp": 0.22043243050575256, "entropy": 0.5485244989395142}
+{"time": "20:05:58", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 839.0197150623225, "loss": 0.6136984527111053, "entropy": 0.5985273905098438, "sharp": 0.18140683509409428}
+{"time": "20:09:19", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 840.2404149577467, "loss": 0.550676129758358, "entropy": 0.5377001911401749, "sharp": 0.21572289615869522}
+{"time": "20:12:45", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 841.4183726916838, "loss": 0.5305672101676464, "entropy": 0.5622280426323414, "sharp": 0.19305559433996677}
+{"time": "20:16:21", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 842.6452051335475, "loss": 0.6160295791924, "entropy": 0.5603121034801006, "sharp": 0.2012714110314846}
+{"time": "20:19:48", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 843.6824205343846, "loss": 0.5229029860347509, "entropy": 0.5595130100846291, "sharp": 0.20582914724946022}
+{"time": "20:23:14", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 844.7317171070208, "loss": 0.6560404412448406, "entropy": 0.5750383175909519, "sharp": 0.19762952625751495}
+{"time": "20:26:33", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 845.4529329628481, "loss": 0.5476043671369553, "entropy": 0.546930655837059, "sharp": 0.22458686213940382}
+{"time": "20:29:59", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 846.3777327414912, "loss": 0.624289732426405, "entropy": 0.6143895387649536, "sharp": 0.16962487250566483}
+{"time": "20:33:20", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 847.237457540468, "loss": 0.6649070307612419, "entropy": 0.6072584241628647, "sharp": 0.1687420140951872}
+{"time": "20:36:48", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 847.9245483596861, "loss": 0.5515025109052658, "entropy": 0.5709206089377403, "sharp": 0.21045234985649586}
+{"time": "20:38:11", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5620757937431335, "noul_T": 0.9683943061556367, "noul_auc": 0.7512109500261598, "noul_acc": 0.712, "noul_f1": 0.7784615384615384, "noul_nll": 0.5668388909623027, "noul_ece": 0.05230886512994766, "noul_brier": 0.1936771763058299, "noul_sharp": 0.20258867740631104, "entropy": 0.5677476525306702}
+{"time": "20:41:36", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 840.5399307464603, "loss": 0.5968423187732697, "entropy": 0.5905477814376354, "sharp": 0.18528656754642725}
+{"time": "20:45:13", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 841.3357921444739, "loss": 0.5331993214786053, "entropy": 0.5674544647336006, "sharp": 0.21184590086340904}
+{"time": "20:48:41", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 842.3486006689151, "loss": 0.5863401032984257, "entropy": 0.58509261906147, "sharp": 0.18916013184934855}
+{"time": "20:52:18", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 843.4468066809073, "loss": 0.6694341227412224, "entropy": 0.5947818495333195, "sharp": 0.18867262359708548}
+{"time": "20:55:49", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 844.3182953267985, "loss": 0.6030524843372405, "entropy": 0.5999331902712584, "sharp": 0.17722808383405209}
+{"time": "20:59:17", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 844.978336474818, "loss": 0.5859084390103817, "entropy": 0.5759350918233395, "sharp": 0.20073925517499447}
+{"time": "21:02:49", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 845.6385710721066, "loss": 0.6102757956832647, "entropy": 0.57953742146492, "sharp": 0.2006380744278431}
+{"time": "21:06:14", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 846.3686105831997, "loss": 0.5835025738924742, "entropy": 0.5854384824633598, "sharp": 0.19495875295251608}
+{"time": "21:09:47", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 847.0584538405265, "loss": 0.580293245613575, "entropy": 0.6035159081220627, "sharp": 0.1735741477459669}
+{"time": "21:13:13", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 847.7724245926123, "loss": 0.535621203482151, "entropy": 0.5555501654744148, "sharp": 0.20442692190408707}
+{"time": "21:14:37", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5630671977996826, "noul_T": 1.0043145982537256, "noul_auc": 0.7505864879917638, "noul_acc": 0.71, "noul_f1": 0.7772657450076805, "noul_nll": 0.5674639673009515, "noul_ece": 0.05479300147294997, "noul_brier": 0.19391193835914353, "noul_sharp": 0.2046908736228943, "entropy": 0.5622748136520386}
+{"time": "21:17:36", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9113372, "tok_per_s": 827.6340625625323, "rows_per_s": 1.5295121143466355, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5498384237289429, "noul_T": 0.9783217562563435, "choice_ce": 0.6782203316688538, "choice_T": 1.1098564219074363, "score_ce": 1.054585576057434, "score_T": 1.005318578069763, "noul_auc": 0.7478229333333333, "noul_acc": 0.703, "noul_f1": 0.779510022271715, "noul_nll": 0.5655421125572174, "noul_ece": 0.04479948242008685, "noul_brier": 0.19314745050444793, "noul_sharp": 0.20572781562805176, "entropy": 0.5626664757728577}, "dropped_long": 0, "peak_gib": 18.23796796798706}