backup e16/S1-E19-a1-n16k-a100-syn (Pod B)

e16/S1-E19-a1-n16k-a100-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

e16/S1-E19-a1-n16k-a100-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": [
+    "up_proj",
+    "o_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "in_proj_z",
+    "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
+}

e16/S1-E19-a1-n16k-a100-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26bbff256f6baec9e9ec8da2de01f76d2f215be87699a7084263a8f28864d4eb
+size 160486456

e16/S1-E19-a1-n16k-a100-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
+}

e16/S1-E19-a1-n16k-a100-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15da5e9783bcf65909b1f5ff55cd13f00a14d021f4e874a9c9f3d9df33d9bc6f
+size 176641832

e16/S1-E19-a1-n16k-a100-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0008848350844345987,
+  -0.000885090499650687,
+  -0.002075083553791046,
+  -0.0014754201984032989,
+  -0.00027172418776899576,
+  0.0017720174510031939,
+  0.000912531919311732,
+  -0.00246368907392025,
+  -0.0011163590243086219,
+  -0.000942745478823781,
+  -0.0003056631830986589,
+  0.0002605628105811775,
+  -0.0010928282281383872,
+  -0.003883223980665207,
+  -0.004518965259194374,
+  -0.005214374046772718,
+  -0.005939367692917585,
+  -0.004417700227349997,
+  -0.00497456407174468,
+  -0.005170551594346762,
+  -0.004228414501994848,
+  -0.0036207044031471014,
+  -0.005773615092039108,
+  -0.0036045874003320932
+ ],
+ "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-E19-a1-n16k-a100-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 1.029952342237469,
+  "choice": 1.0577606522158263,
+  "score": 0.9693892850617055
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 1.029952342237469,
+   "ce_before": 0.6381511092185974,
+   "ce_after": 0.6381175518035889
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0577606522158263,
+   "ce_before": 0.6812111735343933,
+   "ce_after": 0.6804530620574951
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9693892850617055,
+   "ce_before": 1.0487253665924072,
+   "ce_after": 1.0484395027160645
+  }
+ },
+ "source": "models/e16/S1-E19-a1-n16k-a100-syn/ckpt-16000"
+}

e16/S1-E19-a1-n16k-a100-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27596691b6abf3b704e42390db2337e6cef8b3ebc55e727735729770c6de1342
+size 393464

e16/S1-E19-a1-n16k-a100-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/e16/S1-E19-a1-n16k-a100-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e19/E19-a1-n16k-a100",
+  "data_manifest": {
+   "arm": "E19-a1-n16k-a100",
+   "name": null,
+   "train_sha256": "e8630093337aa4e236ec84240be87518ce2f248884bb346f205966a4da98bbe6",
+   "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": 8943984,
+  "tok_per_s": 800.2291356549823,
+  "rows_per_s": 1.506874240361042,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.6381511092185974,
+   "noul_T": 1.029952342237469,
+   "choice_ce": 0.6812111735343933,
+   "choice_T": 1.0577606522158263,
+   "score_ce": 1.0487253665924072,
+   "score_T": 0.9693892850617055,
+   "noul_auc": 0.7012010666666667,
+   "noul_acc": 0.623,
+   "noul_f1": 0.6606660666066607,
+   "noul_nll": 0.6497219701781869,
+   "noul_ece": 0.15711297784745692,
+   "noul_brier": 0.22903177858235785,
+   "noul_sharp": 0.11895649135112762,
+   "entropy": 0.6470414400100708
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.235705852508545
+ }
+}

e16/S1-E19-a1-n16k-a100-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "10:22:59", "event": "start", "data": "data/e19/E19-a1-n16k-a100", "data_manifest": {"arm": "E19-a1-n16k-a100", "name": null, "train_sha256": "e8630093337aa4e236ec84240be87518ce2f248884bb346f205966a4da98bbe6", "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": 82.36370635032654}
+{"time": "10:26:31", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 832.215934471425, "loss": 0.6503720320761204, "entropy": 0.5711615234613419, "sharp": 0.18100939877331257}
+{"time": "10:30:04", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 835.3748754877928, "loss": 0.7035536766052246, "entropy": 0.6894180849194527, "sharp": 0.034258763305842876}
+{"time": "10:33:27", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 838.9595970088511, "loss": 0.6800523512065411, "entropy": 0.5931671634316444, "sharp": 0.21896221209317446}
+{"time": "10:36:59", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 842.815763961821, "loss": 0.6651643253862858, "entropy": 0.6212584301829338, "sharp": 0.1841421201825142}
+{"time": "10:40:30", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 844.9477148634276, "loss": 0.8803777396678925, "entropy": 0.5221148766577244, "sharp": 0.2714403895661235}
+{"time": "10:44:05", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 846.8398017550991, "loss": 0.5903759626671672, "entropy": 0.6428889781236649, "sharp": 0.15241909213364124}
+{"time": "10:47:31", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 846.2101719978011, "loss": 0.5371279790997505, "entropy": 0.625563457608223, "sharp": 0.14285138621926308}
+{"time": "10:51:02", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 846.7297082415794, "loss": 0.5095812827348709, "entropy": 0.6165564339607954, "sharp": 0.17431860882788897}
+{"time": "10:54:43", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 847.0694888589081, "loss": 0.5790985561907291, "entropy": 0.5464204847812653, "sharp": 0.23400881234556437}
+{"time": "10:58:11", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 846.8619857013724, "loss": 0.6190801188349724, "entropy": 0.5829369276762009, "sharp": 0.204022865742445}
+{"time": "10:59:39", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.6026919484138489, "noul_T": 0.9985054403162195, "noul_auc": 0.723025771716933, "noul_acc": 0.696, "noul_f1": 0.7516339869281046, "noul_nll": 0.6028332934379578, "noul_ece": 0.08748101645708084, "noul_brier": 0.2066839419229499, "noul_sharp": 0.18342091143131256, "entropy": 0.6030364036560059}
+{"time": "11:03:13", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 815.8798989024405, "loss": 0.6510646883398294, "entropy": 0.5296716243028641, "sharp": 0.2527691125869751}
+{"time": "11:06:45", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 818.205485309743, "loss": 0.6181143224239349, "entropy": 0.6208961382508278, "sharp": 0.15619943849742413}
+{"time": "11:10:20", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 820.515999020221, "loss": 0.5577158182859421, "entropy": 0.6032292917370796, "sharp": 0.17383813671767712}
+{"time": "11:13:56", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 822.4567253191066, "loss": 0.5824116636067629, "entropy": 0.5780835635960102, "sharp": 0.20110554620623589}
+{"time": "11:17:32", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 823.8366029342371, "loss": 0.5870324000716209, "entropy": 0.5703915953636169, "sharp": 0.22162242233753204}
+{"time": "11:21:06", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 825.3793335940491, "loss": 0.5691555878147483, "entropy": 0.5476700067520142, "sharp": 0.25301511213183403}
+{"time": "11:24:39", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 826.387685388931, "loss": 0.6594888791441917, "entropy": 0.5493587926030159, "sharp": 0.23202674090862274}
+{"time": "11:28:13", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 827.6791375822697, "loss": 0.45203861221671104, "entropy": 0.5760078802704811, "sharp": 0.21370270289480686}
+{"time": "11:31:42", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 828.775444930111, "loss": 0.4263534629717469, "entropy": 0.5652435384690762, "sharp": 0.2145265731960535}
+{"time": "11:35:17", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 829.9704047498159, "loss": 0.6323573105037212, "entropy": 0.5215331017971039, "sharp": 0.25061337277293205}
+{"time": "11:36:45", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.7070821523666382, "noul_T": 2.607318523164162, "noul_auc": 0.6837690503113871, "noul_acc": 0.576, "noul_f1": 0.5725806451612904, "noul_nll": 0.6949131693169475, "noul_ece": 0.19022765171527864, "noul_brier": 0.24933418391212944, "noul_sharp": 0.13735003769397736, "entropy": 0.6294962763786316}
+{"time": "11:40:11", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 814.5729680080522, "loss": 0.5041964033152908, "entropy": 0.54010427929461, "sharp": 0.24342864658683538}
+{"time": "11:43:41", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 816.044691468237, "loss": 0.6632502619177103, "entropy": 0.595496354624629, "sharp": 0.19346865080296993}
+{"time": "11:47:14", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 817.4013498744666, "loss": 0.5497537031769753, "entropy": 0.5058524012565613, "sharp": 0.25955813378095627}
+{"time": "11:50:44", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 818.3953394499622, "loss": 0.5206624902784824, "entropy": 0.5650177896022797, "sharp": 0.22011052072048187}
+{"time": "11:54:21", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 818.902714274178, "loss": 0.6027582138776779, "entropy": 0.5734657794237137, "sharp": 0.20418879389762878}
+{"time": "11:57:48", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 819.8711681602891, "loss": 0.582035715226084, "entropy": 0.4800318330526352, "sharp": 0.28131208941340446}
+{"time": "12:01:13", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 820.7199643115657, "loss": 0.5497518759220839, "entropy": 0.6182224117219448, "sharp": 0.1632665190845728}
+{"time": "12:04:53", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 821.9872993392887, "loss": 0.5552526749670506, "entropy": 0.600985124707222, "sharp": 0.18093677423894405}
+{"time": "12:08:17", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 823.0906642841982, "loss": 0.5772420540452003, "entropy": 0.5172719657421112, "sharp": 0.261272668838501}
+{"time": "12:11:49", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 823.8119914514645, "loss": 0.6288931090384722, "entropy": 0.6425002608448267, "sharp": 0.12107713799923658}
+{"time": "12:13:17", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.6300765872001648, "noul_T": 0.5641575143935115, "noul_auc": 0.7005113837741135, "noul_acc": 0.684, "noul_f1": 0.742671009771987, "noul_nll": 0.6282359160482883, "noul_ece": 0.10625261414051057, "noul_brier": 0.2184704393580207, "noul_sharp": 0.09788722544908524, "entropy": 0.6657898426055908}
+{"time": "12:16:38", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 813.8181990496638, "loss": 0.6217633411288261, "entropy": 0.6106591522693634, "sharp": 0.17323236912488937}
+{"time": "12:20:01", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 814.670081320438, "loss": 0.6677860468626022, "entropy": 0.5611538887023926, "sharp": 0.22135654091835022}
+{"time": "12:23:29", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 815.8281520106739, "loss": 0.6287044901400805, "entropy": 0.4863416440784931, "sharp": 0.2717239446938038}
+{"time": "12:27:05", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 816.9355133598575, "loss": 0.5834899470210075, "entropy": 0.552046649158001, "sharp": 0.2202904187142849}
+{"time": "12:30:27", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 817.9634898548093, "loss": 0.5206081196665764, "entropy": 0.552464809268713, "sharp": 0.22253237292170525}
+{"time": "12:34:08", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 818.8537966389988, "loss": 0.49824991822242737, "entropy": 0.540007758885622, "sharp": 0.22444947436451912}
+{"time": "12:37:41", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 819.7461320756281, "loss": 0.5261658243834972, "entropy": 0.5358233228325844, "sharp": 0.23015872202813625}
+{"time": "12:41:02", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 820.4543170265516, "loss": 0.6043067872524261, "entropy": 0.5097386874258518, "sharp": 0.25294330157339573}
+{"time": "12:44:29", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 821.1772794456665, "loss": 0.4678148231469095, "entropy": 0.5416636019945145, "sharp": 0.22772100288420916}
+{"time": "12:47:56", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 821.9935936442631, "loss": 0.5432258527725935, "entropy": 0.48394267726689577, "sharp": 0.2772157145664096}
+{"time": "12:49:25", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.6663276553153992, "noul_T": 1.5120448444779917, "noul_auc": 0.7131187659280013, "noul_acc": 0.618, "noul_f1": 0.6375711574952562, "noul_nll": 0.6587968682050704, "noul_ece": 0.1698397262990475, "noul_brier": 0.2323156793457572, "noul_sharp": 0.14484210312366486, "entropy": 0.6248260140419006}
+{"time": "12:52:55", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 814.5441762398887, "loss": 0.6182875856757164, "entropy": 0.5299367345869541, "sharp": 0.24415271915495396}
+{"time": "12:56:28", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 815.3198678596252, "loss": 0.7247134894132614, "entropy": 0.5087413843721151, "sharp": 0.2524926494807005}
+{"time": "13:00:00", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 816.2574234521925, "loss": 0.5267088999971747, "entropy": 0.5376625880599022, "sharp": 0.23282405734062195}
+{"time": "13:03:33", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 816.6075526160726, "loss": 0.6298979036509991, "entropy": 0.5059014093130827, "sharp": 0.27642867527902126}
+{"time": "13:07:07", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 817.514755423971, "loss": 0.4871196635067463, "entropy": 0.5451572798192501, "sharp": 0.23542554676532745}
+{"time": "13:10:35", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 817.9885595654318, "loss": 0.5189292952418327, "entropy": 0.5577503703534603, "sharp": 0.2263322975486517}
+{"time": "13:14:00", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 818.5885594405482, "loss": 0.7248121611773968, "entropy": 0.5662439949810505, "sharp": 0.21394966915249825}
+{"time": "13:17:32", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 819.258972805518, "loss": 0.568549009039998, "entropy": 0.5418598055839539, "sharp": 0.2290923986583948}
+{"time": "13:21:04", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 820.0843010722512, "loss": 0.34664853755384684, "entropy": 0.5586813353002071, "sharp": 0.22262434288859367}
+{"time": "13:24:39", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 820.5237510309239, "loss": 0.5983148724772036, "entropy": 0.5489839129149914, "sharp": 0.22317792102694511}
+{"time": "13:26:07", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.6579700708389282, "noul_T": 1.2135891261448262, "noul_auc": 0.7154815952473376, "noul_acc": 0.63, "noul_f1": 0.6489563567362429, "noul_nll": 0.6520484886020422, "noul_ece": 0.1714279436469078, "noul_brier": 0.23002566455107015, "noul_sharp": 0.1269138753414154, "entropy": 0.6419970989227295}
+{"time": "13:29:17", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 8943984, "tok_per_s": 800.2291356549823, "rows_per_s": 1.506874240361042, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.6381511092185974, "noul_T": 1.029952342237469, "choice_ce": 0.6812111735343933, "choice_T": 1.0577606522158263, "score_ce": 1.0487253665924072, "score_T": 0.9693892850617055, "noul_auc": 0.7012010666666667, "noul_acc": 0.623, "noul_f1": 0.6606660666066607, "noul_nll": 0.6497219701781869, "noul_ece": 0.15711297784745692, "noul_brier": 0.22903177858235785, "noul_sharp": 0.11895649135112762, "entropy": 0.6470414400100708}, "dropped_long": 0, "peak_gib": 18.235705852508545}