backup e16/S1-MIX-E18E19-n16k-syn (Pod B)

e16/S1-MIX-E18E19-n16k-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-MIX-E18E19-n16k-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",
+    "q_proj",
+    "in_proj_qkv",
+    "out_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "in_proj_z",
+    "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-MIX-E18E19-n16k-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9558c80a20a5d3984fb783929370cbc892cb0abc3fcb0ae6c759c110b735255e
+size 160486456

e16/S1-MIX-E18E19-n16k-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-MIX-E18E19-n16k-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926fc7b86d5234c3c2c66fb6e3273a479f22c67720e0cc406661938d8a2affaf
+size 176641832

e16/S1-MIX-E18E19-n16k-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0005538347759284079,
+  -0.00055409298511222,
+  -0.002143150195479393,
+  -0.0015476744156330824,
+  -0.0004421252233441919,
+  0.0018956552958115935,
+  0.001235729898326099,
+  -0.0023153629153966904,
+  -0.00035404376103542745,
+  -0.0003437245322857052,
+  -5.0134898629039526e-05,
+  0.0006978277233429253,
+  -0.00027858413523063064,
+  -0.003457631915807724,
+  -0.004375374875962734,
+  -0.00513782724738121,
+  -0.005981497000902891,
+  -0.004383038263767958,
+  -0.004941539838910103,
+  -0.004990904591977596,
+  -0.003767705522477627,
+  -0.0034003336913883686,
+  -0.005695451516658068,
+  -0.0034970836713910103
+ ],
+ "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-MIX-E18E19-n16k-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8751727618537676,
+  "choice": 1.0150718081591845,
+  "score": 1.0349391062070443
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.8751727618537676,
+   "ce_before": 0.5610436201095581,
+   "ce_after": 0.5595861673355103
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0150718081591845,
+   "ce_before": 0.671417772769928,
+   "ce_after": 0.6713714599609375
+  },
+  "score": {
+   "n": 53,
+   "T": 1.0349391062070443,
+   "ce_before": 1.072701096534729,
+   "ce_after": 1.0723479986190796
+  }
+ },
+ "source": "models/e16/S1-MIX-E18E19-n16k-syn/ckpt-16000"
+}

e16/S1-MIX-E18E19-n16k-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fac41d0a8cbfb22eb17409812bc761366f2b630580b534d2a34c3521f3c46d
+size 393464

e16/S1-MIX-E18E19-n16k-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-MIX-E18E19-n16k-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e20/MIX-E18E19-n16k",
+  "data_manifest": {
+   "arm": "MIX-E18E19-n16k",
+   "name": null,
+   "train_sha256": "ba13b9d4db176b12973a734bd6bd6f1ba0ba7fb8f84865ceeea1428f2a55812f",
+   "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": 9086141,
+  "tok_per_s": 828.4453207820701,
+  "rows_per_s": 1.5355997763134102,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5610436201095581,
+   "noul_T": 0.8751727618537676,
+   "choice_ce": 0.671417772769928,
+   "choice_T": 1.0150718081591845,
+   "score_ce": 1.072701096534729,
+   "score_T": 1.0349391062070443,
+   "noul_auc": 0.7408511999999999,
+   "noul_acc": 0.694,
+   "noul_f1": 0.7656967840735069,
+   "noul_nll": 0.5750355223156511,
+   "noul_ece": 0.05720370879769325,
+   "noul_brier": 0.19642639417583996,
+   "noul_sharp": 0.18411453068256378,
+   "entropy": 0.59227454662323
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.237416744232178
+ }
+}

e16/S1-MIX-E18E19-n16k-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "18:12:17", "event": "start", "data": "data/e20/MIX-E18E19-n16k", "data_manifest": {"arm": "MIX-E18E19-n16k", "name": null, "train_sha256": "ba13b9d4db176b12973a734bd6bd6f1ba0ba7fb8f84865ceeea1428f2a55812f", "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": 90.94873237609863}
+{"time": "18:15:48", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 856.2015115487613, "loss": 0.5910945609211922, "entropy": 0.6128711700439453, "sharp": 0.17914598621428013}
+{"time": "18:19:20", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 867.435322211945, "loss": 0.6039625704288483, "entropy": 0.6315186154097319, "sharp": 0.14092257898300886}
+{"time": "18:22:46", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 873.4560366260295, "loss": 0.6668390035629272, "entropy": 0.5564631447196007, "sharp": 0.23058079183101654}
+{"time": "18:26:10", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 873.2776225053261, "loss": 0.6103467233479023, "entropy": 0.6172405257821083, "sharp": 0.16298955585807562}
+{"time": "18:29:31", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 872.7369073201618, "loss": 0.6230732388794422, "entropy": 0.660416267812252, "sharp": 0.10554463509470224}
+{"time": "18:33:00", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 874.0140170510948, "loss": 0.5733295418322086, "entropy": 0.5668243132531643, "sharp": 0.21512411162257195}
+{"time": "18:36:27", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 875.4605570493254, "loss": 0.5945744849741459, "entropy": 0.6177707985043526, "sharp": 0.16127404384315014}
+{"time": "18:39:58", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 874.6413386459209, "loss": 0.5991457849740982, "entropy": 0.5960103273391724, "sharp": 0.18788549583405256}
+{"time": "18:43:27", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 874.427234433007, "loss": 0.5869529908522964, "entropy": 0.5615637470036745, "sharp": 0.22855196334421635}
+{"time": "18:46:54", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 874.3313841454019, "loss": 0.5538884289562702, "entropy": 0.5894552692770958, "sharp": 0.1847353633493185}
+{"time": "18:48:17", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.6102227568626404, "noul_T": 0.7953906930988737, "noul_auc": 0.7445443958751752, "noul_acc": 0.68, "noul_f1": 0.7163120567375887, "noul_nll": 0.6081427060365677, "noul_ece": 0.11193782103061678, "noul_brier": 0.20994903035748474, "noul_sharp": 0.1390538066625595, "entropy": 0.6341201066970825}
+{"time": "18:51:54", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 843.96242214572, "loss": 0.6013364130631089, "entropy": 0.5801065247505903, "sharp": 0.2037685327231884}
+{"time": "18:55:27", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 846.4262384099914, "loss": 0.645103495568037, "entropy": 0.6143962442874908, "sharp": 0.15814609453082085}
+{"time": "18:58:53", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 848.0368319321688, "loss": 0.5380914397537708, "entropy": 0.6066201888024807, "sharp": 0.18104170635342598}
+{"time": "19:02:26", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 850.095553946079, "loss": 0.5551523715257645, "entropy": 0.6021782122552395, "sharp": 0.1850847341120243}
+{"time": "19:05:39", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 851.1223790275718, "loss": 0.6208911864086986, "entropy": 0.5740309190005064, "sharp": 0.2051469124853611}
+{"time": "19:09:03", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 852.4654445577897, "loss": 0.6660349164158106, "entropy": 0.591098852455616, "sharp": 0.19115800969302654}
+{"time": "19:12:38", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 854.7295925262056, "loss": 0.6734093353152275, "entropy": 0.5890645608305931, "sharp": 0.20002372190356255}
+{"time": "19:16:07", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 855.453323814641, "loss": 0.5560750868171453, "entropy": 0.5941686686128378, "sharp": 0.18030551448464394}
+{"time": "19:19:39", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 856.6682761294571, "loss": 0.5706328377127647, "entropy": 0.5999313071370125, "sharp": 0.17803552746772766}
+{"time": "19:23:07", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 857.5030783484716, "loss": 0.626886522397399, "entropy": 0.5912183970212936, "sharp": 0.18365227337926626}
+{"time": "19:24:31", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5945950746536255, "noul_T": 1.0002400246445513, "noul_auc": 0.7436330188520025, "noul_acc": 0.692, "noul_f1": 0.7398648648648649, "noul_nll": 0.5940811600089073, "noul_ece": 0.08846133857965471, "noul_brier": 0.20372273175101402, "noul_sharp": 0.18138056993484497, "entropy": 0.5945013165473938}
+{"time": "19:28:00", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 842.5425074789878, "loss": 0.6095570512115955, "entropy": 0.5763310268521309, "sharp": 0.19983317516744137}
+{"time": "19:31:27", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 843.7583320449322, "loss": 0.48227665573358536, "entropy": 0.5190770588815212, "sharp": 0.2601925879716873}
+{"time": "19:34:58", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 844.9711802923222, "loss": 0.6189186163246632, "entropy": 0.6222886294126511, "sharp": 0.1527715865522623}
+{"time": "19:38:32", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 845.9860096873075, "loss": 0.594485305249691, "entropy": 0.5993044674396515, "sharp": 0.18067020550370216}
+{"time": "19:41:51", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 846.8016862431099, "loss": 0.6110380291938782, "entropy": 0.6181324496865273, "sharp": 0.16106490138918161}
+{"time": "19:45:17", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 847.6525793641177, "loss": 0.6586330756545067, "entropy": 0.6264025196433067, "sharp": 0.13325349614024162}
+{"time": "19:48:42", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 848.6182184540294, "loss": 0.6169783994555473, "entropy": 0.6110673658549786, "sharp": 0.1817007791250944}
+{"time": "19:52:05", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 849.3431557685277, "loss": 0.6417281106114388, "entropy": 0.5882612615823746, "sharp": 0.1967076165601611}
+{"time": "19:55:33", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 850.2790857955396, "loss": 0.6232142075896263, "entropy": 0.5885290503501892, "sharp": 0.19435120932757854}
+{"time": "19:59:04", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 851.4311842937504, "loss": 0.6320807114243507, "entropy": 0.6034808456897736, "sharp": 0.16463040839880705}
+{"time": "20:00:27", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5944254994392395, "noul_T": 0.7469657915517918, "noul_auc": 0.7545189110732309, "noul_acc": 0.704, "noul_f1": 0.7482993197278912, "noul_nll": 0.5899844839125872, "noul_ece": 0.11533634048700332, "noul_brier": 0.20176810427456643, "noul_sharp": 0.14755597710609436, "entropy": 0.627729594707489}
+{"time": "20:04:01", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 841.8722517346255, "loss": 0.4955503735691309, "entropy": 0.5355878584086895, "sharp": 0.24201007187366486}
+{"time": "20:07:33", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 843.0654051820238, "loss": 0.60224533919245, "entropy": 0.6131217647343874, "sharp": 0.16305802576243877}
+{"time": "20:10:53", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 844.1481950664163, "loss": 0.590254582464695, "entropy": 0.6148912906646729, "sharp": 0.1722602117806673}
+{"time": "20:14:17", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 845.1835350224319, "loss": 0.5726158581674099, "entropy": 0.5842449590563774, "sharp": 0.18641688488423824}
+{"time": "20:17:45", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 846.2507222771873, "loss": 0.5730059593915939, "entropy": 0.553474847227335, "sharp": 0.22218932211399078}
+{"time": "20:21:18", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 847.0911137225455, "loss": 0.5912212058901787, "entropy": 0.542980395257473, "sharp": 0.22978665865957737}
+{"time": "20:24:41", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 848.0397391858016, "loss": 0.5746152903884649, "entropy": 0.6082169003784657, "sharp": 0.16986137069761753}
+{"time": "20:27:57", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 848.7295230062916, "loss": 0.634641632437706, "entropy": 0.5945497415959835, "sharp": 0.19308296777307987}
+{"time": "20:31:24", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 849.3321223641248, "loss": 0.6202500853687525, "entropy": 0.5706854965537786, "sharp": 0.19744966737926006}
+{"time": "20:34:51", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 849.8624961829468, "loss": 0.6164764575660229, "entropy": 0.5772212389856577, "sharp": 0.20606796629726887}
+{"time": "20:36:15", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5687903165817261, "noul_T": 0.9139744345224954, "noul_auc": 0.7536244114023392, "noul_acc": 0.704, "noul_f1": 0.774390243902439, "noul_nll": 0.5680907810851932, "noul_ece": 0.06584550815820696, "noul_brier": 0.19344708074123493, "noul_sharp": 0.1899472028017044, "entropy": 0.5835056304931641}
+{"time": "20:39:36", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 842.2843700454285, "loss": 0.5783768184483051, "entropy": 0.5865571163594723, "sharp": 0.19377531856298447}
+{"time": "20:43:14", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 843.0841776285129, "loss": 0.5885072015225887, "entropy": 0.6030223108828068, "sharp": 0.18002171628177166}
+{"time": "20:46:47", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 843.9126751122953, "loss": 0.6208619438111782, "entropy": 0.5966559685766697, "sharp": 0.17650933843106031}
+{"time": "20:50:18", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 844.784481402997, "loss": 0.5554603170603514, "entropy": 0.5721810348331928, "sharp": 0.21450471878051758}
+{"time": "20:53:44", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 845.5539240792273, "loss": 0.6192282103002071, "entropy": 0.606688778847456, "sharp": 0.17560429219156504}
+{"time": "20:57:09", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 846.152482062666, "loss": 0.607556413859129, "entropy": 0.602709211409092, "sharp": 0.16547550167888403}
+{"time": "21:00:29", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 846.6680356447658, "loss": 0.6334729269146919, "entropy": 0.6234759539365768, "sharp": 0.1531918402761221}
+{"time": "21:03:50", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 847.3018715086054, "loss": 0.5987235065549612, "entropy": 0.5939801447093487, "sharp": 0.190364645794034}
+{"time": "21:07:15", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 848.0809647694914, "loss": 0.5406575873494148, "entropy": 0.5900666937232018, "sharp": 0.19450743310153484}
+{"time": "21:10:43", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 848.6645995286307, "loss": 0.578721184283495, "entropy": 0.5857630036771297, "sharp": 0.180152484215796}
+{"time": "21:12:07", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5748822093009949, "noul_T": 0.8815254849066488, "noul_auc": 0.7501983088893014, "noul_acc": 0.696, "noul_f1": 0.7579617834394905, "noul_nll": 0.5747102235332131, "noul_ece": 0.060916461706161516, "noul_brier": 0.19611031258817405, "noul_sharp": 0.18125006556510925, "entropy": 0.5941748023033142}
+{"time": "21:15:07", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9086141, "tok_per_s": 828.4453207820701, "rows_per_s": 1.5355997763134102, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5610436201095581, "noul_T": 0.8751727618537676, "choice_ce": 0.671417772769928, "choice_T": 1.0150718081591845, "score_ce": 1.072701096534729, "score_T": 1.0349391062070443, "noul_auc": 0.7408511999999999, "noul_acc": 0.694, "noul_f1": 0.7656967840735069, "noul_nll": 0.5750355223156511, "noul_ece": 0.05720370879769325, "noul_brier": 0.19642639417583996, "noul_sharp": 0.18411453068256378, "entropy": 0.59227454662323}, "dropped_long": 0, "peak_gib": 18.237416744232178}