pod backup 2026-11-07: e47/S1-E41-FRESH-A100NR-ts1-syn (0-11)

e47/S1-E41-FRESH-A100NR-ts1-syn/DONE

@@ -0,0 +1 @@
+2026-11-07 09:40:52

e47/S1-E41-FRESH-A100NR-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

e47/S1-E41-FRESH-A100NR-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": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "in_proj_qkv",
+    "out_proj",
+    "o_proj",
+    "in_proj_z",
+    "up_proj",
+    "q_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
+}

e47/S1-E41-FRESH-A100NR-ts1-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df4743b57d014788c83ae03b21d29f19fbebc35dcabd461f05f998acf6d441c
+size 160486456

e47/S1-E41-FRESH-A100NR-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": "0.21.2",
+  "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
+}

e47/S1-E41-FRESH-A100NR-ts1-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5cc7ea16db653081ebb32f1795b08dc5ec1069a82b3d847ff56b056484ad659
+size 176641832

e47/S1-E41-FRESH-A100NR-ts1-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  -9.991772822104394e-05,
+  9.990473336074501e-05,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0,
+  0.0
+ ],
+ "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"
+}

e47/S1-E41-FRESH-A100NR-ts1-syn/ckpt-16000/calibration.json

@@ -0,0 +1,17 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.974694936862304,
+  "choice": 1.0,
+  "score": 1.0
+ },
+ "fit": {
+  "noul": {
+   "n": 1000,
+   "T": 0.974694936862304,
+   "ce_before": 0.5651007294654846,
+   "ce_after": 0.565041184425354
+  }
+ },
+ "source": "models/e47/S1-E41-FRESH-A100NR-ts1-syn/ckpt-16000"
+}

e47/S1-E41-FRESH-A100NR-ts1-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947bb049b042d3a8ae627d3bf2c58bdab372df89e012b939309dd21ccad23a89
+size 393464

e47/S1-E41-FRESH-A100NR-ts1-syn/ckpt-16000/judge_config.json

@@ -0,0 +1,160 @@
+{
+ "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/e47/S1-E41-FRESH-A100NR-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": "fresh",
+  "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": null,
+  "replay_frac": 0.0,
+  "replay_sha256": null,
+  "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": 0,
+  "step": 500,
+  "tokens": 9001452,
+  "tok_per_s": 1259.4995772221084,
+  "rows_per_s": 2.238749174041652,
+  "val": {
+   "n": 1000,
+   "dropped_long": 0,
+   "noul_ce": 0.5651007294654846,
+   "noul_T": 0.974694936862304,
+   "noul_auc": 0.7436074666666668,
+   "noul_acc": 0.704,
+   "noul_f1": 0.774390243902439,
+   "noul_nll": 0.5715125135499984,
+   "noul_ece": 0.041158414766192454,
+   "noul_brier": 0.19510236746006102,
+   "noul_sharp": 0.20121751725673676,
+   "entropy": 0.569628894329071
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.28404712677002
+ }
+}

e47/S1-E41-FRESH-A100NR-ts1-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "07:41:44", "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": "fresh", "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": null, "replay_frac": 0.0, "replay_sha256": null, "max_len": 3072, "schedule": "warmup 0.03 + cosine to x0.05 over 500 steps", "total_rows": 16000, "lora": {"r": 16, "lora_alpha": 32, "lora_dropout": 0.05}, "trainer_sha256": "a0b9d7552588ffb068565686509162a4f122f6f03392e693fa20088493e2a4f3", "device": "cuda", "load_s": 5.411858320236206}
+{"time": "07:43:54", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 1305.302005483205, "loss": 0.6141763404011726, "entropy": 0.5148954316973686, "sharp": 0.2618070300668478}
+{"time": "07:46:12", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 1323.4987631809427, "loss": 0.6828065346926451, "entropy": 0.618787438608706, "sharp": 0.15933925192803144}
+{"time": "07:48:29", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 1323.240397704393, "loss": 0.7481556832790375, "entropy": 0.6238142512738705, "sharp": 0.1560011226683855}
+{"time": "07:50:49", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 1328.3048998875943, "loss": 0.6200447231531143, "entropy": 0.6682101190090179, "sharp": 0.08649626094847918}
+{"time": "07:53:07", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 1329.7324953421785, "loss": 0.7304747737944126, "entropy": 0.624552158638835, "sharp": 0.15169713087379932}
+{"time": "07:55:25", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 1330.9771214536438, "loss": 0.6478938683867455, "entropy": 0.6664767116308212, "sharp": 0.09510779194533825}
+{"time": "07:57:34", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 1330.6311393959404, "loss": 0.6897933036088943, "entropy": 0.4518067203462124, "sharp": 0.2996923327445984}
+{"time": "07:59:43", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 1328.186259429836, "loss": 0.6695680469274521, "entropy": 0.6697773635387421, "sharp": 0.09382889419794083}
+{"time": "08:02:03", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 1328.3527507287038, "loss": 0.6218358064070344, "entropy": 0.5100930891931057, "sharp": 0.2700143828988075}
+{"time": "08:04:19", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 1328.357381232401, "loss": 0.7624733746051788, "entropy": 0.48452139645814896, "sharp": 0.3037568926811218}
+{"time": "08:05:12", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.7967416644096375, "noul_T": 2.992077701490329, "noul_auc": 0.7104690216198883, "noul_acc": 0.614, "noul_f1": 0.7608426270136307, "noul_nll": 0.8145223663151264, "noul_ece": 0.25138598608970647, "noul_brier": 0.2863052716040694, "noul_sharp": 0.3653859794139862, "entropy": 0.3853965401649475}
+{"time": "08:07:27", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 1283.266909492693, "loss": 0.7280249465256929, "entropy": 0.5940764993429184, "sharp": 0.19700959045439959}
+{"time": "08:09:43", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 1286.5330820375825, "loss": 0.6344308629631996, "entropy": 0.5792548172175884, "sharp": 0.20233177859336138}
+{"time": "08:12:01", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 1289.9837079671433, "loss": 0.578548239544034, "entropy": 0.5726379882544279, "sharp": 0.20680940430611372}
+{"time": "08:14:07", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 1290.6808771667613, "loss": 0.6039197240024805, "entropy": 0.6217619981616735, "sharp": 0.16304177418351173}
+{"time": "08:16:24", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 1292.731710040699, "loss": 0.6180316023528576, "entropy": 0.5085446331650019, "sharp": 0.26450089178979397}
+{"time": "08:18:42", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 1294.2227312694433, "loss": 0.5652714408934116, "entropy": 0.5900612529367208, "sharp": 0.18537042941898108}
+{"time": "08:21:04", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 1296.3079391501917, "loss": 0.5230578668415546, "entropy": 0.5530219078063965, "sharp": 0.22573711909353733}
+{"time": "08:23:18", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 1297.5743303432018, "loss": 0.6263164728879929, "entropy": 0.6472915150225163, "sharp": 0.11730743013322353}
+{"time": "08:25:36", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 1298.6373124437591, "loss": 0.705049553886056, "entropy": 0.584519200026989, "sharp": 0.18750329315662384}
+{"time": "08:27:51", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 1301.1657342601413, "loss": 0.600053284317255, "entropy": 0.6098419390618801, "sharp": 0.17044267430901527}
+{"time": "08:28:44", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.586711049079895, "noul_T": 0.8708379522506325, "noul_auc": 0.7500464127187726, "noul_acc": 0.682, "noul_f1": 0.7272727272727273, "noul_nll": 0.5865307522714138, "noul_ece": 0.07933724355697633, "noul_brier": 0.20058880980596377, "noul_sharp": 0.1712387502193451, "entropy": 0.6066256165504456}
+{"time": "08:30:58", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 1278.87547414279, "loss": 0.633856225758791, "entropy": 0.6103864703327417, "sharp": 0.1617232235148549}
+{"time": "08:33:11", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 1280.6483502378233, "loss": 0.6425990909337997, "entropy": 0.5597686152905226, "sharp": 0.22704331949353218}
+{"time": "08:35:25", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 1283.3801551541894, "loss": 0.5847409069538116, "entropy": 0.5658595226705074, "sharp": 0.2169533483684063}
+{"time": "08:37:39", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 1285.0881238378279, "loss": 0.6134736351668835, "entropy": 0.5885772332549095, "sharp": 0.19118849001824856}
+{"time": "08:39:55", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 1286.8211209352496, "loss": 0.5679008234292269, "entropy": 0.5470043607056141, "sharp": 0.22694682702422142}
+{"time": "08:42:15", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 1289.3919117631924, "loss": 0.5712298266589642, "entropy": 0.6187104154378176, "sharp": 0.156032825820148}
+{"time": "08:44:27", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 1290.0464496316215, "loss": 0.5817154124379158, "entropy": 0.5902568101882935, "sharp": 0.17986438982188702}
+{"time": "08:46:43", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 1291.3242732869064, "loss": 0.6007361635565758, "entropy": 0.6077076997607946, "sharp": 0.16652427148073912}
+{"time": "08:48:54", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 1293.151486350983, "loss": 0.5622068010270596, "entropy": 0.6032283678650856, "sharp": 0.1665986506268382}
+{"time": "08:51:06", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 1294.2625252607238, "loss": 0.5868409648537636, "entropy": 0.5752169974148273, "sharp": 0.18700854759663343}
+{"time": "08:51:59", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5736395716667175, "noul_T": 1.02701741078389, "noul_auc": 0.7532699870044388, "noul_acc": 0.698, "noul_f1": 0.7495854063018242, "noul_nll": 0.5732692723311484, "noul_ece": 0.05052299350500108, "noul_brier": 0.19575310983031705, "noul_sharp": 0.20075689256191254, "entropy": 0.5689802169799805}
+{"time": "08:54:16", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 1279.5028505563796, "loss": 0.6250042393803596, "entropy": 0.5860024094581604, "sharp": 0.18980049900710583}
+{"time": "08:56:26", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 1281.2900043992663, "loss": 0.5508326012641191, "entropy": 0.5280071198940277, "sharp": 0.21964939031749964}
+{"time": "08:58:41", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 1282.5980589163723, "loss": 0.5349204000085592, "entropy": 0.5585554707795382, "sharp": 0.1983426082879305}
+{"time": "09:01:02", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 1284.2978449679592, "loss": 0.6082957610487938, "entropy": 0.5755369663238525, "sharp": 0.18817360512912273}
+{"time": "09:03:17", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 1285.5487934402079, "loss": 0.5216501359827816, "entropy": 0.5574097521603107, "sharp": 0.2098760660737753}
+{"time": "09:05:32", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 1286.660956658688, "loss": 0.6370944641530514, "entropy": 0.5841389410197735, "sharp": 0.1843966767191887}
+{"time": "09:07:41", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 1287.5803072625843, "loss": 0.5479276701807976, "entropy": 0.5678174123167992, "sharp": 0.212494901381433}
+{"time": "09:09:56", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 1288.5686371389534, "loss": 0.6080551873892546, "entropy": 0.6012360453605652, "sharp": 0.1750257359817624}
+{"time": "09:12:08", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 1289.5247819910237, "loss": 0.6576315239071846, "entropy": 0.6040166690945625, "sharp": 0.1716329362243414}
+{"time": "09:14:24", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 1290.163268944439, "loss": 0.5666048508137465, "entropy": 0.5545690469443798, "sharp": 0.22460116352885962}
+{"time": "09:15:17", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5682370662689209, "noul_T": 1.0474786155771671, "noul_auc": 0.7495063374457814, "noul_acc": 0.692, "noul_f1": 0.7818696883852692, "noul_nll": 0.5755615932643413, "noul_ece": 0.06037398767471315, "noul_brier": 0.19713292842541422, "noul_sharp": 0.21044330298900604, "entropy": 0.5596388578414917}
+{"time": "09:17:31", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 1279.0584910733305, "loss": 0.5879145413637161, "entropy": 0.5955156162381172, "sharp": 0.18108020070940256}
+{"time": "09:19:51", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 1280.2618630261718, "loss": 0.5432694088667631, "entropy": 0.5819350648671389, "sharp": 0.2033116165548563}
+{"time": "09:22:08", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 1281.4206158788145, "loss": 0.568385899066925, "entropy": 0.5620876774191856, "sharp": 0.20391862466931343}
+{"time": "09:24:31", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 1282.9213310269392, "loss": 0.6557003445923328, "entropy": 0.5956002585589886, "sharp": 0.18724403157830238}
+{"time": "09:26:47", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 1284.2229958201026, "loss": 0.619361256249249, "entropy": 0.6044403687119484, "sharp": 0.16646049171686172}
+{"time": "09:29:03", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 1285.1462004968528, "loss": 0.5800669230520725, "entropy": 0.5837314613163471, "sharp": 0.19177454058080912}
+{"time": "09:31:22", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 1285.8101149845097, "loss": 0.5746333990246058, "entropy": 0.5720129497349262, "sharp": 0.20680970139801502}
+{"time": "09:33:36", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 1286.88940022292, "loss": 0.5791548974812031, "entropy": 0.5840528532862663, "sharp": 0.19611687865108252}
+{"time": "09:35:54", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 1287.7576553450756, "loss": 0.593000253662467, "entropy": 0.6002691984176636, "sharp": 0.1774348011240363}
+{"time": "09:38:10", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 1288.51248247542, "loss": 0.5384229607880116, "entropy": 0.5601943098008633, "sharp": 0.207489094696939}
+{"time": "09:39:03", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5677882432937622, "noul_T": 0.9884091895357671, "noul_auc": 0.7502826956507063, "noul_acc": 0.698, "noul_f1": 0.7606973058637084, "noul_nll": 0.5719932747147978, "noul_ece": 0.04592022883892059, "noul_brier": 0.1952406379498974, "noul_sharp": 0.2003953605890274, "entropy": 0.5698043704032898}
+{"time": "09:40:52", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 0, "step": 500, "tokens": 9001452, "tok_per_s": 1259.4995772221084, "rows_per_s": 2.238749174041652, "val": {"n": 1000, "dropped_long": 0, "noul_ce": 0.5651007294654846, "noul_T": 0.974694936862304, "noul_auc": 0.7436074666666668, "noul_acc": 0.704, "noul_f1": 0.774390243902439, "noul_nll": 0.5715125135499984, "noul_ece": 0.041158414766192454, "noul_brier": 0.19510236746006102, "noul_sharp": 0.20121751725673676, "entropy": 0.569628894329071}, "dropped_long": 0, "peak_gib": 18.28404712677002}