backup e16/S1-ABCLODO16-xes3g5m (Pod B)

e16/S1-ABCLODO16-xes3g5m/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-xes3g5m/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",
+    "in_proj_qkv",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "out_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "up_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-xes3g5m/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b5374a09ebe3313416d759e60f2040de8556c3da7d71753c18586f646d1c8f
+size 160486456

e16/S1-ABCLODO16-xes3g5m/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-xes3g5m/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea9cba6c11ce5b7da7bc9e67d665e1f6bf771d3a59a7f4a6738f0080c7c75c73
+size 176641832

e16/S1-ABCLODO16-xes3g5m/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00044250194332562387,
+  -0.0004427573876455426,
+  -0.002515261759981513,
+  -0.0018425389425829053,
+  -0.0010149205336347222,
+  0.0017628689529374242,
+  0.001181533676572144,
+  -0.002392465015873313,
+  -5.942553252680227e-05,
+  -0.00022873528359923512,
+  0.00035611301427707076,
+  0.0009066389175131917,
+  -0.0001335123524768278,
+  -0.003954227548092604,
+  -0.0051437076181173325,
+  -0.005590393673628569,
+  -0.0056053586304187775,
+  -0.004702459555119276,
+  -0.00513436971232295,
+  -0.005502124782651663,
+  -0.004379077814519405,
+  -0.003983685281127691,
+  -0.005911420099437237,
+  -0.003933779429644346
+ ],
+ "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-xes3g5m/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.9045858651383833,
+  "choice": 1.0744958476910513,
+  "score": 0.9966783767332946
+ },
+ "fit": {
+  "noul": {
+   "n": 1801,
+   "T": 0.9045858651383833,
+   "ce_before": 0.5407951474189758,
+   "ce_after": 0.5397862195968628
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0744958476910513,
+   "ce_before": 0.6649215817451477,
+   "ce_after": 0.6637855768203735
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9966783767332946,
+   "ce_before": 1.0628070831298828,
+   "ce_after": 1.0628023147583008
+  }
+ },
+ "source": "models/e16/S1-ABCLODO16-xes3g5m/ckpt-16000"
+}

e16/S1-ABCLODO16-xes3g5m/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7351155b46f79d436fc653ce31d5aceec9bb42a843aab5360a4bc4ed4cad2a4
+size 393464

e16/S1-ABCLODO16-xes3g5m/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-xes3g5m/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e15/F1-pool-jev-LODO-xes3g5m",
+  "data_manifest": {
+   "arm": "F1-pool-jev-LODO-xes3g5m",
+   "name": "F1-pool-jev-LODO-xes3g5m",
+   "train_sha256": "ce799a89a01d9d562c86ab0b0dad769d2edf4a718f3a3bca8910d657ad572f8c",
+   "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": 10744046,
+  "tok_per_s": 842.0854866022604,
+  "rows_per_s": 1.3200244822788152,
+  "val": {
+   "n": 1914,
+   "dropped_long": 0,
+   "noul_ce": 0.5407951474189758,
+   "noul_T": 0.9045858651383833,
+   "choice_ce": 0.6649215817451477,
+   "choice_T": 1.0744958476910513,
+   "score_ce": 1.0628070831298828,
+   "score_T": 0.9966783767332946,
+   "noul_auc": 0.7698139449367163,
+   "noul_acc": 0.7263710618436406,
+   "noul_f1": 0.7922020381036774,
+   "noul_nll": 0.5459416545753649,
+   "noul_ece": 0.03983069845022092,
+   "noul_brier": 0.1832468902866895,
+   "noul_sharp": 0.2157512605190277,
+   "entropy": 0.5649888515472412
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.23796796798706
+ }
+}

e16/S1-ABCLODO16-xes3g5m/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "06:35:33", "event": "start", "data": "data/e15/F1-pool-jev-LODO-xes3g5m", "data_manifest": {"arm": "F1-pool-jev-LODO-xes3g5m", "name": "F1-pool-jev-LODO-xes3g5m", "train_sha256": "ce799a89a01d9d562c86ab0b0dad769d2edf4a718f3a3bca8910d657ad572f8c", "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": 83.81045627593994}
+{"time": "06:39:34", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 895.3914259687574, "loss": 0.6400964707136154, "entropy": 0.6002822890877724, "sharp": 0.17962706740945578}
+{"time": "06:43:36", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 900.346019202699, "loss": 0.6109463702887297, "entropy": 0.5951504521071911, "sharp": 0.1839375291019678}
+{"time": "06:47:39", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 899.1086113682769, "loss": 0.5776976142078638, "entropy": 0.5675550773739815, "sharp": 0.21200897358357906}
+{"time": "06:51:36", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 900.7590993172112, "loss": 0.564489733427763, "entropy": 0.6208629012107849, "sharp": 0.16711855586618185}
+{"time": "06:55:34", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 903.002247462646, "loss": 0.6686192825436592, "entropy": 0.5830763038247824, "sharp": 0.20287082344293594}
+{"time": "06:59:28", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 902.7776049013379, "loss": 0.5581513121724129, "entropy": 0.584723336622119, "sharp": 0.1991353165358305}
+{"time": "07:03:27", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 902.5844851491031, "loss": 0.593255759216845, "entropy": 0.6082150265574455, "sharp": 0.1562352441251278}
+{"time": "07:07:28", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 902.2490037053722, "loss": 0.6168863605707884, "entropy": 0.6070262491703033, "sharp": 0.18747281655669212}
+{"time": "07:11:29", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 903.1816062769974, "loss": 0.6556607000529766, "entropy": 0.5827947799116373, "sharp": 0.1986649688333273}
+{"time": "07:15:17", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 903.2111377168986, "loss": 0.5909067206084728, "entropy": 0.5599776618182659, "sharp": 0.2065832642838359}
+{"time": "07:16:57", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5680442452430725, "noul_T": 1.094949060925051, "noul_auc": 0.7432089695824807, "noul_acc": 0.708, "noul_f1": 0.7746913580246914, "noul_nll": 0.5680442335233092, "noul_ece": 0.0918515951037407, "noul_brier": 0.19329628678625618, "noul_sharp": 0.2274375706911087, "entropy": 0.5491006374359131}
+{"time": "07:20:48", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 869.4949508029603, "loss": 0.5396197242662311, "entropy": 0.5859172604978085, "sharp": 0.18899868056178093}
+{"time": "07:24:47", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 871.6481098911597, "loss": 0.6121177710592747, "entropy": 0.5366751570254564, "sharp": 0.2478839885443449}
+{"time": "07:28:49", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 873.7269059395471, "loss": 0.6052731554955244, "entropy": 0.5963765103369951, "sharp": 0.18653630837798119}
+{"time": "07:32:51", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 876.194725540872, "loss": 0.5381726110354066, "entropy": 0.5414764247834682, "sharp": 0.23788123950362206}
+{"time": "07:36:45", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 877.6532593469266, "loss": 0.6435420801863074, "entropy": 0.5981589946895838, "sharp": 0.1795908808708191}
+{"time": "07:40:32", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 879.4896052948235, "loss": 0.6610072152689099, "entropy": 0.5762741910293698, "sharp": 0.20037797652184963}
+{"time": "07:44:39", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 881.2680289414254, "loss": 0.585918489843607, "entropy": 0.5840070471167564, "sharp": 0.19837483391165733}
+{"time": "07:48:40", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 881.9323486112067, "loss": 0.561856109648943, "entropy": 0.5772623820230365, "sharp": 0.19215230643749237}
+{"time": "07:52:30", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 882.9921481752443, "loss": 0.5564196361228824, "entropy": 0.52583297342062, "sharp": 0.24734552949666977}
+{"time": "07:56:27", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 884.5112903822227, "loss": 0.5828118091449142, "entropy": 0.5437588598579168, "sharp": 0.23686270229518414}
+{"time": "07:58:08", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5606597661972046, "noul_T": 0.933144182976614, "noul_auc": 0.7468471777649507, "noul_acc": 0.724, "noul_f1": 0.7952522255192879, "noul_nll": 0.5606597882807255, "noul_ece": 0.05754222053289414, "noul_brier": 0.18894549412119235, "noul_sharp": 0.2043958157300949, "entropy": 0.5733844637870789}
+{"time": "08:02:03", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 868.1769402867884, "loss": 0.5926663260906935, "entropy": 0.6019470784813166, "sharp": 0.18010499700903893}
+{"time": "08:05:53", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 869.4701599859625, "loss": 0.5275128167122602, "entropy": 0.512208852916956, "sharp": 0.25839984230697155}
+{"time": "08:09:49", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 870.793923477815, "loss": 0.5535645475611091, "entropy": 0.5604903120547533, "sharp": 0.20851518772542477}
+{"time": "08:13:47", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 871.9239490706541, "loss": 0.5605363100767136, "entropy": 0.5614703148603439, "sharp": 0.22105170227587223}
+{"time": "08:17:46", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 873.4229164549173, "loss": 0.5997957233339548, "entropy": 0.5718167759478092, "sharp": 0.2007963564246893}
+{"time": "08:21:45", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 874.2990672449902, "loss": 0.5677495561540127, "entropy": 0.5619004815816879, "sharp": 0.23214998096227646}
+{"time": "08:25:48", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 875.325717574354, "loss": 0.5646688919514418, "entropy": 0.6073211524635553, "sharp": 0.17946111131459475}
+{"time": "08:29:47", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 876.0806432453703, "loss": 0.6109884493052959, "entropy": 0.5868619568645954, "sharp": 0.19545931369066238}
+{"time": "08:33:44", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 876.778792829955, "loss": 0.6100507080554962, "entropy": 0.5773353390395641, "sharp": 0.21015083696693182}
+{"time": "08:37:46", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 877.7304064783515, "loss": 0.6564334984868765, "entropy": 0.524394785054028, "sharp": 0.24260113015770912}
+{"time": "08:39:26", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5517610311508179, "noul_T": 1.0589391539871706, "noul_auc": 0.7526368263630163, "noul_acc": 0.72, "noul_f1": 0.7971014492753623, "noul_nll": 0.5517610460445285, "noul_ece": 0.08581498813629151, "noul_brier": 0.18596073872151, "noul_sharp": 0.230805441737175, "entropy": 0.5395169854164124}
+{"time": "08:43:18", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 866.9663200264135, "loss": 0.5804359838366508, "entropy": 0.6001070402562618, "sharp": 0.1800562236458063}
+{"time": "08:47:14", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 868.0283067011337, "loss": 0.5500270696356893, "entropy": 0.5598568730056286, "sharp": 0.21481758635491133}
+{"time": "08:51:18", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 869.4223518339055, "loss": 0.5743823237717152, "entropy": 0.5970825143158436, "sharp": 0.1804541666060686}
+{"time": "08:55:14", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 870.2388807111691, "loss": 0.5932586807757616, "entropy": 0.5574623048305511, "sharp": 0.20524157211184502}
+{"time": "08:59:16", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 871.1908490813215, "loss": 0.6298261033371091, "entropy": 0.5840919520705938, "sharp": 0.199787475168705}
+{"time": "09:03:15", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 871.9880868739817, "loss": 0.6696434244513512, "entropy": 0.5840845368802547, "sharp": 0.18666459899395704}
+{"time": "09:07:16", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 872.8442378740019, "loss": 0.5552999768406153, "entropy": 0.5681333672255278, "sharp": 0.21301064640283585}
+{"time": "09:11:13", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 873.539707119155, "loss": 0.6721382103860378, "entropy": 0.57978805154562, "sharp": 0.18642971944063902}
+{"time": "09:15:11", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 874.1942212118252, "loss": 0.6273027397692204, "entropy": 0.5719568626955152, "sharp": 0.21323172748088837}
+{"time": "09:19:13", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 874.7635361494006, "loss": 0.566404378041625, "entropy": 0.5726980231702328, "sharp": 0.20746181346476078}
+{"time": "09:20:53", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5585575103759766, "noul_T": 0.9436484224018707, "noul_auc": 0.749890678840671, "noul_acc": 0.716, "noul_f1": 0.78419452887538, "noul_nll": 0.5585574712604284, "noul_ece": 0.07099086409807208, "noul_brier": 0.18886044593341972, "noul_sharp": 0.2083398401737213, "entropy": 0.5693234205245972}
+{"time": "09:24:49", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 866.8747995313847, "loss": 0.5730536775663495, "entropy": 0.5574533771723509, "sharp": 0.22644141130149364}
+{"time": "09:28:47", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 867.8579908939106, "loss": 0.5990699827671051, "entropy": 0.5722697079181671, "sharp": 0.20612954907119274}
+{"time": "09:32:44", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 868.7279345427843, "loss": 0.6226212922483683, "entropy": 0.5967363733798265, "sharp": 0.18528218381106853}
+{"time": "09:36:47", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 869.3740748143927, "loss": 0.619580402970314, "entropy": 0.6158276051282883, "sharp": 0.1642099991440773}
+{"time": "09:40:44", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 870.2667009629394, "loss": 0.5985166346654296, "entropy": 0.6030270997434855, "sharp": 0.16814589779824018}
+{"time": "09:44:45", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 870.9420680283052, "loss": 0.6091124080121517, "entropy": 0.5465963892638683, "sharp": 0.23021978698670864}
+{"time": "09:48:47", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 871.3932970103745, "loss": 0.6081517990678549, "entropy": 0.5864070616662502, "sharp": 0.18609152920544147}
+{"time": "09:52:44", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 872.0350015710451, "loss": 0.5961437691003084, "entropy": 0.5794455576688051, "sharp": 0.20215598121285439}
+{"time": "09:56:41", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 872.4777246361316, "loss": 0.5870085638016462, "entropy": 0.5797422826290131, "sharp": 0.19784089550375938}
+{"time": "10:00:41", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 872.9500298515728, "loss": 0.6085839904844761, "entropy": 0.573230616748333, "sharp": 0.21435772720724344}
+{"time": "10:02:22", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5602756142616272, "noul_T": 0.9633077045468452, "noul_auc": 0.7507827395007959, "noul_acc": 0.722, "noul_f1": 0.7864823348694316, "noul_nll": 0.5602756090462208, "noul_ece": 0.05254515117406845, "noul_brier": 0.18970373201750446, "noul_sharp": 0.21209144592285156, "entropy": 0.5674711465835571}
+{"time": "10:09:35", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 10744046, "tok_per_s": 842.0854866022604, "rows_per_s": 1.3200244822788152, "val": {"n": 1914, "dropped_long": 0, "noul_ce": 0.5407951474189758, "noul_T": 0.9045858651383833, "choice_ce": 0.6649215817451477, "choice_T": 1.0744958476910513, "score_ce": 1.0628070831298828, "score_T": 0.9966783767332946, "noul_auc": 0.7698139449367163, "noul_acc": 0.7263710618436406, "noul_f1": 0.7922020381036774, "noul_nll": 0.5459416545753649, "noul_ece": 0.03983069845022092, "noul_brier": 0.1832468902866895, "noul_sharp": 0.2157512605190277, "entropy": 0.5649888515472412}, "dropped_long": 0, "peak_gib": 18.23796796798706}