backup e16/S1-ABCLODO16-algebra2005 (Pod B)

e16/S1-ABCLODO16-algebra2005/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-ABCLODO16-algebra2005/ckpt-16000/adapter/adapter_config.json

@@ -0,0 +1,57 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForCausalLM",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
+  },
+  "base_model_name_or_path": "/workspace/jev_kt/models/hf/JEV-9B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_z",
+    "gate_proj",
+    "in_proj_qkv",
+    "o_proj",
+    "v_proj",
+    "out_proj",
+    "q_proj",
+    "down_proj",
+    "up_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-ABCLODO16-algebra2005/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4bc40dba5af94b9f7bce28b84ccd40210f0ca4f873b675d62136b4e6c943a6
+size 160486456

e16/S1-ABCLODO16-algebra2005/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-ABCLODO16-algebra2005/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4a28cf69b9c6d240cd4215d1f4523030b6627c0541b36b3e2adcb4efdbda7b
+size 176641832

e16/S1-ABCLODO16-algebra2005/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0004257883410900831,
+  -0.00042604756890796125,
+  -0.0023042927496135235,
+  -0.0016022558556869626,
+  -0.000798841065261513,
+  0.001815550378523767,
+  0.001182276988402009,
+  -0.002107820240780711,
+  -0.000263647292740643,
+  -0.00033289031125605106,
+  0.00017901301907841116,
+  0.0005971578066237271,
+  0.00014491035835817456,
+  -0.004085839726030827,
+  -0.004938725382089615,
+  -0.005196988582611084,
+  -0.005909585393965244,
+  -0.004485780838876963,
+  -0.005001697223633528,
+  -0.005216957535594702,
+  -0.004247116390615702,
+  -0.0036851181648671627,
+  -0.0057541667483747005,
+  -0.0036142810713499784
+ ],
+ "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-ABCLODO16-algebra2005/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8437305378688278,
+  "choice": 1.031541289168218,
+  "score": 0.974046797619904
+ },
+ "fit": {
+  "noul": {
+   "n": 1801,
+   "T": 0.8437305378688278,
+   "ce_before": 0.5268602967262268,
+   "ce_after": 0.5239372253417969
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.031541289168218,
+   "ce_before": 0.658643364906311,
+   "ce_after": 0.6584425568580627
+  },
+  "score": {
+   "n": 53,
+   "T": 0.974046797619904,
+   "ce_before": 1.0547399520874023,
+   "ce_after": 1.0545295476913452
+  }
+ },
+ "source": "models/e16/S1-ABCLODO16-algebra2005/ckpt-16000"
+}

e16/S1-ABCLODO16-algebra2005/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7918d035bed39f76f487ac8d197dd5b243b017383743788cbc10127809b28a
+size 393464

e16/S1-ABCLODO16-algebra2005/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-ABCLODO16-algebra2005/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e15/F1-pool-jev-LODO-algebra2005",
+  "data_manifest": {
+   "arm": "F1-pool-jev-LODO-algebra2005",
+   "name": "F1-pool-jev-LODO-algebra2005",
+   "train_sha256": "3e20ff0b5e790e3e7f26f3bdaaa3c15f530ccef021f0efbf06a44c0a2e5bc521",
+   "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": 9615732,
+  "tok_per_s": 818.5192013869797,
+  "rows_per_s": 1.4336402451946022,
+  "val": {
+   "n": 1914,
+   "dropped_long": 0,
+   "noul_ce": 0.5268602967262268,
+   "noul_T": 0.8437305378688278,
+   "choice_ce": 0.658643364906311,
+   "choice_T": 1.031541289168218,
+   "score_ce": 1.0547399520874023,
+   "score_T": 0.974046797619904,
+   "noul_auc": 0.7843765137231815,
+   "noul_acc": 0.73512252042007,
+   "noul_f1": 0.7998236331569665,
+   "noul_nll": 0.5315972880667886,
+   "noul_ece": 0.041881909448318745,
+   "noul_brier": 0.17758800465233748,
+   "noul_sharp": 0.214067280292511,
+   "entropy": 0.5644049644470215
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.235232830047607
+ }
+}

e16/S1-ABCLODO16-algebra2005/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "20:25:54", "event": "start", "data": "data/e15/F1-pool-jev-LODO-algebra2005", "data_manifest": {"arm": "F1-pool-jev-LODO-algebra2005", "name": "F1-pool-jev-LODO-algebra2005", "train_sha256": "3e20ff0b5e790e3e7f26f3bdaaa3c15f530ccef021f0efbf06a44c0a2e5bc521", "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": 84.25058960914612}
+{"time": "20:29:37", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 877.0633407652533, "loss": 0.6163181290030479, "entropy": 0.5646605938673019, "sharp": 0.2108820676803589}
+{"time": "20:33:19", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 874.0850558896001, "loss": 0.5928459651768208, "entropy": 0.5348040238022804, "sharp": 0.23297069221735}
+{"time": "20:37:01", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 873.9794628141669, "loss": 0.5556608159095049, "entropy": 0.5236891116946936, "sharp": 0.25772849842906}
+{"time": "20:40:43", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 874.1991220160903, "loss": 0.5899911681190133, "entropy": 0.6380737088620663, "sharp": 0.14333672262728214}
+{"time": "20:44:20", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 876.4504694455342, "loss": 0.624206118285656, "entropy": 0.5202877074480057, "sharp": 0.2618987448513508}
+{"time": "20:48:01", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 876.7499673272679, "loss": 0.5814247131347656, "entropy": 0.6003498435020447, "sharp": 0.18525872938334942}
+{"time": "20:51:39", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 876.5127690027238, "loss": 0.582489401102066, "entropy": 0.5760254412889481, "sharp": 0.1876644231379032}
+{"time": "20:55:18", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 876.9000473378468, "loss": 0.6054622046649456, "entropy": 0.5904636830091476, "sharp": 0.2012663632631302}
+{"time": "20:59:00", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 877.0483955952358, "loss": 0.6214403361082077, "entropy": 0.5750461779534817, "sharp": 0.2188836671411991}
+{"time": "21:02:33", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 876.8421552565137, "loss": 0.5856427252292633, "entropy": 0.58738212287426, "sharp": 0.1778053194284439}
+{"time": "21:04:06", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5509954690933228, "noul_T": 0.7857555439858478, "noul_auc": 0.7622305728871244, "noul_acc": 0.714, "noul_f1": 0.783661119515885, "noul_nll": 0.5509954926967621, "noul_ece": 0.08088283193111422, "noul_brier": 0.18571909053840938, "noul_sharp": 0.19093331694602966, "entropy": 0.5905840396881104}
+{"time": "21:07:41", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 843.6024344717987, "loss": 0.530875701457262, "entropy": 0.5694689378142357, "sharp": 0.20996871776878834}
+{"time": "21:11:23", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 845.7669249231344, "loss": 0.5958671644330025, "entropy": 0.558093711733818, "sharp": 0.2343120165169239}
+{"time": "21:15:03", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 848.102476505493, "loss": 0.5903111808001995, "entropy": 0.60843076556921, "sharp": 0.1738066952675581}
+{"time": "21:18:45", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 850.3809237417929, "loss": 0.5418108813464642, "entropy": 0.5756772086024284, "sharp": 0.20441205333918333}
+{"time": "21:22:20", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 852.0628266916144, "loss": 0.6820017397403717, "entropy": 0.5724130049347878, "sharp": 0.20827661454677582}
+{"time": "21:25:58", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 853.4335278119289, "loss": 0.650178350508213, "entropy": 0.5880794450640678, "sharp": 0.18731006048619747}
+{"time": "21:29:39", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 855.0240864601037, "loss": 0.6085174791514874, "entropy": 0.5828424766659737, "sharp": 0.18879341706633568}
+{"time": "21:33:19", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 855.9836926937751, "loss": 0.556072099134326, "entropy": 0.5716801844537258, "sharp": 0.19471389427781105}
+{"time": "21:36:54", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 857.1707451412102, "loss": 0.5569462087005377, "entropy": 0.5259438809007406, "sharp": 0.243586715310812}
+{"time": "21:40:34", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 858.2815802319901, "loss": 0.6113039888441563, "entropy": 0.5060208886861801, "sharp": 0.2692507114261389}
+{"time": "21:42:07", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5413312911987305, "noul_T": 0.9238786942249207, "noul_auc": 0.7638613159387407, "noul_acc": 0.736, "noul_f1": 0.8070175438596491, "noul_nll": 0.5413312581852079, "noul_ece": 0.05677143752574921, "noul_brier": 0.18146175735362793, "noul_sharp": 0.2183174192905426, "entropy": 0.5571559071540833}
+{"time": "21:45:47", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 842.4586207628992, "loss": 0.6403232365846634, "entropy": 0.6268881782889366, "sharp": 0.14933013916015625}
+{"time": "21:49:24", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 843.537674309887, "loss": 0.5142319872975349, "entropy": 0.5400103107094765, "sharp": 0.23541546426713467}
+{"time": "21:53:03", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 844.655665346897, "loss": 0.5263765342533588, "entropy": 0.5032942183315754, "sharp": 0.2646155208349228}
+{"time": "21:56:45", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 846.1080395844351, "loss": 0.5591904548928142, "entropy": 0.5531947333365679, "sharp": 0.22286729514598846}
+{"time": "22:00:26", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 847.4358973951068, "loss": 0.5999408848583698, "entropy": 0.5975480936467648, "sharp": 0.17616480216383934}
+{"time": "22:04:05", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 848.7588019239154, "loss": 0.5316345654428005, "entropy": 0.5388349071145058, "sharp": 0.25320821069180965}
+{"time": "22:07:45", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 849.4195489479487, "loss": 0.5253276526927948, "entropy": 0.5702388510107994, "sharp": 0.21211008727550507}
+{"time": "22:11:27", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 850.5240682325234, "loss": 0.5609802827239037, "entropy": 0.5514357686042786, "sharp": 0.22274786606431007}
+{"time": "22:15:03", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 851.3984559933655, "loss": 0.5997639670968056, "entropy": 0.6092598661780357, "sharp": 0.17542470432817936}
+{"time": "22:18:42", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 852.520919590221, "loss": 0.662249282002449, "entropy": 0.5364976935088634, "sharp": 0.23141703009605408}
+{"time": "22:20:16", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5334437489509583, "noul_T": 1.0002632687631674, "noul_auc": 0.7691612308564947, "noul_acc": 0.734, "noul_f1": 0.8124118476727785, "noul_nll": 0.5334437018036843, "noul_ece": 0.05969960308074952, "noul_brier": 0.17901649886612445, "noul_sharp": 0.2321663796901703, "entropy": 0.5333390831947327}
+{"time": "22:23:51", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 841.871557494443, "loss": 0.5761331245303154, "entropy": 0.5865519866347313, "sharp": 0.19403651729226112}
+{"time": "22:27:28", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 842.8223121622805, "loss": 0.5809413604438305, "entropy": 0.5622905679047108, "sharp": 0.20583797991275787}
+{"time": "22:31:08", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 844.0625811751652, "loss": 0.5536311864852905, "entropy": 0.5841734185814857, "sharp": 0.18942509777843952}
+{"time": "22:34:44", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 845.0903388666507, "loss": 0.5877197002992034, "entropy": 0.5794639214873314, "sharp": 0.18704485148191452}
+{"time": "22:38:23", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 846.2453000693953, "loss": 0.6222841069102287, "entropy": 0.5973845720291138, "sharp": 0.18529586866497993}
+{"time": "22:42:02", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 847.1938068622701, "loss": 0.6621196568012238, "entropy": 0.6006181687116623, "sharp": 0.1774719338864088}
+{"time": "22:45:42", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 848.053577741812, "loss": 0.5588612947613001, "entropy": 0.5538235753774643, "sharp": 0.22706357203423977}
+{"time": "22:49:20", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 848.818667371423, "loss": 0.6123428549617529, "entropy": 0.5573387481272221, "sharp": 0.20310528669506311}
+{"time": "22:52:59", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 849.5813203110888, "loss": 0.6277705729007721, "entropy": 0.5980867110192776, "sharp": 0.18660707958042622}
+{"time": "22:56:40", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 850.1489351517562, "loss": 0.5704017020761967, "entropy": 0.5806789081543684, "sharp": 0.20103364251554012}
+{"time": "22:58:13", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5450872778892517, "noul_T": 0.8746814979962089, "noul_auc": 0.7613620249574589, "noul_acc": 0.722, "noul_f1": 0.7916041979010495, "noul_nll": 0.5450873227342963, "noul_ece": 0.07963733690977098, "noul_brier": 0.18367417164795835, "noul_sharp": 0.20684006810188293, "entropy": 0.5696081519126892}
+{"time": "23:01:49", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 842.4551951996289, "loss": 0.6229969672858715, "entropy": 0.5814150795340538, "sharp": 0.19780864380300045}
+{"time": "23:05:27", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 843.4283828463111, "loss": 0.5564611367881298, "entropy": 0.5699611902236938, "sharp": 0.2025282196700573}
+{"time": "23:09:09", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 844.012463586118, "loss": 0.603136770427227, "entropy": 0.5819652825593948, "sharp": 0.19714265130460262}
+{"time": "23:12:54", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 844.3664254585981, "loss": 0.6040152497589588, "entropy": 0.6139626950025558, "sharp": 0.1569946762174368}
+{"time": "23:16:31", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 845.21327619196, "loss": 0.6316507533192635, "entropy": 0.6195649430155754, "sharp": 0.14638809766620398}
+{"time": "23:20:10", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 845.9391986296669, "loss": 0.5696476958692074, "entropy": 0.5613267160952091, "sharp": 0.21176292933523655}
+{"time": "23:23:47", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 846.6311396942564, "loss": 0.6234072968363762, "entropy": 0.606579601764679, "sharp": 0.16244059056043625}
+{"time": "23:27:26", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 847.3289311054251, "loss": 0.5977704599499702, "entropy": 0.5903095938265324, "sharp": 0.18771444633603096}
+{"time": "23:31:06", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 847.9285217400575, "loss": 0.5848414171487093, "entropy": 0.5786398220807314, "sharp": 0.19603360444307327}
+{"time": "23:34:48", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 848.4179252220971, "loss": 0.5841092970222235, "entropy": 0.5754982940852642, "sharp": 0.21243495866656303}
+{"time": "23:36:20", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5431119203567505, "noul_T": 0.8891588717657484, "noul_auc": 0.7639676687464549, "noul_acc": 0.732, "noul_f1": 0.7981927710843374, "noul_nll": 0.5431119735166431, "noul_ece": 0.07156614959239961, "noul_brier": 0.18289236774580564, "noul_sharp": 0.21222960948944092, "entropy": 0.5653395652770996}
+{"time": "23:41:43", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9615732, "tok_per_s": 818.5192013869797, "rows_per_s": 1.4336402451946022, "val": {"n": 1914, "dropped_long": 0, "noul_ce": 0.5268602967262268, "noul_T": 0.8437305378688278, "choice_ce": 0.658643364906311, "choice_T": 1.031541289168218, "score_ce": 1.0547399520874023, "score_T": 0.974046797619904, "noul_auc": 0.7843765137231815, "noul_acc": 0.73512252042007, "noul_f1": 0.7998236331569665, "noul_nll": 0.5315972880667886, "noul_ece": 0.041881909448318745, "noul_brier": 0.17758800465233748, "noul_sharp": 0.214067280292511, "entropy": 0.5644049644470215}, "dropped_long": 0, "peak_gib": 18.235232830047607}