pod backup 2026-11-07: e49/S1-E49-M3P40-ts0-syn (0-11)

e49/S1-E49-M3P40-ts0-syn/DONE

@@ -0,0 +1 @@
+2026-11-09 00:59:24

e49/S1-E49-M3P40-ts0-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

e49/S1-E49-M3P40-ts0-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": [
+    "out_proj",
+    "gate_proj",
+    "v_proj",
+    "in_proj_z",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "in_proj_qkv",
+    "o_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
+}

e49/S1-E49-M3P40-ts0-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b190f927a9d3b1dfeb7638a40fe92b9751428815cfd1dc8378aaf6fb8ce7a4
+size 160486456

e49/S1-E49-M3P40-ts0-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
+}

e49/S1-E49-M3P40-ts0-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb97bf8fcb72efa41444c0551c5e4397f3e3d4a197b002c534548ca57acde19
+size 176641832

e49/S1-E49-M3P40-ts0-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00040294858627021313,
+  -0.00040320327389054,
+  -0.002139620017260313,
+  -0.0014755874872207642,
+  -0.0003709830925799906,
+  0.0018427562899887562,
+  0.0014172472292557359,
+  -0.0022315685637295246,
+  -0.0003957725712098181,
+  -0.00024207351088989526,
+  -0.00021605943038593978,
+  0.00040033654659055173,
+  -3.940001261071302e-05,
+  -0.0035299137234687805,
+  -0.004159468691796064,
+  -0.005128446966409683,
+  -0.0059883263893425465,
+  -0.004374444019049406,
+  -0.004934099968522787,
+  -0.0049802083522081375,
+  -0.0037994212470948696,
+  -0.003376553300768137,
+  -0.005730702541768551,
+  -0.0034792853984981775
+ ],
+ "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"
+}

e49/S1-E49-M3P40-ts0-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.7371338293381365,
+  "choice": 1.0545985082196214,
+  "score": 0.9723845392636948
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.7371338293381365,
+   "ce_before": 0.578153669834137,
+   "ce_after": 0.5718048810958862
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0545985082196214,
+   "ce_before": 0.6828810572624207,
+   "ce_after": 0.6822186708450317
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9723845392636948,
+   "ce_before": 1.0541447401046753,
+   "ce_after": 1.053906798362732
+  }
+ },
+ "source": "models/e49/S1-E49-M3P40-ts0-syn/ckpt-16000"
+}

e49/S1-E49-M3P40-ts0-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc5408df65028414cbd09a30ef267974d39d6f8cbd6974453e5697ea87f6bae
+size 393464

e49/S1-E49-M3P40-ts0-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/e49/S1-E49-M3P40-ts0-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e49/E49-M3P40-n16k",
+  "data_manifest": {
+   "arm": "E49-M3P40-n16k",
+   "name": null,
+   "train_sha256": "a6827e994bdfc35315b00c3c75a70a5c8c01944b0461e4ae643506a25135f65f",
+   "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": 0,
+  "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": 9822245,
+  "tok_per_s": 1288.6173413626,
+  "rows_per_s": 2.2095654565527685,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.578153669834137,
+   "noul_T": 0.7371338293381365,
+   "choice_ce": 0.6828810572624207,
+   "choice_T": 1.0545985082196214,
+   "score_ce": 1.0541447401046753,
+   "score_T": 0.9723845392636948,
+   "noul_auc": 0.7196458666666667,
+   "noul_acc": 0.692,
+   "noul_f1": 0.7735294117647059,
+   "noul_nll": 0.5929008256793022,
+   "noul_ece": 0.061506176322698586,
+   "noul_brier": 0.20304384187012745,
+   "noul_sharp": 0.15162453055381775,
+   "entropy": 0.6269420385360718
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.282634735107422
+ }
+}

e49/S1-E49-M3P40-ts0-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "22:52:21", "event": "start", "data": "data/e49/E49-M3P40-n16k", "data_manifest": {"arm": "E49-M3P40-n16k", "name": null, "train_sha256": "a6827e994bdfc35315b00c3c75a70a5c8c01944b0461e4ae643506a25135f65f", "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": 0, "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": 10.137736320495605}
+{"time": "22:54:48", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 1351.9854343807945, "loss": 0.6530981808900833, "entropy": 0.6814227476716042, "sharp": 0.06281620170921087}
+{"time": "22:57:11", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 1348.196687474426, "loss": 0.6346454173326492, "entropy": 0.6385672464966774, "sharp": 0.1319736884906888}
+{"time": "22:59:39", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 1347.5974999018792, "loss": 0.7159059345722198, "entropy": 0.6238710135221481, "sharp": 0.1714243534952402}
+{"time": "23:02:06", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 1347.0675337440027, "loss": 0.6910362839698792, "entropy": 0.65925282984972, "sharp": 0.1031957296654582}
+{"time": "23:04:27", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 1349.4502708535706, "loss": 0.6258364245295525, "entropy": 0.6612336039543152, "sharp": 0.10302982572466135}
+{"time": "23:06:50", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 1350.984451466821, "loss": 0.6387734226882458, "entropy": 0.6527519896626472, "sharp": 0.1356109417974949}
+{"time": "23:09:11", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 1351.9613799704734, "loss": 0.5979587510228157, "entropy": 0.6410370357334614, "sharp": 0.13804892543703318}
+{"time": "23:11:35", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 1353.0778254748975, "loss": 0.6601868849247694, "entropy": 0.6444680020213127, "sharp": 0.13687903061509132}
+{"time": "23:13:58", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 1352.2562796209518, "loss": 0.6587491258978844, "entropy": 0.6705602332949638, "sharp": 0.09556412883102894}
+{"time": "23:16:21", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 1351.3302928501503, "loss": 0.5907428599894047, "entropy": 0.6241977624595165, "sharp": 0.1666927319020033}
+{"time": "23:17:14", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.6052772402763367, "noul_T": 1.0869303359573783, "noul_auc": 0.7128824829960676, "noul_acc": 0.674, "noul_f1": 0.7739251040221914, "noul_nll": 0.6053929928094148, "noul_ece": 0.07513066148757934, "noul_brier": 0.20849644747619675, "noul_sharp": 0.19506077468395233, "entropy": 0.5916603207588196}
+{"time": "23:19:38", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 1307.4397223518763, "loss": 0.66495081782341, "entropy": 0.6655408293008804, "sharp": 0.09787371382117271}
+{"time": "23:22:02", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 1310.560314520779, "loss": 0.6355526614934206, "entropy": 0.6631234996020794, "sharp": 0.10183154232800007}
+{"time": "23:24:28", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 1314.8253226284642, "loss": 0.6729799807071686, "entropy": 0.6347096115350723, "sharp": 0.13176731020212173}
+{"time": "23:26:52", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 1317.5530847682696, "loss": 0.6417621038854122, "entropy": 0.6720068790018559, "sharp": 0.08963996637612581}
+{"time": "23:29:15", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 1318.9448147327678, "loss": 0.6399557404220104, "entropy": 0.6344099715352058, "sharp": 0.1379923140630126}
+{"time": "23:31:43", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 1321.650423343978, "loss": 0.6815049340948462, "entropy": 0.656640887260437, "sharp": 0.10095621459186077}
+{"time": "23:34:03", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 1323.4136704767022, "loss": 0.7100321911275387, "entropy": 0.6153231263160706, "sharp": 0.15973364748060703}
+{"time": "23:36:25", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 1324.7837093926166, "loss": 0.6511268615722656, "entropy": 0.6640821024775505, "sharp": 0.09706870652735233}
+{"time": "23:38:52", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 1326.5327350324294, "loss": 0.6490727979689837, "entropy": 0.6839070543646812, "sharp": 0.04778794106096029}
+{"time": "23:41:15", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 1327.7188039926923, "loss": 0.6468356885015965, "entropy": 0.6480111181735992, "sharp": 0.12004439812153578}
+{"time": "23:42:08", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5930025577545166, "noul_T": 0.6440547997668951, "noul_auc": 0.7368652005873317, "noul_acc": 0.714, "noul_f1": 0.7843137254901961, "noul_nll": 0.5946154245734214, "noul_ece": 0.08047327160835267, "noul_brier": 0.20296944312858126, "noul_sharp": 0.1356474906206131, "entropy": 0.6385215520858765}
+{"time": "23:44:36", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 1306.5210243699191, "loss": 0.6480093244463205, "entropy": 0.6360490452498198, "sharp": 0.13464284408837557}
+{"time": "23:47:01", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 1308.4646953375084, "loss": 0.6652616038918495, "entropy": 0.6667790859937668, "sharp": 0.08494193945080042}
+{"time": "23:49:26", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 1311.4071254972268, "loss": 0.652984980493784, "entropy": 0.6520639508962631, "sharp": 0.1095202062278986}
+{"time": "23:51:45", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 1312.8447476787612, "loss": 0.6832772810012102, "entropy": 0.6437769290059805, "sharp": 0.12579268403351307}
+{"time": "23:54:09", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 1314.5516461569034, "loss": 0.6844874508678913, "entropy": 0.6685876771807671, "sharp": 0.08877790346741676}
+{"time": "23:56:35", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 1316.5829531815427, "loss": 0.6879166886210442, "entropy": 0.6578417643904686, "sharp": 0.1153772696852684}
+{"time": "23:59:02", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 1318.1548945693892, "loss": 0.6197369219735265, "entropy": 0.6329919751733541, "sharp": 0.14218788594007492}
+{"time": "00:01:24", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 1319.4885443729722, "loss": 0.6923806816339493, "entropy": 0.661826379597187, "sharp": 0.10250879265367985}
+{"time": "00:03:51", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 1320.863658066909, "loss": 0.6187025271356106, "entropy": 0.6301463916897774, "sharp": 0.15161877870559692}
+{"time": "00:06:17", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 1321.9635708747157, "loss": 0.7154421489685774, "entropy": 0.6565988194197416, "sharp": 0.10900765843689442}
+{"time": "00:07:10", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5891314148902893, "noul_T": 0.7648175632022174, "noul_auc": 0.7406457274982701, "noul_acc": 0.712, "noul_f1": 0.7728706624605678, "noul_nll": 0.5876290616691112, "noul_ece": 0.07541247868537904, "noul_brier": 0.20023681099621904, "noul_sharp": 0.1585230976343155, "entropy": 0.6229686737060547}
+{"time": "00:09:39", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 1307.9870218210142, "loss": 0.6001608371734619, "entropy": 0.6441550925374031, "sharp": 0.13129491358995438}
+{"time": "00:12:04", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 1309.3747458429464, "loss": 0.6562502831220627, "entropy": 0.6371064186096191, "sharp": 0.12470798846334219}
+{"time": "00:14:30", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 1310.8572174974188, "loss": 0.6410549730062485, "entropy": 0.6105051450431347, "sharp": 0.17231273092329502}
+{"time": "00:16:55", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 1311.964897553271, "loss": 0.6358421444892883, "entropy": 0.6468661352992058, "sharp": 0.12901831604540348}
+{"time": "00:19:17", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 1313.3553252714016, "loss": 0.6403319872915745, "entropy": 0.6638774536550045, "sharp": 0.08673314098268747}
+{"time": "00:21:47", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 1314.9430070761177, "loss": 0.6417022999376059, "entropy": 0.630672687664628, "sharp": 0.14168872870504856}
+{"time": "00:24:10", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 1316.2315655592458, "loss": 0.6423200778663158, "entropy": 0.6427788585424423, "sharp": 0.11840091645717621}
+{"time": "00:26:35", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 1317.2108998255758, "loss": 0.7218098379671574, "entropy": 0.6412270665168762, "sharp": 0.13758659828454256}
+{"time": "00:29:00", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 1318.1401226285761, "loss": 0.6789048500359058, "entropy": 0.666886942461133, "sharp": 0.08952340669929981}
+{"time": "00:31:25", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 1319.1878981066804, "loss": 0.6011928394436836, "entropy": 0.6449129767715931, "sharp": 0.11972789745777845}
+{"time": "00:32:18", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5867455005645752, "noul_T": 0.7772750525934338, "noul_auc": 0.7370339741101416, "noul_acc": 0.704, "noul_f1": 0.7716049382716049, "noul_nll": 0.587340874761343, "noul_ece": 0.07299766647815706, "noul_brier": 0.2002016747445943, "noul_sharp": 0.15746961534023285, "entropy": 0.6188217401504517}
+{"time": "00:34:39", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 1308.6126576485105, "loss": 0.6033900305628777, "entropy": 0.6545284017920494, "sharp": 0.10647153295576572}
+{"time": "00:37:05", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 1309.6020725131086, "loss": 0.6357110254466534, "entropy": 0.6164897419512272, "sharp": 0.16562487371265888}
+{"time": "00:39:27", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 1310.5936554517466, "loss": 0.6310360450297594, "entropy": 0.6347669400274754, "sharp": 0.1430748514831066}
+{"time": "00:41:59", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 1311.645562095489, "loss": 0.665755070745945, "entropy": 0.6474885120987892, "sharp": 0.1252711759880185}
+{"time": "00:44:23", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 1312.8890278337203, "loss": 0.6664185672998428, "entropy": 0.6539379432797432, "sharp": 0.11049937549978495}
+{"time": "00:46:47", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 1313.8971040881704, "loss": 0.6059975847601891, "entropy": 0.6217656210064888, "sharp": 0.1572846993803978}
+{"time": "00:49:12", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 1314.749676315748, "loss": 0.7304577939212322, "entropy": 0.6476190760731697, "sharp": 0.12159848399460316}
+{"time": "00:51:44", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 1315.599959132657, "loss": 0.6799561530351639, "entropy": 0.6625010594725609, "sharp": 0.10166066512465477}
+{"time": "00:54:13", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 1316.4690850362535, "loss": 0.6037785857915878, "entropy": 0.6579442396759987, "sharp": 0.11239604093134403}
+{"time": "00:56:37", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 1317.2697002366829, "loss": 0.632384205237031, "entropy": 0.6528995223343372, "sharp": 0.1145164743065834}
+{"time": "00:57:30", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5907816886901855, "noul_T": 0.7082151443957251, "noul_auc": 0.737405275860323, "noul_acc": 0.708, "noul_f1": 0.7753846153846153, "noul_nll": 0.58987773630023, "noul_ece": 0.07660906100273132, "noul_brier": 0.2012220606240171, "noul_sharp": 0.14647962152957916, "entropy": 0.6304632425308228}
+{"time": "00:59:24", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9822245, "tok_per_s": 1288.6173413626, "rows_per_s": 2.2095654565527685, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.578153669834137, "noul_T": 0.7371338293381365, "choice_ce": 0.6828810572624207, "choice_T": 1.0545985082196214, "score_ce": 1.0541447401046753, "score_T": 0.9723845392636948, "noul_auc": 0.7196458666666667, "noul_acc": 0.692, "noul_f1": 0.7735294117647059, "noul_nll": 0.5929008256793022, "noul_ece": 0.061506176322698586, "noul_brier": 0.20304384187012745, "noul_sharp": 0.15162453055381775, "entropy": 0.6269420385360718}, "dropped_long": 0, "peak_gib": 18.282634735107422}