backup e16/S1-ABCLODO16-nips34 (Pod B)

e16/S1-ABCLODO16-nips34/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-nips34/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_z",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "out_proj",
+    "gate_proj",
+    "in_proj_qkv",
+    "q_proj",
+    "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
+}

e16/S1-ABCLODO16-nips34/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d412f32cfb9fda592e2d6eca2a0e445125f6640c94b8298e6e8e530949628f14
+size 160486456

e16/S1-ABCLODO16-nips34/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-nips34/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5ea3a2db3cc264267d229595568b31d264573cfdf554f5b347982993fe305f
+size 176641832

e16/S1-ABCLODO16-nips34/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00037709137541241944,
+  -0.00037735069054178894,
+  -0.0027201834600418806,
+  -0.001901994226500392,
+  -0.0008279570029117167,
+  0.0018933265237137675,
+  0.0011228469666093588,
+  -0.002297227503731847,
+  -0.0002648523368407041,
+  0.00010398461017757654,
+  0.00035337533336132765,
+  0.00036609743256121874,
+  0.00035324980854056776,
+  -0.004104902967810631,
+  -0.004933446645736694,
+  -0.005380893591791391,
+  -0.005537974648177624,
+  -0.004482411313802004,
+  -0.0050194417126476765,
+  -0.0052953907288610935,
+  -0.004336507525295019,
+  -0.003729609539732337,
+  -0.005816658493131399,
+  -0.0037010323721915483
+ ],
+ "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-nips34/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8704294267162054,
+  "choice": 1.0495197142559871,
+  "score": 0.9643243257790365
+ },
+ "fit": {
+  "noul": {
+   "n": 1801,
+   "T": 0.8704294267162054,
+   "ce_before": 0.5117048025131226,
+   "ce_after": 0.5095264315605164
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0495197142559871,
+   "ce_before": 0.6699819564819336,
+   "ce_after": 0.6694608926773071
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9643243257790365,
+   "ce_before": 1.0489827394485474,
+   "ce_after": 1.0485860109329224
+  }
+ },
+ "source": "models/e16/S1-ABCLODO16-nips34/ckpt-16000"
+}

e16/S1-ABCLODO16-nips34/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3baa8c986a9b5ba0324d9fb6aaf3f401d36eab5312d9f670ce61ec9ce21952cd
+size 393464

e16/S1-ABCLODO16-nips34/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-nips34/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e15/F1-pool-jev-LODO-nips34",
+  "data_manifest": {
+   "arm": "F1-pool-jev-LODO-nips34",
+   "name": "F1-pool-jev-LODO-nips34",
+   "train_sha256": "245ca628d70b60dfab08c9f3a26e378e68f0c6f84f0900e977800d68fc0636d8",
+   "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": 10804252,
+  "tok_per_s": 843.1949043402115,
+  "rows_per_s": 1.3143981251844525,
+  "val": {
+   "n": 1914,
+   "dropped_long": 0,
+   "noul_ce": 0.5117048025131226,
+   "noul_T": 0.8704294267162054,
+   "choice_ce": 0.6699819564819336,
+   "choice_T": 1.0495197142559871,
+   "score_ce": 1.0489827394485474,
+   "score_T": 0.9643243257790365,
+   "noul_auc": 0.7790549828178694,
+   "noul_acc": 0.7520420070011669,
+   "noul_f1": 0.8256052523594584,
+   "noul_nll": 0.5159688715669767,
+   "noul_ece": 0.04287605681385988,
+   "noul_brier": 0.1704286281781888,
+   "noul_sharp": 0.2341597080230713,
+   "entropy": 0.5461862087249756
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.23796796798706
+ }
+}

e16/S1-ABCLODO16-nips34/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "01:05:02", "event": "start", "data": "data/e15/F1-pool-jev-LODO-nips34", "data_manifest": {"arm": "F1-pool-jev-LODO-nips34", "name": "F1-pool-jev-LODO-nips34", "train_sha256": "245ca628d70b60dfab08c9f3a26e378e68f0c6f84f0900e977800d68fc0636d8", "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": 90.33989787101746}
+{"time": "01:09:04", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 895.1667977824525, "loss": 0.6081564333289862, "entropy": 0.5547713190317154, "sharp": 0.22806158103048801}
+{"time": "01:13:09", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 899.2154921738359, "loss": 0.5709814727306366, "entropy": 0.5441936701536179, "sharp": 0.2364728692919016}
+{"time": "01:17:10", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 899.6712268567306, "loss": 0.5537567250430584, "entropy": 0.525471169501543, "sharp": 0.2532952893525362}
+{"time": "01:21:09", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 902.2621121735169, "loss": 0.587475435808301, "entropy": 0.6267548315227032, "sharp": 0.16385282762348652}
+{"time": "01:25:13", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 902.1004359293853, "loss": 0.6447278764098883, "entropy": 0.5853160489350557, "sharp": 0.20546626672148705}
+{"time": "01:29:05", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 902.817317583147, "loss": 0.553057499229908, "entropy": 0.567755838856101, "sharp": 0.22217054665088654}
+{"time": "01:33:05", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 903.3620250998804, "loss": 0.5913794161751866, "entropy": 0.5273975934833288, "sharp": 0.23073335736989975}
+{"time": "01:37:07", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 902.7002511550693, "loss": 0.6144660962745547, "entropy": 0.5888736816123128, "sharp": 0.20118617825210094}
+{"time": "01:41:07", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 903.9103415493196, "loss": 0.6365818595513701, "entropy": 0.5563330063596368, "sharp": 0.22292824275791645}
+{"time": "01:44:55", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 903.8852119633111, "loss": 0.5987623855471611, "entropy": 0.5363389551639557, "sharp": 0.24652124848216772}
+{"time": "01:46:36", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5539748072624207, "noul_T": 1.1150613383098502, "noul_auc": 0.7366434378629501, "noul_acc": 0.734, "noul_f1": 0.813986013986014, "noul_nll": 0.5539747409671545, "noul_ece": 0.06709418308734894, "noul_brier": 0.18613331596553725, "noul_sharp": 0.2547200620174408, "entropy": 0.5269979238510132}
+{"time": "01:50:29", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 869.7410784178411, "loss": 0.5269262790679932, "entropy": 0.5756323710083961, "sharp": 0.21107020042836666}
+{"time": "01:54:31", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 871.7464884372469, "loss": 0.5771820480003953, "entropy": 0.503880949690938, "sharp": 0.27522504329681396}
+{"time": "01:58:32", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 874.0160635069062, "loss": 0.5770479831844568, "entropy": 0.6104616802185774, "sharp": 0.1797542590647936}
+{"time": "02:02:35", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 876.3917115341146, "loss": 0.5478026736527681, "entropy": 0.480885187163949, "sharp": 0.28024033084511757}
+{"time": "02:06:31", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 878.0376871406563, "loss": 0.6272200318053365, "entropy": 0.5670340340584517, "sharp": 0.20876357331871986}
+{"time": "02:10:20", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 879.8594074468627, "loss": 0.6103469310328364, "entropy": 0.5369548508897424, "sharp": 0.23639588989317417}
+{"time": "02:14:28", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 881.5288386829342, "loss": 0.5965513922274113, "entropy": 0.5410613343119621, "sharp": 0.24300893023610115}
+{"time": "02:18:29", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 882.8125134967648, "loss": 0.5597183015197515, "entropy": 0.5867893025279045, "sharp": 0.1978574190288782}
+{"time": "02:22:18", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 883.9002784436682, "loss": 0.5524098463356495, "entropy": 0.5014245510101318, "sharp": 0.27559840492904186}
+{"time": "02:26:18", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 885.1727027513211, "loss": 0.5926805483177304, "entropy": 0.5926058255136013, "sharp": 0.19789239577949047}
+{"time": "02:28:00", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5540652275085449, "noul_T": 0.7262186068922203, "noul_auc": 0.7444105691056911, "noul_acc": 0.728, "noul_f1": 0.8084507042253521, "noul_nll": 0.5540652163028718, "noul_ece": 0.0820941023826599, "noul_brier": 0.1854434630687669, "noul_sharp": 0.18022963404655457, "entropy": 0.603283703327179}
+{"time": "02:31:57", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 868.7668475376514, "loss": 0.6166052520275116, "entropy": 0.5360413622111082, "sharp": 0.23834474571049213}
+{"time": "02:35:47", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 870.3322355372458, "loss": 0.49887737073004246, "entropy": 0.48201022297143936, "sharp": 0.28353738971054554}
+{"time": "02:39:45", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 871.7810217482727, "loss": 0.5020052269101143, "entropy": 0.5278225354850292, "sharp": 0.24431749992072582}
+{"time": "02:43:43", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 872.9861682431897, "loss": 0.535607360303402, "entropy": 0.533254612237215, "sharp": 0.24454083666205406}
+{"time": "02:47:43", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 874.214502003311, "loss": 0.5580518562346697, "entropy": 0.5774025805294514, "sharp": 0.1978490687906742}
+{"time": "02:51:41", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 875.5449911358467, "loss": 0.5251100417226553, "entropy": 0.4955702871084213, "sharp": 0.28454206604510546}
+{"time": "02:55:45", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 876.604157100171, "loss": 0.5398826310411096, "entropy": 0.5904733054339886, "sharp": 0.1965536130592227}
+{"time": "02:59:44", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 877.4496027672578, "loss": 0.5669517852365971, "entropy": 0.5411127023398876, "sharp": 0.2413452174514532}
+{"time": "03:03:42", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 878.2672695856289, "loss": 0.5512564294040203, "entropy": 0.5532778948545456, "sharp": 0.23241716995835304}
+{"time": "03:07:46", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 879.1770811930362, "loss": 0.5901628835126758, "entropy": 0.542279020883143, "sharp": 0.224813312292099}
+{"time": "03:09:28", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5419799089431763, "noul_T": 1.0025704443402235, "noul_auc": 0.7507077526132404, "noul_acc": 0.724, "noul_f1": 0.8011527377521613, "noul_nll": 0.5419799349680543, "noul_ece": 0.07044993710517883, "noul_brier": 0.18239340755092023, "noul_sharp": 0.23407718539237976, "entropy": 0.5414556860923767}
+{"time": "03:13:21", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 868.3453152247131, "loss": 0.5428530275821686, "entropy": 0.5940081067383289, "sharp": 0.192720303311944}
+{"time": "03:17:18", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 869.2014918991914, "loss": 0.5322753516957164, "entropy": 0.5373967783525586, "sharp": 0.23881784453988075}
+{"time": "03:21:24", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 870.5320476075987, "loss": 0.5225669015198946, "entropy": 0.5532892495393753, "sharp": 0.22287250589579344}
+{"time": "03:25:20", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 871.4169455389298, "loss": 0.6098964959383011, "entropy": 0.541626013815403, "sharp": 0.23185491003096104}
+{"time": "03:29:22", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 872.488981390791, "loss": 0.6072507565841079, "entropy": 0.5930944997817278, "sharp": 0.19157098419964314}
+{"time": "03:33:22", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 873.1937178058898, "loss": 0.6212170049548149, "entropy": 0.5761906765401363, "sharp": 0.20310518704354763}
+{"time": "03:37:21", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 874.1396323775194, "loss": 0.5309572434052825, "entropy": 0.5531360656023026, "sharp": 0.2283371388912201}
+{"time": "03:41:20", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 874.8322204006435, "loss": 0.645755622535944, "entropy": 0.53306735586375, "sharp": 0.22905216552317142}
+{"time": "03:45:17", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 875.5885399517138, "loss": 0.6033470779657364, "entropy": 0.5717220157384872, "sharp": 0.21070896089076996}
+{"time": "03:49:19", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 876.3416051591441, "loss": 0.5588993262499571, "entropy": 0.5403499864041805, "sharp": 0.23974999971687794}
+{"time": "03:51:01", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5431507229804993, "noul_T": 1.0149155232158766, "noul_auc": 0.7439568815331012, "noul_acc": 0.736, "noul_f1": 0.8130311614730878, "noul_nll": 0.5431507168784737, "noul_ece": 0.08238356143236161, "noul_brier": 0.18228612957410775, "noul_sharp": 0.2353409081697464, "entropy": 0.5400134325027466}
+{"time": "03:55:03", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 868.1203946185368, "loss": 0.5770748695358634, "entropy": 0.5502989403903484, "sharp": 0.21771643683314323}
+{"time": "03:59:03", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 868.9403265510879, "loss": 0.5826062262058258, "entropy": 0.5609152559190989, "sharp": 0.2164121102541685}
+{"time": "04:03:01", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 869.8367026618675, "loss": 0.6288668401539326, "entropy": 0.5564761068671942, "sharp": 0.2240370400249958}
+{"time": "04:07:06", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 870.4305017872435, "loss": 0.586422823369503, "entropy": 0.5905444677919149, "sharp": 0.18326434679329395}
+{"time": "04:11:05", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 871.3293089084183, "loss": 0.6021123845130205, "entropy": 0.5894033843651414, "sharp": 0.18402628973126411}
+{"time": "04:15:07", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 871.8292306258045, "loss": 0.5860404875129461, "entropy": 0.523433979600668, "sharp": 0.24922526441514492}
+{"time": "04:19:09", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 872.3817420939995, "loss": 0.5773937180638313, "entropy": 0.562871802598238, "sharp": 0.21234620921313763}
+{"time": "04:23:05", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 873.1275840866748, "loss": 0.5914360731840134, "entropy": 0.5808037351816893, "sharp": 0.20758569054305553}
+{"time": "04:27:00", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 873.7737164529553, "loss": 0.5530982054769993, "entropy": 0.5578135419636965, "sharp": 0.22192480228841305}
+{"time": "04:31:01", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 874.2525934098853, "loss": 0.60325588285923, "entropy": 0.5555567257106304, "sharp": 0.23548231460154057}
+{"time": "04:32:42", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5440235137939453, "noul_T": 0.9760520103298269, "noul_auc": 0.746551974448316, "noul_acc": 0.736, "noul_f1": 0.811965811965812, "noul_nll": 0.5440234857648611, "noul_ece": 0.08069455933570863, "noul_brier": 0.18284940086984888, "noul_sharp": 0.23029829561710358, "entropy": 0.549235463142395}
+{"time": "04:38:38", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 10804252, "tok_per_s": 843.1949043402115, "rows_per_s": 1.3143981251844525, "val": {"n": 1914, "dropped_long": 0, "noul_ce": 0.5117048025131226, "noul_T": 0.8704294267162054, "choice_ce": 0.6699819564819336, "choice_T": 1.0495197142559871, "score_ce": 1.0489827394485474, "score_T": 0.9643243257790365, "noul_auc": 0.7790549828178694, "noul_acc": 0.7520420070011669, "noul_f1": 0.8256052523594584, "noul_nll": 0.5159688715669767, "noul_ece": 0.04287605681385988, "noul_brier": 0.1704286281781888, "noul_sharp": 0.2341597080230713, "entropy": 0.5461862087249756}, "dropped_long": 0, "peak_gib": 18.23796796798706}