E39 train-seed checkpoint E39-E18A100-ts2

e39/S1-E39-E18A100-ts2-syn/DONE

@@ -0,0 +1 @@
+2026-10-28 13:51:49

e39/S1-E39-E18A100-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-E18A100-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",
+    "in_proj_z",
+    "up_proj",
+    "o_proj",
+    "out_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "in_proj_qkv",
+    "k_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-ts2-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a00e66599c35af35c6cd093d492e8198228c8102ac0772cb1fc43c2af46a17
+size 160486456

e39/S1-E39-E18A100-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-E18A100-ts2-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d0e8a0de1034ab136403b41ed0cb90ce681d1d6f4fe1bc788253f82c27232b
+size 176641832

e39/S1-E39-E18A100-ts2-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00042443646816536784,
+  -0.0004246964235790074,
+  -0.002723469864577055,
+  -0.001929741119965911,
+  -0.0005273816059343517,
+  0.0018129183445125818,
+  0.0011884644627571106,
+  -0.0024350162129849195,
+  -0.0004412611888255924,
+  -0.0004118526994716376,
+  0.0002913996868301183,
+  0.0009190452401526272,
+  -5.753212099079974e-05,
+  -0.0034479284659028053,
+  -0.004138409625738859,
+  -0.005256468430161476,
+  -0.005616664420813322,
+  -0.0043669892475008965,
+  -0.004947149194777012,
+  -0.0050150142051279545,
+  -0.003811770584434271,
+  -0.0034106732346117496,
+  -0.005676032975316048,
+  -0.003511295188218355
+ ],
+ "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-ts2-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.9727707761713401,
+  "choice": 0.978351862144888,
+  "score": 1.0077124218018663
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.9727707761713401,
+   "ce_before": 0.5512580871582031,
+   "ce_after": 0.5511888861656189
+  },
+  "choice": {
+   "n": 60,
+   "T": 0.978351862144888,
+   "ce_before": 0.6630859971046448,
+   "ce_after": 0.6629763841629028
+  },
+  "score": {
+   "n": 53,
+   "T": 1.0077124218018663,
+   "ce_before": 1.0504124164581299,
+   "ce_after": 1.0503981113433838
+  }
+ },
+ "source": "models/e39/S1-E39-E18A100-ts2-syn/ckpt-16000"
+}

e39/S1-E39-E18A100-ts2-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b5186165cd81b677204e0afcfdea8d07d222443af16b30a7c8c73d89a0e5e2
+size 393464

e39/S1-E39-E18A100-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-E18A100-ts2-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": 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": 777.0987668026698,
+  "rows_per_s": 1.436120178609059,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5512580871582031,
+   "noul_T": 0.9727707761713401,
+   "choice_ce": 0.6630859971046448,
+   "choice_T": 0.978351862144888,
+   "score_ce": 1.0504124164581299,
+   "score_T": 1.0077124218018663,
+   "noul_auc": 0.7436842666666668,
+   "noul_acc": 0.699,
+   "noul_f1": 0.7741935483870968,
+   "noul_nll": 0.5682537431614474,
+   "noul_ece": 0.03230030950903894,
+   "noul_brier": 0.194314412204326,
+   "noul_sharp": 0.20308831334114075,
+   "entropy": 0.5647566318511963
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.237416744232178
+ }
+}

e39/S1-E39-E18A100-ts2-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "10:36:20", "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": 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": 146.6973352432251}
+{"time": "10:39:47", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 808.0489928465521, "loss": 0.5755471792072058, "entropy": 0.5969058834016323, "sharp": 0.18663408514112234}
+{"time": "10:43:27", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 813.9085508834119, "loss": 0.608481977134943, "entropy": 0.4926673024892807, "sharp": 0.2711038328707218}
+{"time": "10:47:08", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 817.7410682549738, "loss": 0.6502921562641859, "entropy": 0.5326111745089293, "sharp": 0.24218523129820824}
+{"time": "10:50:48", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 819.1582205237829, "loss": 0.6258702464401722, "entropy": 0.6353558339178562, "sharp": 0.125725076533854}
+{"time": "10:54:30", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 821.8688081312094, "loss": 0.6907116379588842, "entropy": 0.5630590599030256, "sharp": 0.2119182115420699}
+{"time": "10:58:14", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 822.5270269084987, "loss": 0.559532605111599, "entropy": 0.5785080268979073, "sharp": 0.21074667759239674}
+{"time": "11:02:00", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 822.6269921884941, "loss": 0.6544749028980732, "entropy": 0.5791650116443634, "sharp": 0.20748988632112741}
+{"time": "11:05:30", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 822.4735463476578, "loss": 0.6214367523789406, "entropy": 0.5821039415895939, "sharp": 0.19365998730063438}
+{"time": "11:09:09", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 822.6022911622164, "loss": 0.5842289663851261, "entropy": 0.5805527344346046, "sharp": 0.19597002677619457}
+{"time": "11:12:51", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 822.3618214277317, "loss": 0.7184304110705853, "entropy": 0.5286688059568405, "sharp": 0.24538304470479488}
+{"time": "11:14:20", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5824539065361023, "noul_T": 1.2785745242490347, "noul_auc": 0.7541476093230495, "noul_acc": 0.696, "noul_f1": 0.7877094972067039, "noul_nll": 0.5876135779507459, "noul_ece": 0.09196217727661134, "noul_brier": 0.20251240418811348, "noul_sharp": 0.2405952513217926, "entropy": 0.5263214707374573}
+{"time": "11:18:02", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 792.57685310925, "loss": 0.5486190803349018, "entropy": 0.5674925353378057, "sharp": 0.20847551338374615}
+{"time": "11:21:43", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 794.4039388301452, "loss": 0.5717584025114775, "entropy": 0.602478040382266, "sharp": 0.17949633114039898}
+{"time": "11:25:22", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 796.2836608195914, "loss": 0.5786074884235859, "entropy": 0.5585911273956299, "sharp": 0.21262388303875923}
+{"time": "11:29:06", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 798.4250557488318, "loss": 0.5744117577560246, "entropy": 0.5654403101652861, "sharp": 0.20920583605766296}
+{"time": "11:32:44", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 800.0345582873779, "loss": 0.6405918356031179, "entropy": 0.6607719957828522, "sharp": 0.10416183061897755}
+{"time": "11:36:18", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 800.8876269420787, "loss": 0.6640964224934578, "entropy": 0.5135048031806946, "sharp": 0.25221476797014475}
+{"time": "11:39:57", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 801.6602301732037, "loss": 0.6009912863373756, "entropy": 0.5987213104963303, "sharp": 0.18240388296544552}
+{"time": "11:43:50", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 802.9328779393123, "loss": 0.5431233216077089, "entropy": 0.5717207454144955, "sharp": 0.20256792567670345}
+{"time": "11:47:39", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 803.8278343937892, "loss": 0.5391823370009661, "entropy": 0.5523409880697727, "sharp": 0.2214393261820078}
+{"time": "11:51:15", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 804.8620107495975, "loss": 0.6085787401534617, "entropy": 0.5230790609493852, "sharp": 0.24205060582607985}
+{"time": "11:52:45", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5692656636238098, "noul_T": 1.0369247768665488, "noul_auc": 0.7410507839530135, "noul_acc": 0.71, "noul_f1": 0.787701317715959, "noul_nll": 0.5807672257311642, "noul_ece": 0.07991532492637636, "noul_brier": 0.19876913820306463, "noul_sharp": 0.2104538530111313, "entropy": 0.5625191926956177}
+{"time": "11:56:27", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 790.8341107104683, "loss": 0.5801369724795222, "entropy": 0.5475843101739883, "sharp": 0.21787947230041027}
+{"time": "12:00:12", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 791.9788373861477, "loss": 0.5681632608175278, "entropy": 0.5568980202078819, "sharp": 0.2037397576496005}
+{"time": "12:03:41", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 792.8470257641004, "loss": 0.5654693059623241, "entropy": 0.6094402149319649, "sharp": 0.17674479633569717}
+{"time": "12:07:18", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 794.1147983454309, "loss": 0.6180395111441612, "entropy": 0.5460173338651657, "sharp": 0.21639157459139824}
+{"time": "12:10:58", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 795.4334663802734, "loss": 0.5986553784459829, "entropy": 0.6036119777709246, "sharp": 0.1766619198024273}
+{"time": "12:14:43", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 796.4436249163314, "loss": 0.6236767508089542, "entropy": 0.6360786277800798, "sharp": 0.1486936006695032}
+{"time": "12:18:32", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 797.7797762159402, "loss": 0.5810160227119923, "entropy": 0.5997805576771498, "sharp": 0.18378605786710978}
+{"time": "12:22:10", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 798.6049792105971, "loss": 0.6105928346514702, "entropy": 0.5306933494284749, "sharp": 0.22411690093576908}
+{"time": "12:25:56", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 799.4091935645238, "loss": 0.6061406284570694, "entropy": 0.5775085054337978, "sharp": 0.18652012757956982}
+{"time": "12:29:52", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 800.7280191337637, "loss": 0.5707076229155064, "entropy": 0.5305592231452465, "sharp": 0.2350449115037918}
+{"time": "12:31:21", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5742945671081543, "noul_T": 1.1224274052305128, "noul_auc": 0.743970565897622, "noul_acc": 0.698, "noul_f1": 0.7544715447154472, "noul_nll": 0.5825579156409949, "noul_ece": 0.06030346840620041, "noul_brier": 0.1995694546983686, "noul_sharp": 0.2115602195262909, "entropy": 0.553159773349762}
+{"time": "12:34:58", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 791.2586932451956, "loss": 0.6186023503541946, "entropy": 0.6051687113940716, "sharp": 0.18111037835478783}
+{"time": "12:38:49", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 792.1100033135184, "loss": 0.6391014829277992, "entropy": 0.6440524682402611, "sharp": 0.13481480069458485}
+{"time": "12:42:23", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 792.6592971511546, "loss": 0.6206443607807159, "entropy": 0.6228020340204239, "sharp": 0.1628923248499632}
+{"time": "12:46:10", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 793.3001311469523, "loss": 0.5667935591191053, "entropy": 0.5751716196537018, "sharp": 0.18516453448683023}
+{"time": "12:49:44", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 793.8428872265274, "loss": 0.575926786288619, "entropy": 0.5424747802317142, "sharp": 0.22244733665138483}
+{"time": "12:53:37", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 794.5443343340904, "loss": 0.5669153966009617, "entropy": 0.5689101442694664, "sharp": 0.2017796067520976}
+{"time": "12:57:28", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 795.3486540521695, "loss": 0.5998039208352566, "entropy": 0.6266055032610893, "sharp": 0.14964794274419546}
+{"time": "13:01:05", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 795.9743331360763, "loss": 0.6205507144331932, "entropy": 0.5951683446764946, "sharp": 0.17779270187020302}
+{"time": "13:04:49", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 796.6896683404466, "loss": 0.540231192484498, "entropy": 0.5893514342606068, "sharp": 0.19430943578481674}
+{"time": "13:08:26", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 797.4522928948394, "loss": 0.5816700402647257, "entropy": 0.5882646813988686, "sharp": 0.18005822598934174}
+{"time": "13:09:55", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5655637383460999, "noul_T": 1.0103866433404536, "noul_auc": 0.7438017923748123, "noul_acc": 0.696, "noul_f1": 0.7639751552795031, "noul_nll": 0.5737111207768321, "noul_ece": 0.054488133192062374, "noul_brier": 0.19638025345558094, "noul_sharp": 0.20410363376140594, "entropy": 0.5638648271560669}
+{"time": "13:13:41", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 790.61147886043, "loss": 0.5806611999869347, "entropy": 0.5875376407057047, "sharp": 0.18156833481043577}
+{"time": "13:17:19", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 791.1770052058968, "loss": 0.5530001558363438, "entropy": 0.5651137791574001, "sharp": 0.22379183769226074}
+{"time": "13:20:55", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 791.837828317056, "loss": 0.577342115342617, "entropy": 0.5682325288653374, "sharp": 0.20654316432774067}
+{"time": "13:24:39", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 792.497334340102, "loss": 0.5817885959986597, "entropy": 0.5641272645443678, "sharp": 0.1975155957043171}
+{"time": "13:28:09", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 793.3825917211352, "loss": 0.5219930857419968, "entropy": 0.5455274358391762, "sharp": 0.22216099314391613}
+{"time": "13:31:58", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 794.1819905246924, "loss": 0.6015477664768696, "entropy": 0.5477119833230972, "sharp": 0.22864489443600178}
+{"time": "13:35:41", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 794.6228976825114, "loss": 0.5931729525327682, "entropy": 0.5720323249697685, "sharp": 0.211152664385736}
+{"time": "13:39:22", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 794.9531307372876, "loss": 0.5665950886905193, "entropy": 0.590231504291296, "sharp": 0.1779257245361805}
+{"time": "13:43:19", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 795.5925499352062, "loss": 0.559782363474369, "entropy": 0.5940907998010516, "sharp": 0.18959941901266575}
+{"time": "13:47:08", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 796.0779906073161, "loss": 0.5262787193059921, "entropy": 0.5482510533183813, "sharp": 0.20315273106098175}
+{"time": "13:48:38", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5643167495727539, "noul_T": 0.9938983000592935, "noul_auc": 0.7447975561593898, "noul_acc": 0.694, "noul_f1": 0.7620528771384136, "noul_nll": 0.5728254345152527, "noul_ece": 0.04275201988220215, "noul_brier": 0.1961983804053071, "noul_sharp": 0.20137472450733185, "entropy": 0.5654032230377197}
+{"time": "13:51:49", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9113372, "tok_per_s": 777.0987668026698, "rows_per_s": 1.436120178609059, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5512580871582031, "noul_T": 0.9727707761713401, "choice_ce": 0.6630859971046448, "choice_T": 0.978351862144888, "score_ce": 1.0504124164581299, "score_T": 1.0077124218018663, "noul_auc": 0.7436842666666668, "noul_acc": 0.699, "noul_f1": 0.7741935483870968, "noul_nll": 0.5682537431614474, "noul_ece": 0.03230030950903894, "noul_brier": 0.194314412204326, "noul_sharp": 0.20308831334114075, "entropy": 0.5647566318511963}, "dropped_long": 0, "peak_gib": 18.237416744232178}