E39 train-seed checkpoint E39-M10rt-ts1

e39/S1-E39-M10rt-ts1-syn/DONE

@@ -0,0 +1 @@
+2026-10-28 06:50:24

e39/S1-E39-M10rt-ts1-syn/ckpt-16000/adapter/README.md

@@ -0,0 +1,206 @@
+---
+base_model: /workspace/jev_kt/models/hf/JEV-9B
+library_name: peft
+tags:
+- base_model:adapter:/workspace/jev_kt/models/hf/JEV-9B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.21.2

e39/S1-E39-M10rt-ts1-syn/ckpt-16000/adapter/adapter_config.json

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

e39/S1-E39-M10rt-ts1-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a1134ba9c1c285ee7715b243b03be677be6fd3328adb5e7e2abff7ab2b72fb
+size 160486456

e39/S1-E39-M10rt-ts1-syn/ckpt-16000/adapter_vllm/adapter_config.json

@@ -0,0 +1,58 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForCausalLM",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64.0,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "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-ts1-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac7c89e3426e33481ef804ffacd07526420df9d4a42524cbe5fff1620944c18
+size 176641832

e39/S1-E39-M10rt-ts1-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00036990197259001434,
+  -0.0003701559908222407,
+  -0.0026363448705524206,
+  -0.0011380503419786692,
+  -0.00036670410190708935,
+  0.0018145879730582237,
+  0.0009248700807802379,
+  -0.0029254627879709005,
+  -0.0006361633422784507,
+  -0.00046642665984109044,
+  -0.00018758562509901822,
+  0.00031106913229450583,
+  -0.000523221620824188,
+  -0.0036165558267384768,
+  -0.004481486976146698,
+  -0.0051675839349627495,
+  -0.006013522390276194,
+  -0.004430485889315605,
+  -0.004944872576743364,
+  -0.005014632362872362,
+  -0.003854682669043541,
+  -0.0034102152567356825,
+  -0.005699618719518185,
+  -0.0035048334393650293
+ ],
+ "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-ts1-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8341449767598494,
+  "choice": 1.0330241294022329,
+  "score": 0.9635039234242315
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.8341449767598494,
+   "ce_before": 0.5729873180389404,
+   "ce_after": 0.5705336928367615
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0330241294022329,
+   "ce_before": 0.6694928407669067,
+   "ce_after": 0.6692550778388977
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9635039234242315,
+   "ce_before": 1.0674387216567993,
+   "ce_after": 1.0670380592346191
+  }
+ },
+ "source": "models/e39/S1-E39-M10rt-ts1-syn/ckpt-16000"
+}

e39/S1-E39-M10rt-ts1-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c013f3867f03fd79849b6bd033fc45227a03a26d14535cb6182a127ff24b7776
+size 393464

e39/S1-E39-M10rt-ts1-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-ts1-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": 1,
+  "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": 854.7467939560478,
+  "rows_per_s": 1.465926750251348,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5729873180389404,
+   "noul_T": 0.8341449767598494,
+   "choice_ce": 0.6694928407669067,
+   "choice_T": 1.0330241294022329,
+   "score_ce": 1.0674387216567993,
+   "score_T": 0.9635039234242315,
+   "noul_auc": 0.7172394666666667,
+   "noul_acc": 0.688,
+   "noul_f1": 0.7688888888888888,
+   "noul_nll": 0.5912366390600801,
+   "noul_ece": 0.0581335077881813,
+   "noul_brier": 0.20279603431303037,
+   "noul_sharp": 0.1673423945903778,
+   "entropy": 0.6098084449768066
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.236003875732422
+ }
+}

e39/S1-E39-M10rt-ts1-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "03:38:53", "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": 1, "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": 114.57284545898438}
+{"time": "03:42:37", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 890.6231356617408, "loss": 0.6698530837893486, "entropy": 0.6859179437160492, "sharp": 0.05077365692704916}
+{"time": "03:46:13", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 893.8949129280918, "loss": 0.6865050755441189, "entropy": 0.6471910178661346, "sharp": 0.12071212939918041}
+{"time": "03:49:52", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 894.6181006648617, "loss": 0.6156240999698639, "entropy": 0.5820978283882141, "sharp": 0.22475219517946243}
+{"time": "03:53:27", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 895.5246509131749, "loss": 0.6207198835909367, "entropy": 0.6574558280408382, "sharp": 0.11970189213752747}
+{"time": "03:57:02", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 896.0181631738999, "loss": 0.6453479006886482, "entropy": 0.670293178409338, "sharp": 0.09803647734224796}
+{"time": "04:00:39", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 897.1050869312174, "loss": 0.6580189391970634, "entropy": 0.6471119821071625, "sharp": 0.1264345496892929}
+{"time": "04:04:23", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 898.9091385461002, "loss": 0.6253260187804699, "entropy": 0.6494025606662035, "sharp": 0.1272061625495553}
+{"time": "04:08:10", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 900.1474949630682, "loss": 0.6468066722154617, "entropy": 0.6618186682462692, "sharp": 0.09931132942438126}
+{"time": "04:11:52", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 900.001527238923, "loss": 0.6781892944127321, "entropy": 0.6240004822611809, "sharp": 0.15244683530181646}
+{"time": "04:15:27", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 899.1081245017243, "loss": 0.5934516526758671, "entropy": 0.6228345073759556, "sharp": 0.16252772323787212}
+{"time": "04:16:50", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5918524265289307, "noul_T": 0.8156488803281355, "noul_auc": 0.7428060285902348, "noul_acc": 0.698, "noul_f1": 0.7839771101573677, "noul_nll": 0.5903734021782875, "noul_ece": 0.0785423768758774, "noul_brier": 0.2018127392181022, "noul_sharp": 0.15395331382751465, "entropy": 0.6180278658866882}
+{"time": "04:20:27", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 869.683360601591, "loss": 0.6816892474889755, "entropy": 0.6633625030517578, "sharp": 0.09821921028196812}
+{"time": "04:24:03", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 872.5224979323963, "loss": 0.6673248074948788, "entropy": 0.6040437556803226, "sharp": 0.1810412686318159}
+{"time": "04:27:44", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 874.6968657277553, "loss": 0.6171955168247223, "entropy": 0.6773406341671944, "sharp": 0.07591120339930058}
+{"time": "04:31:20", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 876.6739546564626, "loss": 0.6281183250248432, "entropy": 0.6503353081643581, "sharp": 0.12313521653413773}
+{"time": "04:35:04", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 879.1526494846576, "loss": 0.6507890168577433, "entropy": 0.6038949973881245, "sharp": 0.1832370338961482}
+{"time": "04:38:36", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 880.4299704227493, "loss": 0.6703578494489193, "entropy": 0.6565906032919884, "sharp": 0.12132514733821154}
+{"time": "04:42:17", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 882.1911421173793, "loss": 0.6341719590127468, "entropy": 0.6576056256890297, "sharp": 0.11320191901177168}
+{"time": "04:45:52", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 883.3075938287975, "loss": 0.6692505516111851, "entropy": 0.6569838747382164, "sharp": 0.1084096236154437}
+{"time": "04:49:30", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 884.201189556049, "loss": 0.6427570879459381, "entropy": 0.6393121853470802, "sharp": 0.12441134732216597}
+{"time": "04:52:57", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 885.133826369841, "loss": 0.6599843669682741, "entropy": 0.6392397098243237, "sharp": 0.12978201359510422}
+{"time": "04:54:20", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5913382768630981, "noul_T": 0.7619866993280556, "noul_auc": 0.7359538235641592, "noul_acc": 0.712, "noul_f1": 0.7863501483679525, "noul_nll": 0.5919297788888216, "noul_ece": 0.07669527316093444, "noul_brier": 0.20204027667423424, "noul_sharp": 0.14885318279266357, "entropy": 0.6239320039749146}
+{"time": "04:58:01", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 870.8241325824615, "loss": 0.6744599053636193, "entropy": 0.5993244685232639, "sharp": 0.17118381801992655}
+{"time": "05:01:37", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 872.1246156043167, "loss": 0.6503523383289576, "entropy": 0.644964063540101, "sharp": 0.13204433303326368}
+{"time": "05:05:12", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 873.2587048302182, "loss": 0.664135467261076, "entropy": 0.6465795338153839, "sharp": 0.11976205557584763}
+{"time": "05:08:44", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 874.4675027668475, "loss": 0.6176124848425388, "entropy": 0.6222716718912125, "sharp": 0.1554673993960023}
+{"time": "05:12:27", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 875.4751008210878, "loss": 0.6476612463593483, "entropy": 0.654975388199091, "sharp": 0.12009957060217857}
+{"time": "05:16:01", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 876.4100901237305, "loss": 0.6466079242527485, "entropy": 0.6563321650028229, "sharp": 0.1112319678068161}
+{"time": "05:19:35", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 877.1434641430773, "loss": 0.6359717920422554, "entropy": 0.6619999781250954, "sharp": 0.10115316603332758}
+{"time": "05:23:11", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 878.080303503028, "loss": 0.65989138931036, "entropy": 0.6348603144288063, "sharp": 0.14981314167380333}
+{"time": "05:26:45", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 878.4735552886108, "loss": 0.619942232966423, "entropy": 0.6331550404429436, "sharp": 0.14380937442183495}
+{"time": "05:30:26", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 879.2021423304129, "loss": 0.6461249403655529, "entropy": 0.6441416591405869, "sharp": 0.12496006675064564}
+{"time": "05:31:49", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5849108099937439, "noul_T": 0.9463100719089879, "noul_auc": 0.7285952979696545, "noul_acc": 0.704, "noul_f1": 0.7716049382716049, "noul_nll": 0.5876582636833191, "noul_ece": 0.05147277820110322, "noul_brier": 0.20066476117779866, "noul_sharp": 0.18598245084285736, "entropy": 0.5937753319740295}
+{"time": "05:35:23", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 869.5437757995053, "loss": 0.6119502782821655, "entropy": 0.6448539346456528, "sharp": 0.13262873515486717}
+{"time": "05:39:05", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 870.5598049021153, "loss": 0.6359443068504333, "entropy": 0.6504126861691475, "sharp": 0.1221847366541624}
+{"time": "05:42:40", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 871.3546422928388, "loss": 0.6340418271720409, "entropy": 0.6070582829415798, "sharp": 0.18886791728436947}
+{"time": "05:46:22", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 872.1086750569336, "loss": 0.6390993818640709, "entropy": 0.6595559418201447, "sharp": 0.09969124663621187}
+{"time": "05:50:02", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 872.9637807879291, "loss": 0.6313100755214691, "entropy": 0.6516627632081509, "sharp": 0.11984669044613838}
+{"time": "05:53:40", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 873.8467798666746, "loss": 0.6618650108575821, "entropy": 0.647387333214283, "sharp": 0.12246948294341564}
+{"time": "05:57:18", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 874.3044038547179, "loss": 0.6690172106027603, "entropy": 0.6330742761492729, "sharp": 0.13884990848600864}
+{"time": "06:00:53", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 874.8144829691138, "loss": 0.6568529158830643, "entropy": 0.6474350243806839, "sharp": 0.115815713070333}
+{"time": "06:04:31", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 875.6666883080014, "loss": 0.6263900250196457, "entropy": 0.6232814230024815, "sharp": 0.14968409202992916}
+{"time": "06:08:14", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 876.3986048232283, "loss": 0.6814512871205807, "entropy": 0.6541032642126083, "sharp": 0.11089529283344746}
+{"time": "06:09:37", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5877735614776611, "noul_T": 0.7919188426539996, "noul_auc": 0.7301648917317851, "noul_acc": 0.702, "noul_f1": 0.7725190839694657, "noul_nll": 0.5908381664007902, "noul_ece": 0.09107265257835387, "noul_brier": 0.20215611873982545, "noul_sharp": 0.15544116497039795, "entropy": 0.6173528432846069}
+{"time": "06:13:13", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 869.1958235122399, "loss": 0.6598978117108345, "entropy": 0.6541579738259315, "sharp": 0.10524883773177862}
+{"time": "06:16:54", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 869.8752424505578, "loss": 0.6891345977783203, "entropy": 0.6542583610862494, "sharp": 0.11640481557697058}
+{"time": "06:20:32", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 870.7539064170817, "loss": 0.657434843480587, "entropy": 0.6539718732237816, "sharp": 0.11347445100545883}
+{"time": "06:24:15", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 871.3219197728985, "loss": 0.6574790962040424, "entropy": 0.6533040702342987, "sharp": 0.11469076666980982}
+{"time": "06:27:57", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 871.9562202686363, "loss": 0.5814850050956011, "entropy": 0.6502319537103176, "sharp": 0.12274837866425514}
+{"time": "06:31:35", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 872.5193523699785, "loss": 0.678306789137423, "entropy": 0.6351782958954573, "sharp": 0.1413166355341673}
+{"time": "06:35:13", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 873.1227940716203, "loss": 0.7038612216711044, "entropy": 0.6443473622202873, "sharp": 0.11757536046206951}
+{"time": "06:38:48", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 873.5271420282868, "loss": 0.6753363236784935, "entropy": 0.6540349759161472, "sharp": 0.1082241740077734}
+{"time": "06:42:21", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 873.9844097509355, "loss": 0.6025602072477341, "entropy": 0.6417293399572372, "sharp": 0.12989347148686647}
+{"time": "06:46:02", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 874.5742247018679, "loss": 0.6701694317162037, "entropy": 0.6548742018640041, "sharp": 0.10731262806802988}
+{"time": "06:47:25", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5866867303848267, "noul_T": 0.8028849021348725, "noul_auc": 0.7314813252097011, "noul_acc": 0.7, "noul_f1": 0.7678018575851393, "noul_nll": 0.5890036908835172, "noul_ece": 0.07969180285930634, "noul_brier": 0.20124241379932198, "noul_sharp": 0.1602277308702469, "entropy": 0.6154716610908508}
+{"time": "06:50:24", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9820167, "tok_per_s": 854.7467939560478, "rows_per_s": 1.465926750251348, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5729873180389404, "noul_T": 0.8341449767598494, "choice_ce": 0.6694928407669067, "choice_T": 1.0330241294022329, "score_ce": 1.0674387216567993, "score_T": 0.9635039234242315, "noul_auc": 0.7172394666666667, "noul_acc": 0.688, "noul_f1": 0.7688888888888888, "noul_nll": 0.5912366390600801, "noul_ece": 0.0581335077881813, "noul_brier": 0.20279603431303037, "noul_sharp": 0.1673423945903778, "entropy": 0.6098084449768066}, "dropped_long": 0, "peak_gib": 18.236003875732422}