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

e16/S1-E19-a1-n16k-soft-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-soft-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",
+    "in_proj_qkv",
+    "down_proj",
+    "q_proj",
+    "out_proj",
+    "in_proj_z",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_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-soft-a100-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d4573e5a94df870f77126a3dce9abe8c047a6eefb604b20a3d0f3ab0719794
+size 160486456

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e7fe1750d6ebd0f6c036a2c8977354c0bf5493aff3d62e746713af834ad88c
+size 176641832

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

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0006658267229795456,
+  -0.0006660837680101395,
+  -0.0022681518457829952,
+  -0.0012672654120251536,
+  -0.00044467038242146373,
+  0.0018637655302882195,
+  0.001113274833187461,
+  -0.0023357649333775043,
+  -0.0004471878055483103,
+  -0.00019837715080939233,
+  5.3723335440736264e-05,
+  0.0004352069809101522,
+  -0.00019835689454339445,
+  -0.0034517450258135796,
+  -0.004249265417456627,
+  -0.005067416932433844,
+  -0.005925778765231371,
+  -0.004341768566519022,
+  -0.0049264864064753056,
+  -0.004925806075334549,
+  -0.0038481371011584997,
+  -0.003338830778375268,
+  -0.005609303712844849,
+  -0.003459909465163946
+ ],
+ "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-soft-a100-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.9114489262835489,
+  "choice": 1.057254374772595,
+  "score": 0.9152068187959267
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.9114489262835489,
+   "ce_before": 0.6224223375320435,
+   "ce_after": 0.6220250129699707
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.057254374772595,
+   "ce_before": 0.6652951836585999,
+   "ce_after": 0.6645907759666443
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9152068187959267,
+   "ce_before": 1.0459662675857544,
+   "ce_after": 1.0437508821487427
+  }
+ },
+ "source": "models/e16/S1-E19-a1-n16k-soft-a100-syn/ckpt-16000"
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3b3463fd64e184a919b16e233b3ecbacb5fa161270834bd4b9a99e0f1eb6db
+size 393464

e16/S1-E19-a1-n16k-soft-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-soft-a100-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e19/E19-a1-n16k-soft-a100",
+  "data_manifest": {
+   "arm": "E19-a1-n16k-soft-a100",
+   "name": null,
+   "train_sha256": "26c76407ec87e34f18ef4d716b29e42a18588832bf6066becc156828e266fd8d",
+   "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": 799.8102136880569,
+  "rows_per_s": 1.5060853878070437,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.6224223375320435,
+   "noul_T": 0.9114489262835489,
+   "choice_ce": 0.6652951836585999,
+   "choice_T": 1.057254374772595,
+   "score_ce": 1.0459662675857544,
+   "score_T": 0.9152068187959267,
+   "noul_auc": 0.7117696,
+   "noul_acc": 0.655,
+   "noul_f1": 0.7048759623609923,
+   "noul_nll": 0.6312288008481264,
+   "noul_ece": 0.13414508992433546,
+   "noul_brier": 0.22015866136246331,
+   "noul_sharp": 0.12622646987438202,
+   "entropy": 0.6429359316825867
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.235705852508545
+ }
+}

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

@@ -0,0 +1,57 @@
+{"time": "11:42:52", "event": "start", "data": "data/e19/E19-a1-n16k-soft-a100", "data_manifest": {"arm": "E19-a1-n16k-soft-a100", "name": null, "train_sha256": "26c76407ec87e34f18ef4d716b29e42a18588832bf6066becc156828e266fd8d", "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": 87.39138960838318}
+{"time": "11:46:24", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 833.045002964947, "loss": 0.588922917842865, "entropy": 0.6021130159497261, "sharp": 0.17588666453957558}
+{"time": "11:49:56", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 838.5924052389523, "loss": 0.6846533715724945, "entropy": 0.6910380870103836, "sharp": 0.02306802850216627}
+{"time": "11:53:18", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 841.6301510007838, "loss": 0.6661521978676319, "entropy": 0.5978059396147728, "sharp": 0.20922003965824842}
+{"time": "11:56:50", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 844.8019385424639, "loss": 0.672111114487052, "entropy": 0.5462029725313187, "sharp": 0.2420680020004511}
+{"time": "12:00:21", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 847.1717991932633, "loss": 0.6684608198702335, "entropy": 0.6568677686154842, "sharp": 0.11821198370307684}
+{"time": "12:03:56", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 848.6487143984357, "loss": 0.552405945956707, "entropy": 0.5897898375988007, "sharp": 0.20209896843880415}
+{"time": "12:07:22", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 847.7344429147342, "loss": 0.5188641361892223, "entropy": 0.6364869475364685, "sharp": 0.13697880692780018}
+{"time": "12:10:53", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 847.9683708874908, "loss": 0.6211176682263613, "entropy": 0.620494456961751, "sharp": 0.14520255476236343}
+{"time": "12:14:33", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 848.5730778642486, "loss": 0.5867630913853645, "entropy": 0.5737877376377583, "sharp": 0.2130492264404893}
+{"time": "12:18:02", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 847.8368070077156, "loss": 0.5943211764097214, "entropy": 0.5628568381071091, "sharp": 0.22679613903164864}
+{"time": "12:19:31", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5962151885032654, "noul_T": 0.855300576648382, "noul_auc": 0.7396162090091306, "noul_acc": 0.7, "noul_f1": 0.7648902821316614, "noul_nll": 0.5883893258273601, "noul_ece": 0.08294241684675217, "noul_brier": 0.19997528592409883, "noul_sharp": 0.1696518510580063, "entropy": 0.6174163222312927}
+{"time": "12:23:03", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 816.8766375980072, "loss": 0.5991598144173622, "entropy": 0.5670166835188866, "sharp": 0.22352871671319008}
+{"time": "12:26:35", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 819.1960774745488, "loss": 0.585709735751152, "entropy": 0.608031690120697, "sharp": 0.1612020917236805}
+{"time": "12:30:11", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 821.1672654573591, "loss": 0.5629651173949242, "entropy": 0.6097195222973824, "sharp": 0.17390846461057663}
+{"time": "12:33:46", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 823.1869020762318, "loss": 0.5362141355872154, "entropy": 0.6094481460750103, "sharp": 0.18048185296356678}
+{"time": "12:37:22", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 824.6688560820248, "loss": 0.5523114912211895, "entropy": 0.5417928174138069, "sharp": 0.23383033648133278}
+{"time": "12:40:57", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 825.9575083602982, "loss": 0.5794190187007189, "entropy": 0.5382421314716339, "sharp": 0.23697717301547527}
+{"time": "12:44:30", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 826.9842393305223, "loss": 0.6229254510253668, "entropy": 0.41902289167046547, "sharp": 0.30930429697036743}
+{"time": "12:48:03", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 828.370290529386, "loss": 0.49636731296777725, "entropy": 0.6162767820060253, "sharp": 0.1822980809956789}
+{"time": "12:51:33", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 829.2403496425219, "loss": 0.49741293862462044, "entropy": 0.511407520622015, "sharp": 0.27605065517127514}
+{"time": "12:55:09", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 830.2659905522881, "loss": 0.6265465468168259, "entropy": 0.5433985404670238, "sharp": 0.24515043199062347}
+{"time": "12:56:37", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.6342898607254028, "noul_T": 1.1485404335145972, "noul_auc": 0.7080555602437089, "noul_acc": 0.674, "noul_f1": 0.7232597623089984, "noul_nll": 0.617951015740633, "noul_ece": 0.10988062268495559, "noul_brier": 0.21429277833614635, "noul_sharp": 0.16713516414165497, "entropy": 0.6170523762702942}
+{"time": "13:00:02", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 814.9638584856447, "loss": 0.5445428052917123, "entropy": 0.6136729270219803, "sharp": 0.16579995956271887}
+{"time": "13:03:33", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 816.2879168358388, "loss": 0.5680861752480268, "entropy": 0.5633813664317131, "sharp": 0.22864008322358131}
+{"time": "13:07:06", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 817.530963309837, "loss": 0.5666002985090017, "entropy": 0.5461645387113094, "sharp": 0.23473116382956505}
+{"time": "13:10:36", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 818.6152142850999, "loss": 0.586516983807087, "entropy": 0.5211193859577179, "sharp": 0.2518439032137394}
+{"time": "13:14:13", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 819.2063564651986, "loss": 0.5545659437775612, "entropy": 0.5577898062765598, "sharp": 0.2275696061551571}
+{"time": "13:17:40", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 820.062669692517, "loss": 0.46058891993016005, "entropy": 0.5386128015816212, "sharp": 0.24167500436306}
+{"time": "13:21:05", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 820.8843295921346, "loss": 0.5058119799941778, "entropy": 0.565500020980835, "sharp": 0.2239266335964203}
+{"time": "13:24:44", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 822.2322944431492, "loss": 0.5481334328651428, "entropy": 0.6028634607791901, "sharp": 0.17307910695672035}
+{"time": "13:28:09", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 823.2309101721536, "loss": 0.5663433335721493, "entropy": 0.519042007625103, "sharp": 0.2564035151153803}
+{"time": "13:31:41", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 823.8825578679619, "loss": 0.6125295609235764, "entropy": 0.6427918300032616, "sharp": 0.12503604125231504}
+{"time": "13:33:10", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.6368759870529175, "noul_T": 0.5320408028986313, "noul_auc": 0.7128656056437866, "noul_acc": 0.692, "noul_f1": 0.7433333333333333, "noul_nll": 0.6319964309036732, "noul_ece": 0.12918312162160875, "noul_brier": 0.22017683533050206, "noul_sharp": 0.0868634358048439, "entropy": 0.6702858805656433}
+{"time": "13:36:31", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 813.8884628223929, "loss": 0.5843488276004791, "entropy": 0.6127106919884682, "sharp": 0.16960112936794758}
+{"time": "13:39:55", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 814.6310314016416, "loss": 0.7197622507810593, "entropy": 0.5646428242325783, "sharp": 0.21796787530183792}
+{"time": "13:43:24", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 815.6557601710133, "loss": 0.5784352049231529, "entropy": 0.5157584249973297, "sharp": 0.23875261191278696}
+{"time": "13:47:01", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 816.6958798111687, "loss": 0.5721590183675289, "entropy": 0.5801337212324142, "sharp": 0.19855961576104164}
+{"time": "13:50:24", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 817.6024403275716, "loss": 0.6272653751075268, "entropy": 0.5256512351334095, "sharp": 0.24470312520861626}
+{"time": "13:54:06", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 818.4129216282679, "loss": 0.5601907148957253, "entropy": 0.5658868476748466, "sharp": 0.1933346427977085}
+{"time": "13:57:39", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 819.2607180204641, "loss": 0.5955355130136013, "entropy": 0.5704315751791, "sharp": 0.18660753779113293}
+{"time": "14:01:02", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 819.8601798315927, "loss": 0.6904039829969406, "entropy": 0.511899490840733, "sharp": 0.24448657780885696}
+{"time": "14:04:29", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 820.4708968536918, "loss": 0.5958489011973143, "entropy": 0.5645651370286942, "sharp": 0.20982736721634865}
+{"time": "14:07:59", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 821.1821068275964, "loss": 0.5036460254341364, "entropy": 0.5719989649951458, "sharp": 0.20386691577732563}
+{"time": "14:09:27", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.6395184993743896, "noul_T": 0.8266468933649221, "noul_auc": 0.7279370812306966, "noul_acc": 0.67, "noul_f1": 0.7069271758436945, "noul_nll": 0.632122870117426, "noul_ece": 0.1352908192873001, "noul_brier": 0.22041567304821358, "noul_sharp": 0.11165791004896164, "entropy": 0.6533892154693604}
+{"time": "14:12:57", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 813.802433499434, "loss": 0.6287189461290836, "entropy": 0.5764273591339588, "sharp": 0.20393908582627773}
+{"time": "14:16:30", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 814.5731110232023, "loss": 0.6615785881876945, "entropy": 0.5217020995914936, "sharp": 0.2479446791112423}
+{"time": "14:20:02", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 815.497796567564, "loss": 0.6035016844980419, "entropy": 0.5069842571392655, "sharp": 0.26279960945248604}
+{"time": "14:23:34", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 815.9498013257964, "loss": 0.6159990951418877, "entropy": 0.48702458292245865, "sharp": 0.2891466598957777}
+{"time": "14:27:09", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 816.8176237196193, "loss": 0.5535023231059313, "entropy": 0.528935207054019, "sharp": 0.2459303755313158}
+{"time": "14:30:36", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 817.3091180175996, "loss": 0.5377992875874043, "entropy": 0.5508109740912914, "sharp": 0.22673368453979492}
+{"time": "14:34:01", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 818.0065653376412, "loss": 0.6162302289158106, "entropy": 0.5840697642415762, "sharp": 0.1880231313407421}
+{"time": "14:37:33", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 818.673447878204, "loss": 0.5571026224642992, "entropy": 0.5564380884170532, "sharp": 0.20396986231207848}
+{"time": "14:41:05", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 819.497433720899, "loss": 0.43161831982433796, "entropy": 0.5723839905112982, "sharp": 0.2016696110367775}
+{"time": "14:44:39", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 820.0609426459966, "loss": 0.6136300815269351, "entropy": 0.5593843199312687, "sharp": 0.21258223615586758}
+{"time": "14:46:07", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.6427628993988037, "noul_T": 1.046814857769061, "noul_auc": 0.7272788644917385, "noul_acc": 0.668, "noul_f1": 0.7046263345195729, "noul_nll": 0.6316258210390806, "noul_ece": 0.14266333568096162, "noul_brier": 0.22007706664471674, "noul_sharp": 0.1327688843011856, "entropy": 0.6386560201644897}
+{"time": "14:49:17", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 8943984, "tok_per_s": 799.8102136880569, "rows_per_s": 1.5060853878070437, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.6224223375320435, "noul_T": 0.9114489262835489, "choice_ce": 0.6652951836585999, "choice_T": 1.057254374772595, "score_ce": 1.0459662675857544, "score_T": 0.9152068187959267, "noul_auc": 0.7117696, "noul_acc": 0.655, "noul_f1": 0.7048759623609923, "noul_nll": 0.6312288008481264, "noul_ece": 0.13414508992433546, "noul_brier": 0.22015866136246331, "noul_sharp": 0.12622646987438202, "entropy": 0.6429359316825867}, "dropped_long": 0, "peak_gib": 18.235705852508545}