E39 train-seed checkpoint E39-M10rt-ts2

e39/S1-E39-M10rt-ts2-syn/DONE

@@ -0,0 +1 @@
+2026-10-29 12:40:31

e39/S1-E39-M10rt-ts2-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

e39/S1-E39-M10rt-ts2-syn/ckpt-16000/adapter/adapter_config.json

@@ -0,0 +1,57 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForCausalLM",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
+  },
+  "base_model_name_or_path": "/workspace/jev_kt/models/hf/JEV-9B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "in_proj_qkv",
+    "in_proj_z",
+    "out_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
+}

e39/S1-E39-M10rt-ts2-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3caae73325e5deb5f55e877fc1c87d931c1da54c9dbba592b6a47adc1c00a500
+size 160486456

e39/S1-E39-M10rt-ts2-syn/ckpt-16000/adapter_vllm/adapter_config.json

@@ -0,0 +1,58 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForCausalLM",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64.0,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "in_proj_qkv",
+    "in_proj_z",
+    "k_proj",
+    "lm_head",
+    "o_proj",
+    "out_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

e39/S1-E39-M10rt-ts2-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c48b47aa70ab22014ced21dda4c62748de42c255300707ce7c70ae5668802985
+size 176641832

e39/S1-E39-M10rt-ts2-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00042568027856759727,
+  -0.00042593429679982364,
+  -0.0026693125255405903,
+  -0.0018267863197252154,
+  -0.0007479671621695161,
+  0.0016414755955338478,
+  0.0012263301759958267,
+  -0.0025517139583826065,
+  -0.00010236329399049282,
+  -0.0005184480105526745,
+  0.00025875758728943765,
+  0.0004096431948710233,
+  -0.00049863156164065,
+  -0.003945255186408758,
+  -0.004657458513975143,
+  -0.00530650932341814,
+  -0.006001691799610853,
+  -0.004606849048286676,
+  -0.004993164446204901,
+  -0.005175268743187189,
+  -0.004082121420651674,
+  -0.003587765619158745,
+  -0.005886952858418226,
+  -0.0035980455577373505
+ ],
+ "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"
+}

e39/S1-E39-M10rt-ts2-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.756268946083386,
+  "choice": 0.9630429435049804,
+  "score": 0.9525498434687176
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.756268946083386,
+   "ce_before": 0.5727526545524597,
+   "ce_after": 0.5671551823616028
+  },
+  "choice": {
+   "n": 60,
+   "T": 0.9630429435049804,
+   "ce_before": 0.6707132458686829,
+   "ce_after": 0.6703933477401733
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9525498434687176,
+   "ce_before": 1.063092589378357,
+   "ce_after": 1.062384009361267
+  }
+ },
+ "source": "models/e39/S1-E39-M10rt-ts2-syn/ckpt-16000"
+}

e39/S1-E39-M10rt-ts2-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7926cd6c3db22d131af2624ccfaa5ed1e5f7d02d6bb4b1974e532e865890b97c
+size 393464

e39/S1-E39-M10rt-ts2-syn/ckpt-16000/judge_config.json

@@ -0,0 +1,164 @@
+{
+ "base_model_path": "/root/models/Qwen3.5-9B",
+ "hidden_size": 4096,
+ "slots": {
+  "num_slots": 24,
+  "ranges": {
+   "noul": [
+    0,
+    2
+   ],
+   "score": [
+    2,
+    8
+   ],
+   "choice": [
+    8,
+    24
+   ]
+  },
+  "verbalizers": [
+   "false",
+   "true",
+   "0",
+   "1",
+   "2",
+   "3",
+   "4",
+   "5",
+   "A",
+   "B",
+   "C",
+   "D",
+   "E",
+   "F",
+   "G",
+   "H",
+   "I",
+   "J",
+   "K",
+   "L",
+   "M",
+   "N",
+   "O",
+   "P"
+  ],
+  "template_version": "bare-v1"
+ },
+ "verbalizer_ids": [
+  3721,
+  1802,
+  15,
+  16,
+  17,
+  18,
+  19,
+  20,
+  32,
+  33,
+  34,
+  35,
+  36,
+  37,
+  38,
+  39,
+  40,
+  41,
+  42,
+  43,
+  44,
+  45,
+  46,
+  47
+ ],
+ "kinds": [
+  "noul",
+  "choice",
+  "score"
+ ],
+ "model_name": "jev-judge-qwen35-9b",
+ "model_version": "0.8.0",
+ "lm_head_included": true,
+ "weights_mode": "unmerged",
+ "adapter_subfolder": "adapter",
+ "lora": {
+  "r": 16,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "target_modules": [
+   "down_proj",
+   "gate_proj",
+   "in_proj_qkv",
+   "in_proj_z",
+   "k_proj",
+   "o_proj",
+   "out_proj",
+   "q_proj",
+   "up_proj",
+   "v_proj"
+  ]
+ },
+ "trained_stage": "e16",
+ "source_checkpoint": "models/e39/S1-E39-M10rt-ts2-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e33/E33-M10-rt-n16k",
+  "data_manifest": {
+   "arm": "E33-M10-rt-n16k",
+   "name": null,
+   "train_sha256": "39574ddaa158a99572227f29fcc2be761352b45f2f70805ff1c7883379ef2228",
+   "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": 2,
+  "replay": "data/e16/replay/train.jsonl",
+  "replay_frac": 0.05,
+  "replay_sha256": "9dd2df19851678750cf79d2fdb47581720930ef2f0c6e18e6fbe23ef2181847e",
+  "max_len": 3072,
+  "schedule": "warmup 0.03 + cosine to x0.05 over 500 steps",
+  "total_rows": 16000,
+  "lora": {
+   "r": 16,
+   "lora_alpha": 32,
+   "lora_dropout": 0.05
+  },
+  "trainer_sha256": "a0b9d7552588ffb068565686509162a4f122f6f03392e693fa20088493e2a4f3",
+  "event": "ckpt",
+  "tag": "ckpt-16000",
+  "rows_seen": 16000,
+  "replay_seen": 842,
+  "step": 500,
+  "tokens": 9820167,
+  "tok_per_s": 802.5078639597049,
+  "rows_per_s": 1.3763347852450893,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5727526545524597,
+   "noul_T": 0.756268946083386,
+   "choice_ce": 0.6707132458686829,
+   "choice_T": 0.9630429435049804,
+   "score_ce": 1.063092589378357,
+   "score_T": 0.9525498434687176,
+   "noul_auc": 0.7205290666666667,
+   "noul_acc": 0.69,
+   "noul_f1": 0.7696879643387816,
+   "noul_nll": 0.591524988912046,
+   "noul_ece": 0.06541209155321123,
+   "noul_brier": 0.20267626322777926,
+   "noul_sharp": 0.15836110711097717,
+   "entropy": 0.6200612187385559
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.236003875732422
+ }
+}

e39/S1-E39-M10rt-ts2-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "09:16:30", "event": "start", "data": "data/e33/E33-M10-rt-n16k", "data_manifest": {"arm": "E33-M10-rt-n16k", "name": null, "train_sha256": "39574ddaa158a99572227f29fcc2be761352b45f2f70805ff1c7883379ef2228", "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": 2, "replay": "data/e16/replay/train.jsonl", "replay_frac": 0.05, "replay_sha256": "9dd2df19851678750cf79d2fdb47581720930ef2f0c6e18e6fbe23ef2181847e", "max_len": 3072, "schedule": "warmup 0.03 + cosine to x0.05 over 500 steps", "total_rows": 16000, "lora": {"r": 16, "lora_alpha": 32, "lora_dropout": 0.05}, "trainer_sha256": "a0b9d7552588ffb068565686509162a4f122f6f03392e693fa20088493e2a4f3", "device": "cuda", "load_s": 86.58909368515015}
+{"time": "09:20:30", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 831.0406864692288, "loss": 0.6510581523180008, "entropy": 0.6628449689596891, "sharp": 0.1030053710564971}
+{"time": "09:24:10", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 831.4932141119137, "loss": 0.6528139859437943, "entropy": 0.5800324156880379, "sharp": 0.1984642269089818}
+{"time": "09:28:05", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 837.0035328284999, "loss": 0.7003905400633812, "entropy": 0.6112290695309639, "sharp": 0.18637951463460922}
+{"time": "09:32:01", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 838.2122615954625, "loss": 0.6757134944200516, "entropy": 0.670067785307765, "sharp": 0.09046235680580139}
+{"time": "09:35:45", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 839.5202496086646, "loss": 0.6990202777087688, "entropy": 0.6168841309845448, "sharp": 0.17453687451779842}
+{"time": "09:39:33", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 839.6123578844778, "loss": 0.6125369668006897, "entropy": 0.6084899753332138, "sharp": 0.16890908125787973}
+{"time": "09:43:16", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 840.7194166370532, "loss": 0.6420796513557434, "entropy": 0.6500925198197365, "sharp": 0.12422364484518766}
+{"time": "09:47:17", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 842.0411488970459, "loss": 0.6853606477379799, "entropy": 0.6656990200281143, "sharp": 0.09239852614700794}
+{"time": "09:51:06", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 842.6754770771137, "loss": 0.6146648600697517, "entropy": 0.6345440819859505, "sharp": 0.12143377494066954}
+{"time": "09:54:54", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 841.5944533626964, "loss": 0.546112846583128, "entropy": 0.6230141147971153, "sharp": 0.15667817369103432}
+{"time": "09:56:24", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5977060794830322, "noul_T": 0.8352790746431655, "noul_auc": 0.7354643803480111, "noul_acc": 0.714, "noul_f1": 0.7704654895666132, "noul_nll": 0.593057998508215, "noul_ece": 0.07757893973588945, "noul_brier": 0.20226671626126627, "noul_sharp": 0.16247330605983734, "entropy": 0.620979368686676}
+{"time": "10:00:20", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 812.8593453824263, "loss": 0.6509331688284874, "entropy": 0.5847092866897583, "sharp": 0.2073003388941288}
+{"time": "10:04:09", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 815.1880556314699, "loss": 0.6412869766354561, "entropy": 0.652700312435627, "sharp": 0.11306645441800356}
+{"time": "10:08:00", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 817.298201033122, "loss": 0.6427236869931221, "entropy": 0.6734615415334702, "sharp": 0.07844028901308775}
+{"time": "10:11:49", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 819.3072084296412, "loss": 0.6368653327226639, "entropy": 0.6350740939378738, "sharp": 0.1489528426900506}
+{"time": "10:15:47", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 821.0140852925135, "loss": 0.6832927539944649, "entropy": 0.6485660001635551, "sharp": 0.13114421535283327}
+{"time": "10:19:40", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 822.693647207475, "loss": 0.6928505599498749, "entropy": 0.6680712923407555, "sharp": 0.09517216123640537}
+{"time": "10:23:33", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 824.4612144462264, "loss": 0.6557623110711575, "entropy": 0.6465953979641199, "sharp": 0.12264378648251295}
+{"time": "10:27:23", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 825.7730658131676, "loss": 0.679605558514595, "entropy": 0.6322944164276123, "sharp": 0.150183099322021}
+{"time": "10:31:09", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 826.6971043640959, "loss": 0.6581827290356159, "entropy": 0.6522229351103306, "sharp": 0.11678315792232752}
+{"time": "10:34:55", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 827.4302128135205, "loss": 0.6283691897988319, "entropy": 0.638420294970274, "sharp": 0.13605591468513012}
+{"time": "10:36:25", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5909906625747681, "noul_T": 0.6979180285452042, "noul_auc": 0.738772341395082, "noul_acc": 0.704, "noul_f1": 0.7730061349693251, "noul_nll": 0.5901871187537908, "noul_ece": 0.06985761046409605, "noul_brier": 0.20155968121796508, "noul_sharp": 0.1421777904033661, "entropy": 0.6310994029045105}
+{"time": "10:40:19", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 813.5326307299613, "loss": 0.629303589463234, "entropy": 0.628941185772419, "sharp": 0.13689093198627234}
+{"time": "10:44:11", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 814.9307568157716, "loss": 0.7139074690639973, "entropy": 0.6479368098080158, "sharp": 0.12744292337447405}
+{"time": "10:48:00", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 816.4513634590973, "loss": 0.6191560365259647, "entropy": 0.6536073237657547, "sharp": 0.10912103950977325}
+{"time": "10:51:58", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 817.8374518988347, "loss": 0.6629565581679344, "entropy": 0.6492936611175537, "sharp": 0.11740991286933422}
+{"time": "10:55:47", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 819.0763006955559, "loss": 0.6674642562866211, "entropy": 0.6276727467775345, "sharp": 0.14797602221369743}
+{"time": "10:59:42", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 820.0099210537139, "loss": 0.6209814883768559, "entropy": 0.6634104028344154, "sharp": 0.09461766667664051}
+{"time": "11:03:32", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 820.6561037335852, "loss": 0.6148519515991211, "entropy": 0.639094777405262, "sharp": 0.12599019799381495}
+{"time": "11:07:22", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 821.9256347633193, "loss": 0.7109029963612556, "entropy": 0.6656394079327583, "sharp": 0.09093428030610085}
+{"time": "11:11:19", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 822.7911094907754, "loss": 0.6674392018467188, "entropy": 0.6195236071944237, "sharp": 0.1667905393987894}
+{"time": "11:15:08", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 823.8780239857876, "loss": 0.6299148350954056, "entropy": 0.6428708918392658, "sharp": 0.13077908754348755}
+{"time": "11:16:38", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5889590382575989, "noul_T": 0.7730909850563897, "noul_auc": 0.7325783531079645, "noul_acc": 0.706, "noul_f1": 0.7782805429864253, "noul_nll": 0.5890120302140712, "noul_ece": 0.07276141059398651, "noul_brier": 0.20087057527670096, "noul_sharp": 0.15935461223125458, "entropy": 0.6219715476036072}
+{"time": "11:20:32", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 814.6599163571854, "loss": 0.6183697879314423, "entropy": 0.6086293309926987, "sharp": 0.1797013645991683}
+{"time": "11:24:25", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 815.5498606061693, "loss": 0.6364924218505621, "entropy": 0.6377070806920528, "sharp": 0.13368332851678133}
+{"time": "11:28:11", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 816.5292884031732, "loss": 0.6779704764485359, "entropy": 0.6316749379038811, "sharp": 0.14531234465539455}
+{"time": "11:32:08", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 817.5966398797207, "loss": 0.6126521565020084, "entropy": 0.6530223451554775, "sharp": 0.1147263403981924}
+{"time": "11:35:59", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 818.3563360824888, "loss": 0.6799592413008213, "entropy": 0.6566562317311764, "sharp": 0.10291524976491928}
+{"time": "11:39:59", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 819.2398868049017, "loss": 0.6816084049642086, "entropy": 0.65358567237854, "sharp": 0.10752285737544298}
+{"time": "11:43:58", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 820.2251384026229, "loss": 0.6586412638425827, "entropy": 0.6500765159726143, "sharp": 0.12154246028512716}
+{"time": "11:47:53", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 821.0173076845451, "loss": 0.6337406001985073, "entropy": 0.6489325687289238, "sharp": 0.11850345134735107}
+{"time": "11:51:41", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 821.8290559569314, "loss": 0.6655985414981842, "entropy": 0.6340193599462509, "sharp": 0.14273166935890913}
+{"time": "11:55:36", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 822.5245726663309, "loss": 0.6534064933657646, "entropy": 0.6452223248779774, "sharp": 0.12022273242473602}
+{"time": "11:57:05", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5849305391311646, "noul_T": 0.8273498068643625, "noul_auc": 0.7324095795851548, "noul_acc": 0.698, "noul_f1": 0.7622047244094489, "noul_nll": 0.5890091645717621, "noul_ece": 0.0542107492685318, "noul_brier": 0.20123710857651025, "noul_sharp": 0.1681467741727829, "entropy": 0.6111817359924316}
+{"time": "12:00:53", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 815.5756495686962, "loss": 0.6482101753354073, "entropy": 0.6511899754405022, "sharp": 0.11507229506969452}
+{"time": "12:04:49", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 816.3316542386035, "loss": 0.653830423951149, "entropy": 0.6547558531165123, "sharp": 0.11268606968224049}
+{"time": "12:08:40", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 816.9892471456843, "loss": 0.6716570071876049, "entropy": 0.662009634077549, "sharp": 0.10595453903079033}
+{"time": "12:12:28", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 817.8975243417636, "loss": 0.6467331433668733, "entropy": 0.6592691577970982, "sharp": 0.11045716796070337}
+{"time": "12:16:31", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 818.7427641333252, "loss": 0.6662633791565895, "entropy": 0.6620454266667366, "sharp": 0.09743834752589464}
+{"time": "12:20:20", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 819.1216239531839, "loss": 0.6529142111539841, "entropy": 0.6407266072928905, "sharp": 0.13368438836187124}
+{"time": "12:24:07", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 819.5289374123631, "loss": 0.7034588735550642, "entropy": 0.6706701274961233, "sharp": 0.08897182065993547}
+{"time": "12:27:57", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 820.1208930993836, "loss": 0.6949515864253044, "entropy": 0.6491555646061897, "sharp": 0.11734983790665865}
+{"time": "12:31:53", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 820.7208956891983, "loss": 0.6363747613504529, "entropy": 0.6366436816751957, "sharp": 0.13222702033817768}
+{"time": "12:35:47", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 821.3317125783958, "loss": 0.6431017443537712, "entropy": 0.6270446348935366, "sharp": 0.16068657580763102}
+{"time": "12:37:16", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5876492857933044, "noul_T": 0.7431308912548394, "noul_auc": 0.7330846736763936, "noul_acc": 0.704, "noul_f1": 0.7701863354037267, "noul_nll": 0.5911981515735388, "noul_ece": 0.06713010179996491, "noul_brier": 0.2020150261090471, "noul_sharp": 0.1536373496055603, "entropy": 0.6241338849067688}
+{"time": "12:40:31", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9820167, "tok_per_s": 802.5078639597049, "rows_per_s": 1.3763347852450893, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5727526545524597, "noul_T": 0.756268946083386, "choice_ce": 0.6707132458686829, "choice_T": 0.9630429435049804, "score_ce": 1.063092589378357, "score_T": 0.9525498434687176, "noul_auc": 0.7205290666666667, "noul_acc": 0.69, "noul_f1": 0.7696879643387816, "noul_nll": 0.591524988912046, "noul_ece": 0.06541209155321123, "noul_brier": 0.20267626322777926, "noul_sharp": 0.15836110711097717, "entropy": 0.6200612187385559}, "dropped_long": 0, "peak_gib": 18.236003875732422}