backup e16/S1-ABCLODO16-dbe_kt22 (Pod B)

e16/S1-ABCLODO16-dbe_kt22/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

e16/S1-ABCLODO16-dbe_kt22/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": [
+    "in_proj_qkv",
+    "in_proj_z",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "out_proj",
+    "o_proj",
+    "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
+}

e16/S1-ABCLODO16-dbe_kt22/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3031a7ed7e12a1270af88c3d7deeefb05575792c48a3a2919a649e9053b6470d
+size 160486456

e16/S1-ABCLODO16-dbe_kt22/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
+}

e16/S1-ABCLODO16-dbe_kt22/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41c0cc565d3af8a3180e331c13ea309f413364c7f5e5902013e058df887728c
+size 176641832

e16/S1-ABCLODO16-dbe_kt22/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0003825274179689586,
+  -0.000382786151021719,
+  -0.002474206732586026,
+  -0.0018814544891938567,
+  -0.0006579043692909181,
+  0.0016997664934024215,
+  0.0013256707461550832,
+  -0.002703828737139702,
+  6.569284596480429e-05,
+  -0.00027744926046580076,
+  0.00015276165504474193,
+  0.0006400728598237038,
+  -0.0004360083257779479,
+  -0.004430248402059078,
+  -0.005685324780642986,
+  -0.005414790473878384,
+  -0.005910261534154415,
+  -0.005355154629796743,
+  -0.005279622972011566,
+  -0.005628619808703661,
+  -0.004674861207604408,
+  -0.004169309977442026,
+  -0.006343239918351173,
+  -0.004096445627510548
+ ],
+ "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"
+}

e16/S1-ABCLODO16-dbe_kt22/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8964116838900632,
+  "choice": 1.0645523608216696,
+  "score": 0.9908947045186701
+ },
+ "fit": {
+  "noul": {
+   "n": 1801,
+   "T": 0.8964116838900632,
+   "ce_before": 0.523769736289978,
+   "ce_after": 0.5224588513374329
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0645523608216696,
+   "ce_before": 0.6695350408554077,
+   "ce_after": 0.668681263923645
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9908947045186701,
+   "ce_before": 1.0616679191589355,
+   "ce_after": 1.0616401433944702
+  }
+ },
+ "source": "models/e16/S1-ABCLODO16-dbe_kt22/ckpt-16000"
+}

e16/S1-ABCLODO16-dbe_kt22/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74af233a1c3531f82c8ccef560cf7ff9bdf11f898ee9893856d42da0594558ac
+size 393464

e16/S1-ABCLODO16-dbe_kt22/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/e16/S1-ABCLODO16-dbe_kt22/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e15/F1-pool-jev-LODO-dbe_kt22",
+  "data_manifest": {
+   "arm": "F1-pool-jev-LODO-dbe_kt22",
+   "name": "F1-pool-jev-LODO-dbe_kt22",
+   "train_sha256": "d321705ae078df70e6fb8378e2ab3992c55c81d7125903e755087236f3c7d3f0",
+   "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": "bc7c08e836bd99bb2665b02903cd41404ea029ecfa9b68a9ec1a7cda96958ba4",
+  "event": "ckpt",
+  "tag": "ckpt-16000",
+  "rows_seen": 16000,
+  "replay_seen": 842,
+  "step": 500,
+  "tokens": 10730354,
+  "tok_per_s": 840.9496345699852,
+  "rows_per_s": 1.3199260469894747,
+  "val": {
+   "n": 1914,
+   "dropped_long": 0,
+   "noul_ce": 0.523769736289978,
+   "noul_T": 0.8964116838900632,
+   "choice_ce": 0.6695350408554077,
+   "choice_T": 1.0645523608216696,
+   "score_ce": 1.0616679191589355,
+   "score_T": 0.9908947045186701,
+   "noul_auc": 0.7855084015864272,
+   "noul_acc": 0.7438739789964994,
+   "noul_f1": 0.8075405523893029,
+   "noul_nll": 0.5284214743816206,
+   "noul_ece": 0.04346177069733274,
+   "noul_brier": 0.17581084150535936,
+   "noul_sharp": 0.22804896533489227,
+   "entropy": 0.5513442754745483
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.23796796798706
+ }
+}

e16/S1-ABCLODO16-dbe_kt22/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "12:01:21", "event": "start", "data": "data/e15/F1-pool-jev-LODO-dbe_kt22", "data_manifest": {"arm": "F1-pool-jev-LODO-dbe_kt22", "name": "F1-pool-jev-LODO-dbe_kt22", "train_sha256": "d321705ae078df70e6fb8378e2ab3992c55c81d7125903e755087236f3c7d3f0", "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": "bc7c08e836bd99bb2665b02903cd41404ea029ecfa9b68a9ec1a7cda96958ba4", "device": "cuda", "load_s": 77.7930691242218}
+{"time": "12:05:34", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 854.6336254436715, "loss": 0.582719225436449, "entropy": 0.6042570620775223, "sharp": 0.173474813811481}
+{"time": "12:09:38", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 874.7017837949154, "loss": 0.6250574458390474, "entropy": 0.6123027205467224, "sharp": 0.16889649629592896}
+{"time": "12:13:41", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 880.471307253779, "loss": 0.5657559987157583, "entropy": 0.5535641126334667, "sharp": 0.22709513176232576}
+{"time": "12:17:36", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 886.8846811684233, "loss": 0.5546395815908909, "entropy": 0.6175807490944862, "sharp": 0.16890976950526237}
+{"time": "12:21:35", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 891.7358214808285, "loss": 0.6462056711316109, "entropy": 0.6015858538448811, "sharp": 0.1931078303605318}
+{"time": "12:25:29", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 893.6547148402539, "loss": 0.5537302251905203, "entropy": 0.5585858039557934, "sharp": 0.2220302615314722}
+{"time": "12:29:30", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 894.3860891689695, "loss": 0.574165316298604, "entropy": 0.5979467257857323, "sharp": 0.1631963588297367}
+{"time": "12:33:33", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 893.8806330772487, "loss": 0.5857264781370759, "entropy": 0.5909840483218431, "sharp": 0.19981277734041214}
+{"time": "12:37:34", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 895.4096251284609, "loss": 0.6727115549147129, "entropy": 0.6053775995969772, "sharp": 0.16680541448295116}
+{"time": "12:41:24", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 896.1081216782511, "loss": 0.6170963272452354, "entropy": 0.5709835849702358, "sharp": 0.21026402805000544}
+{"time": "12:43:05", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5528644919395447, "noul_T": 1.0918827662278154, "noul_auc": 0.7482274532047646, "noul_acc": 0.732, "noul_f1": 0.804093567251462, "noul_nll": 0.5528645245581866, "noul_ece": 0.07631387627124786, "noul_brier": 0.18523654082300703, "noul_sharp": 0.24440282583236694, "entropy": 0.5324379801750183}
+{"time": "12:46:55", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 863.0759358685602, "loss": 0.5410706344991922, "entropy": 0.5873692408204079, "sharp": 0.19808154739439487}
+{"time": "12:50:55", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 865.584627010061, "loss": 0.5581128261983395, "entropy": 0.5743535356596112, "sharp": 0.21545443311333656}
+{"time": "12:54:56", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 868.1229504650963, "loss": 0.6024081464856863, "entropy": 0.5931085785850883, "sharp": 0.1931005734950304}
+{"time": "12:58:55", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 871.2363037914033, "loss": 0.5195386363193393, "entropy": 0.523485716432333, "sharp": 0.2539975754916668}
+{"time": "13:02:50", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 873.23756992379, "loss": 0.6895025698468089, "entropy": 0.5884950812906027, "sharp": 0.19000737369060516}
+{"time": "13:06:39", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 875.217113632087, "loss": 0.6265943311154842, "entropy": 0.5497958846390247, "sharp": 0.2322804220020771}
+{"time": "13:10:45", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 877.0745344525129, "loss": 0.6053482219576836, "entropy": 0.5878646299242973, "sharp": 0.19934971258044243}
+{"time": "13:14:46", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 878.2190252384693, "loss": 0.5761304832994938, "entropy": 0.5974140018224716, "sharp": 0.18182115256786346}
+{"time": "13:18:38", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 879.3167417350454, "loss": 0.5573180224746466, "entropy": 0.48482629284262657, "sharp": 0.28050963766872883}
+{"time": "13:22:34", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 881.1926380099967, "loss": 0.597057449631393, "entropy": 0.5405529728159308, "sharp": 0.24340029247105122}
+{"time": "13:24:15", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5488264560699463, "noul_T": 0.8807817358315996, "noul_auc": 0.7565052467385138, "noul_acc": 0.744, "noul_f1": 0.8112094395280236, "noul_nll": 0.548826448507607, "noul_ece": 0.07595152950286867, "noul_brier": 0.1834586158121481, "noul_sharp": 0.20649057626724243, "entropy": 0.5723315477371216}
+{"time": "13:28:11", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 865.0131198811587, "loss": 0.6332806516438723, "entropy": 0.5958666652441025, "sharp": 0.1833042986690998}
+{"time": "13:32:00", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 866.4665746414382, "loss": 0.4778815135359764, "entropy": 0.5300259962677956, "sharp": 0.2470403052866459}
+{"time": "13:35:57", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 868.0675580765778, "loss": 0.5539845563471317, "entropy": 0.5358861237764359, "sharp": 0.2328292801976204}
+{"time": "13:39:53", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 869.3693636662668, "loss": 0.545749094337225, "entropy": 0.5669929310679436, "sharp": 0.21392999589443207}
+{"time": "13:43:52", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 870.9145161091759, "loss": 0.6043302621692419, "entropy": 0.5925710964947939, "sharp": 0.18129427544772625}
+{"time": "13:47:50", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 872.0130619903067, "loss": 0.5397484395653009, "entropy": 0.5192984640598297, "sharp": 0.26870331540703773}
+{"time": "13:51:52", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 872.9576490858688, "loss": 0.5164455752819777, "entropy": 0.5969343390315771, "sharp": 0.18984217755496502}
+{"time": "13:55:51", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 873.8291634636884, "loss": 0.5927920341491699, "entropy": 0.5688162297010422, "sharp": 0.21189415082335472}
+{"time": "13:59:48", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 874.6052367845189, "loss": 0.6062708608806133, "entropy": 0.5770974978804588, "sharp": 0.20987157989293337}
+{"time": "14:03:49", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 875.6863304642785, "loss": 0.6373758688569069, "entropy": 0.5518503915518522, "sharp": 0.2228580117225647}
+{"time": "14:05:29", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5371318459510803, "noul_T": 0.9677995717172543, "noul_auc": 0.7649071185479296, "noul_acc": 0.736, "noul_f1": 0.8092485549132948, "noul_nll": 0.5371318057253957, "noul_ece": 0.04437962770462037, "noul_brier": 0.17918045328209448, "noul_sharp": 0.22969210147857666, "entropy": 0.5442875027656555}
+{"time": "14:09:22", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 864.9545745469454, "loss": 0.5842806994915009, "entropy": 0.5905364714562893, "sharp": 0.1926712617278099}
+{"time": "14:13:17", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 865.9211318924124, "loss": 0.5801789509132504, "entropy": 0.5392513461410999, "sharp": 0.22827341593801975}
+{"time": "14:17:21", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 867.3535305107463, "loss": 0.5542630534619093, "entropy": 0.5843409597873688, "sharp": 0.1921156169846654}
+{"time": "14:21:14", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 868.264775716467, "loss": 0.6004641242325306, "entropy": 0.5943165458738804, "sharp": 0.17410381883382797}
+{"time": "14:25:12", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 869.4849367682743, "loss": 0.5992267755791545, "entropy": 0.5764070097357035, "sharp": 0.20615196228027344}
+{"time": "14:29:10", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 870.3944199382048, "loss": 0.6701882146298885, "entropy": 0.5786745920777321, "sharp": 0.1984860971570015}
+{"time": "14:33:08", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 871.4863586603616, "loss": 0.5701268408447504, "entropy": 0.5872479639947414, "sharp": 0.20344267506152391}
+{"time": "14:37:06", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 872.1241215005757, "loss": 0.6483441926538944, "entropy": 0.5617897305637598, "sharp": 0.20677760802209377}
+{"time": "14:41:04", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 872.8556959185188, "loss": 0.6229835897684097, "entropy": 0.569515073671937, "sharp": 0.21253077685832977}
+{"time": "14:45:04", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 873.5158971550646, "loss": 0.49271385930478573, "entropy": 0.5543322563171387, "sharp": 0.2247193232178688}
+{"time": "14:46:45", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5465988516807556, "noul_T": 0.9819281990534433, "noul_auc": 0.7577283040272262, "noul_acc": 0.746, "noul_f1": 0.8107302533532041, "noul_nll": 0.5465988734066486, "noul_ece": 0.0627106551527977, "noul_brier": 0.18306542833596912, "noul_sharp": 0.22753268480300903, "entropy": 0.5506075024604797}
+{"time": "14:50:40", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 865.6849074311003, "loss": 0.5971751734614372, "entropy": 0.5623155329376459, "sharp": 0.21381733193993568}
+{"time": "14:54:41", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 866.581947565439, "loss": 0.5986406803131104, "entropy": 0.5723493304103613, "sharp": 0.20709266141057014}
+{"time": "14:58:38", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 867.5138636935129, "loss": 0.5864947848021984, "entropy": 0.5809358526021242, "sharp": 0.20279986783862114}
+{"time": "15:02:40", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 868.2473183105307, "loss": 0.6085152495652437, "entropy": 0.6049098633229733, "sharp": 0.1698884917423129}
+{"time": "15:06:37", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 869.1208061154979, "loss": 0.60585174895823, "entropy": 0.6029114276170731, "sharp": 0.17166141793131828}
+{"time": "15:10:36", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 869.7018580684352, "loss": 0.5961096733808517, "entropy": 0.5496900510042906, "sharp": 0.23098980262875557}
+{"time": "15:14:38", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 870.1545637924373, "loss": 0.5715046022087336, "entropy": 0.5688555240631104, "sharp": 0.20814169198274612}
+{"time": "15:18:33", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 870.8417161492936, "loss": 0.5657782927155495, "entropy": 0.5746859516948462, "sharp": 0.2150105219334364}
+{"time": "15:22:28", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 871.341604495359, "loss": 0.564074132591486, "entropy": 0.5697712451219559, "sharp": 0.21025255136191845}
+{"time": "15:26:28", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 871.8940079602129, "loss": 0.5648910887539387, "entropy": 0.5564267709851265, "sharp": 0.22807436529546976}
+{"time": "15:28:09", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5455800294876099, "noul_T": 0.9644782841454859, "noul_auc": 0.7584018718094158, "noul_acc": 0.746, "noul_f1": 0.8101644245142003, "noul_nll": 0.5455800273939967, "noul_ece": 0.05679123646020889, "noul_brier": 0.18276011978036122, "noul_sharp": 0.22573888301849365, "entropy": 0.5532190203666687}
+{"time": "15:34:03", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 10730354, "tok_per_s": 840.9496345699852, "rows_per_s": 1.3199260469894747, "val": {"n": 1914, "dropped_long": 0, "noul_ce": 0.523769736289978, "noul_T": 0.8964116838900632, "choice_ce": 0.6695350408554077, "choice_T": 1.0645523608216696, "score_ce": 1.0616679191589355, "score_T": 0.9908947045186701, "noul_auc": 0.7855084015864272, "noul_acc": 0.7438739789964994, "noul_f1": 0.8075405523893029, "noul_nll": 0.5284214743816206, "noul_ece": 0.04346177069733274, "noul_brier": 0.17581084150535936, "noul_sharp": 0.22804896533489227, "entropy": 0.5513442754745483}, "dropped_long": 0, "peak_gib": 18.23796796798706}