pod backup 2026-11-07: e48/S1-E48-SHRM10-ts1-syn (0-11)

e48/S1-E48-SHRM10-ts1-syn/DONE

@@ -0,0 +1 @@
+2026-11-08 23:11:22

e48/S1-E48-SHRM10-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

e48/S1-E48-SHRM10-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": [
+    "q_proj",
+    "gate_proj",
+    "in_proj_z",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "down_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
+}

e48/S1-E48-SHRM10-ts1-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f87f7701d10f3e02e4425cacdd7aa26ae8b0c049ec0a27d2bfe557140fcd5a2
+size 160486456

e48/S1-E48-SHRM10-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
+}

e48/S1-E48-SHRM10-ts1-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f3b317592528e79e24c2bc135302b5864459c00381d01d91f44e675894e5a3
+size 176641832

e48/S1-E48-SHRM10-ts1-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00044144265120849013,
+  -0.0004416967276483774,
+  -0.0021935016848146915,
+  -0.0012937742285430431,
+  -0.0002521372225601226,
+  0.0021726926788687706,
+  0.001365797477774322,
+  -0.002535896608605981,
+  -0.0007385559729300439,
+  -0.0002240656758658588,
+  -0.00024001504061743617,
+  0.00037440034793689847,
+  -0.00036344098043628037,
+  -0.0035591889172792435,
+  -0.004335443489253521,
+  -0.005142771173268557,
+  -0.0059781684540212154,
+  -0.00439064484089613,
+  -0.004942241590470076,
+  -0.0050276657566428185,
+  -0.003875536611303687,
+  -0.00341920368373394,
+  -0.005717660766094923,
+  -0.0034930300898849964
+ ],
+ "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"
+}

e48/S1-E48-SHRM10-ts1-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.874824788695278,
+  "choice": 1.019716915066528,
+  "score": 0.9695598180765623
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.874824788695278,
+   "ce_before": 0.5726007223129272,
+   "ce_after": 0.5712072849273682
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.019716915066528,
+   "ce_before": 0.6631477475166321,
+   "ce_after": 0.6630677580833435
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9695598180765623,
+   "ce_before": 1.056402564048767,
+   "ce_after": 1.0561193227767944
+  }
+ },
+ "source": "models/e48/S1-E48-SHRM10-ts1-syn/ckpt-16000"
+}

e48/S1-E48-SHRM10-ts1-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f187bfc2e9f5b8f9597779c90151a382dc6a5046ad1183310e0341cd35b0283
+size 393464

e48/S1-E48-SHRM10-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/e48/S1-E48-SHRM10-ts1-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e48/E48-SHR-M10",
+  "data_manifest": {
+   "arm": "E48-SHR-M10",
+   "name": null,
+   "train_sha256": "d50f5af141156380cb9c267329f29c9723e6e207b0149afe49abaf673ff8fece",
+   "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": 9820023,
+  "tok_per_s": 1287.3107429194154,
+  "rows_per_s": 2.207824515973925,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5726007223129272,
+   "noul_T": 0.874824788695278,
+   "choice_ce": 0.6631477475166321,
+   "choice_T": 1.019716915066528,
+   "score_ce": 1.056402564048767,
+   "score_T": 0.9695598180765623,
+   "noul_auc": 0.7219456000000001,
+   "noul_acc": 0.697,
+   "noul_f1": 0.7773695811903012,
+   "noul_nll": 0.5877270710617304,
+   "noul_ece": 0.05408456942439077,
+   "noul_brier": 0.20118995064672715,
+   "noul_sharp": 0.17574872076511383,
+   "entropy": 0.6037643551826477
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.282634735107422
+ }
+}

e48/S1-E48-SHRM10-ts1-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "21:04:13", "event": "start", "data": "data/e48/E48-SHR-M10", "data_manifest": {"arm": "E48-SHR-M10", "name": null, "train_sha256": "d50f5af141156380cb9c267329f29c9723e6e207b0149afe49abaf673ff8fece", "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": 5.082193613052368}
+{"time": "21:06:40", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 1359.208354418537, "loss": 0.6734261736273766, "entropy": 0.6868999525904655, "sharp": 0.04846742656081915}
+{"time": "21:09:03", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 1355.0483308261016, "loss": 0.6619439888745546, "entropy": 0.662225155159831, "sharp": 0.09183100704103708}
+{"time": "21:11:30", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 1351.5592535961796, "loss": 0.6179035976529121, "entropy": 0.6118336878716946, "sharp": 0.1859318856149912}
+{"time": "21:13:51", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 1352.715292397808, "loss": 0.6181449070572853, "entropy": 0.6459565311670303, "sharp": 0.12716094404459}
+{"time": "21:16:14", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 1353.0368370565573, "loss": 0.6373437531292439, "entropy": 0.6704894453287125, "sharp": 0.09126578457653522}
+{"time": "21:18:39", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 1353.054646334143, "loss": 0.6646293252706528, "entropy": 0.6490508541464806, "sharp": 0.12657773308455944}
+{"time": "21:21:08", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 1355.1098603413293, "loss": 0.6285836454480886, "entropy": 0.640211932361126, "sharp": 0.14180529676377773}
+{"time": "21:23:40", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 1355.9796388429875, "loss": 0.6210123971104622, "entropy": 0.6263025477528572, "sharp": 0.1465031784027815}
+{"time": "21:26:07", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 1354.9320725389503, "loss": 0.6490402072668076, "entropy": 0.6460615713149309, "sharp": 0.11495376471430063}
+{"time": "21:28:31", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 1352.9593845389263, "loss": 0.5986882969737053, "entropy": 0.6199346594512463, "sharp": 0.15621330123394728}
+{"time": "21:29:24", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5925114154815674, "noul_T": 0.7563216370868002, "noul_auc": 0.734789286256772, "noul_acc": 0.712, "noul_f1": 0.7784615384615384, "noul_nll": 0.5938723344355822, "noul_ece": 0.07722160470485687, "noul_brier": 0.20312827496345817, "noul_sharp": 0.14279377460479736, "entropy": 0.6244983673095703}
+{"time": "21:31:48", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 1310.5984355168232, "loss": 0.6923847142606974, "entropy": 0.6534133963286877, "sharp": 0.09706154093146324}
+{"time": "21:34:12", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 1314.462031753883, "loss": 0.6429470479488373, "entropy": 0.6243610456585884, "sharp": 0.1504274606704712}
+{"time": "21:36:38", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 1317.7213037335255, "loss": 0.584904208779335, "entropy": 0.640787448734045, "sharp": 0.1287363562732935}
+{"time": "21:39:01", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 1321.0133661806701, "loss": 0.644498948007822, "entropy": 0.6487964615225792, "sharp": 0.12952766381204128}
+{"time": "21:41:31", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 1324.5226176394635, "loss": 0.6413923520594835, "entropy": 0.6500667594373226, "sharp": 0.12750334851443768}
+{"time": "21:43:51", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 1326.5511574953719, "loss": 0.6646339781582355, "entropy": 0.642163522541523, "sharp": 0.13826208002865314}
+{"time": "21:46:17", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 1329.3865788236549, "loss": 0.6418399289250374, "entropy": 0.6453201398253441, "sharp": 0.13441568985581398}
+{"time": "21:48:41", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 1330.5755503314322, "loss": 0.6675303764641285, "entropy": 0.6510829329490662, "sharp": 0.11966427322477102}
+{"time": "21:51:07", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 1331.6374946253216, "loss": 0.6302178651094437, "entropy": 0.6575327962636948, "sharp": 0.10880153626203537}
+{"time": "21:53:24", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 1332.9490418807738, "loss": 0.6868176776915789, "entropy": 0.5973648019134998, "sharp": 0.19044965878129005}
+{"time": "21:54:17", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5986980199813843, "noul_T": 1.1022558810268264, "noul_auc": 0.7297598352770416, "noul_acc": 0.68, "noul_f1": 0.7790055248618785, "noul_nll": 0.5942464038580656, "noul_ece": 0.07139509558677673, "noul_brier": 0.20328964264307064, "noul_sharp": 0.20043523609638214, "entropy": 0.5816423296928406}
+{"time": "21:56:43", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 1312.405029323414, "loss": 0.7058589113876224, "entropy": 0.6478487234562635, "sharp": 0.1164892427623272}
+{"time": "21:59:08", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 1313.9398116581872, "loss": 0.6438948065042496, "entropy": 0.6524463351815939, "sharp": 0.11927152704447508}
+{"time": "22:01:31", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 1315.469560813865, "loss": 0.663886770606041, "entropy": 0.6545993052423, "sharp": 0.11216351110488176}
+{"time": "22:03:52", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 1317.210603093258, "loss": 0.6194548048079014, "entropy": 0.6283477023243904, "sharp": 0.14398175105452538}
+{"time": "22:06:21", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 1318.468229265308, "loss": 0.662515465170145, "entropy": 0.6581557840108871, "sharp": 0.11100310925394297}
+{"time": "22:08:43", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 1319.6531304417872, "loss": 0.6464789696037769, "entropy": 0.6557517573237419, "sharp": 0.1071605421602726}
+{"time": "22:11:07", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 1320.2678494672527, "loss": 0.6448708884418011, "entropy": 0.6590378955006599, "sharp": 0.10508063342422247}
+{"time": "22:13:31", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 1321.4481083798462, "loss": 0.6556278392672539, "entropy": 0.6402985230088234, "sharp": 0.1362789999693632}
+{"time": "22:15:54", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 1321.9772373875844, "loss": 0.6197591572999954, "entropy": 0.6290331557393074, "sharp": 0.1478746710345149}
+{"time": "22:18:21", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 1323.0029827566857, "loss": 0.6522449254989624, "entropy": 0.6481271460652351, "sharp": 0.12185247242450714}
+{"time": "22:19:14", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5839866995811462, "noul_T": 0.8936676673814347, "noul_auc": 0.7374896626217279, "noul_acc": 0.708, "noul_f1": 0.7697160883280757, "noul_nll": 0.5814986445903778, "noul_ece": 0.04650791192054749, "noul_brier": 0.19779522253276097, "noul_sharp": 0.18260805308818817, "entropy": 0.6012378334999084}
+{"time": "22:21:36", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 1309.145327133953, "loss": 0.6143008470535278, "entropy": 0.6502011641860008, "sharp": 0.12293225899338722}
+{"time": "22:24:04", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 1310.451495244497, "loss": 0.6352311372756958, "entropy": 0.6563306674361229, "sharp": 0.11456598155200481}
+{"time": "22:26:28", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 1311.4704064072532, "loss": 0.6308663310483098, "entropy": 0.6061176657676697, "sharp": 0.18769383989274502}
+{"time": "22:28:55", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 1312.5908256798298, "loss": 0.6396751813590527, "entropy": 0.6575146988034248, "sharp": 0.1081841541454196}
+{"time": "22:31:21", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 1313.9079077675487, "loss": 0.6317407488822937, "entropy": 0.6498063467442989, "sharp": 0.12366453092545271}
+{"time": "22:33:46", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 1315.0824306979976, "loss": 0.658956665545702, "entropy": 0.6418837457895279, "sharp": 0.133184096775949}
+{"time": "22:36:11", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 1315.9090147375855, "loss": 0.664650447666645, "entropy": 0.6368817538022995, "sharp": 0.13891667313873768}
+{"time": "22:38:34", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 1316.7595650472892, "loss": 0.6579654030501842, "entropy": 0.6457820683717728, "sharp": 0.12053648754954338}
+{"time": "22:40:58", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 1317.9895691248769, "loss": 0.6256358018144965, "entropy": 0.621058439835906, "sharp": 0.15624481905251741}
+{"time": "22:43:28", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 1318.8643725048362, "loss": 0.683683380484581, "entropy": 0.6525837667286396, "sharp": 0.11077624280005693}
+{"time": "22:44:20", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.585853099822998, "noul_T": 0.8161797221065815, "noul_auc": 0.7361563517915308, "noul_acc": 0.708, "noul_f1": 0.7746913580246914, "noul_nll": 0.5854955110698938, "noul_ece": 0.07577943241596222, "noul_brier": 0.19974890290413738, "noul_sharp": 0.16276663541793823, "entropy": 0.6130449771881104}
+{"time": "22:46:44", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 1308.4696664115752, "loss": 0.6581154316663742, "entropy": 0.6512810438871384, "sharp": 0.11101679783314466}
+{"time": "22:49:12", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 1309.3577064696772, "loss": 0.6902030650526285, "entropy": 0.6508763320744038, "sharp": 0.1202352000400424}
+{"time": "22:51:37", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 1310.6444773762478, "loss": 0.6619375720620155, "entropy": 0.6523192971944809, "sharp": 0.11760497838258743}
+{"time": "22:54:05", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 1311.519919252013, "loss": 0.6593113206326962, "entropy": 0.6557945795357227, "sharp": 0.11445294413715601}
+{"time": "22:56:32", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 1312.4752441201176, "loss": 0.5815364439040422, "entropy": 0.65178507193923, "sharp": 0.12181204371154308}
+{"time": "22:58:57", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 1313.2178055836616, "loss": 0.6736254002898932, "entropy": 0.6370901353657246, "sharp": 0.1398971015587449}
+{"time": "23:01:23", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 1314.020477932773, "loss": 0.6996508352458477, "entropy": 0.6443256735801697, "sharp": 0.11845767591148615}
+{"time": "23:03:46", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 1314.608182127215, "loss": 0.6751684844493866, "entropy": 0.6555676534771919, "sharp": 0.10821118485182524}
+{"time": "23:06:08", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 1315.1514552038816, "loss": 0.6039170250296593, "entropy": 0.64334736764431, "sharp": 0.1291442345827818}
+{"time": "23:08:36", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 1315.9188024408006, "loss": 0.6710052825510502, "entropy": 0.654653012752533, "sharp": 0.11015463154762983}
+{"time": "23:09:29", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5844946503639221, "noul_T": 0.8314398824071966, "noul_auc": 0.7372196249852323, "noul_acc": 0.704, "noul_f1": 0.7694704049844237, "noul_nll": 0.5832936863601208, "noul_ece": 0.06174798214435577, "noul_brier": 0.1987236215897708, "noul_sharp": 0.16769294440746307, "entropy": 0.6102379560470581}
+{"time": "23:11:22", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9820023, "tok_per_s": 1287.3107429194154, "rows_per_s": 2.207824515973925, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5726007223129272, "noul_T": 0.874824788695278, "choice_ce": 0.6631477475166321, "choice_T": 1.019716915066528, "score_ce": 1.056402564048767, "score_T": 0.9695598180765623, "noul_auc": 0.7219456000000001, "noul_acc": 0.697, "noul_f1": 0.7773695811903012, "noul_nll": 0.5877270710617304, "noul_ece": 0.05408456942439077, "noul_brier": 0.20118995064672715, "noul_sharp": 0.17574872076511383, "entropy": 0.6037643551826477}, "dropped_long": 0, "peak_gib": 18.282634735107422}