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

e16/S1-ABCLODO16-junyi/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-junyi/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": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "in_proj_qkv",
+    "o_proj",
+    "gate_proj",
+    "out_proj",
+    "v_proj",
+    "q_proj",
+    "in_proj_z"
+  ],
+  "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-junyi/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2bf3f4c538fbc40fababc67087f752c21f203da200cd9b195f92f9d2c31e8b
+size 160486456

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48bbdc9ed64a38be26fabcdca495748cce5f16a92fb999031beacc964f9f0b9
+size 176641832

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

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0004060330684296787,
+  -0.00040628958959132433,
+  -0.00258005247451365,
+  -0.0016756807453930378,
+  -0.0006792059866711497,
+  0.0019725237507373095,
+  0.0013469189871102571,
+  -0.0022389190271496773,
+  -0.00018652758444659412,
+  -0.00023381681239698082,
+  0.00024248665431514382,
+  0.0008470978937111795,
+  0.0003678629582282156,
+  -0.0045778099447488785,
+  -0.005782118998467922,
+  -0.00566343916580081,
+  -0.006171931512653828,
+  -0.005448245443403721,
+  -0.005534274037927389,
+  -0.006028322037309408,
+  -0.004884829744696617,
+  -0.004546264186501503,
+  -0.00651802122592926,
+  -0.004450250416994095
+ ],
+ "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-junyi/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8842068581106572,
+  "choice": 1.061410127867425,
+  "score": 0.9985754156671756
+ },
+ "fit": {
+  "noul": {
+   "n": 1802,
+   "T": 0.8842068581106572,
+   "ce_before": 0.525688111782074,
+   "ce_after": 0.5240776538848877
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.061410127867425,
+   "ce_before": 0.6684281826019287,
+   "ce_after": 0.6676441431045532
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9985754156671756,
+   "ce_before": 1.0547449588775635,
+   "ce_after": 1.0547438859939575
+  }
+ },
+ "source": "models/e16/S1-ABCLODO16-junyi/ckpt-16000"
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd39601d20554916ab3cd8d4a89fc1eeaa0723a9f8837977767be3a2e16c5ca
+size 393464

e16/S1-ABCLODO16-junyi/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-junyi/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e15/F1-pool-jev-LODO-junyi",
+  "data_manifest": {
+   "arm": "F1-pool-jev-LODO-junyi",
+   "name": "F1-pool-jev-LODO-junyi",
+   "train_sha256": "197a9ae708c4546f360db7bf9e845e2fddbf1c22aa07652ca9009f28d11c828d",
+   "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": 10790962,
+  "tok_per_s": 810.3856332115948,
+  "rows_per_s": 1.2648098314081313,
+  "val": {
+   "n": 1915,
+   "dropped_long": 0,
+   "noul_ce": 0.525688111782074,
+   "noul_T": 0.8842068581106572,
+   "choice_ce": 0.6684281826019287,
+   "choice_T": 1.061410127867425,
+   "score_ce": 1.0547449588775635,
+   "score_T": 0.9985754156671756,
+   "noul_auc": 0.7822765412550756,
+   "noul_acc": 0.7381924198250729,
+   "noul_f1": 0.8050369083803735,
+   "noul_nll": 0.5302975064442214,
+   "noul_ece": 0.04533599079002793,
+   "noul_brier": 0.1769066334590793,
+   "noul_sharp": 0.22304324805736542,
+   "entropy": 0.5552073121070862
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.236003398895264
+ }
+}

e16/S1-ABCLODO16-junyi/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "02:23:51", "event": "start", "data": "data/e15/F1-pool-jev-LODO-junyi", "data_manifest": {"arm": "F1-pool-jev-LODO-junyi", "name": "F1-pool-jev-LODO-junyi", "train_sha256": "197a9ae708c4546f360db7bf9e845e2fddbf1c22aa07652ca9009f28d11c828d", "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": 79.50239443778992}
+{"time": "02:27:59", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 861.8945686470406, "loss": 0.5822928175330162, "entropy": 0.5668162405490875, "sharp": 0.21648880653083324}
+{"time": "02:32:12", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 864.1169644063198, "loss": 0.6113677490502596, "entropy": 0.5817635841667652, "sharp": 0.1980749536305666}
+{"time": "02:36:25", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 865.2610980516926, "loss": 0.546056617051363, "entropy": 0.49664628878235817, "sharp": 0.27341744862496853}
+{"time": "02:40:34", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 865.6448583656367, "loss": 0.5860969433560967, "entropy": 0.6454560235142708, "sharp": 0.13622043281793594}
+{"time": "02:44:45", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 866.712315613865, "loss": 0.6407751813530922, "entropy": 0.5314248874783516, "sharp": 0.2486370261758566}
+{"time": "02:48:53", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 866.329986608656, "loss": 0.5813371334224939, "entropy": 0.5541219525039196, "sharp": 0.21569320745766163}
+{"time": "02:53:04", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 867.1717739728908, "loss": 0.5668085692450404, "entropy": 0.5705241598188877, "sharp": 0.19117500446736813}
+{"time": "02:57:14", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 866.1835896495695, "loss": 0.5840453682467341, "entropy": 0.5577344503253698, "sharp": 0.22707732394337654}
+{"time": "03:01:24", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 866.9249081639184, "loss": 0.6424346081912518, "entropy": 0.5931721851229668, "sharp": 0.19342203065752983}
+{"time": "03:05:27", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 866.9027136032821, "loss": 0.5604449585080147, "entropy": 0.542963445186615, "sharp": 0.2308657243847847}
+{"time": "03:07:14", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5468561053276062, "noul_T": 0.9554732719322565, "noul_auc": 0.7613974758933636, "noul_acc": 0.724, "noul_f1": 0.7952522255192879, "noul_nll": 0.5468561245501041, "noul_ece": 0.054456783533096326, "noul_brier": 0.18395632649809218, "noul_sharp": 0.2241920828819275, "entropy": 0.5563964247703552}
+{"time": "03:11:13", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 834.6521411779086, "loss": 0.520088973455131, "entropy": 0.5855270512402058, "sharp": 0.2014442514628172}
+{"time": "03:15:23", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 837.1402330988045, "loss": 0.5927688190713525, "entropy": 0.5455445125699043, "sharp": 0.23785529285669327}
+{"time": "03:19:33", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 839.835311946561, "loss": 0.6025742162019014, "entropy": 0.5676053166389465, "sharp": 0.2166642788797617}
+{"time": "03:23:45", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 841.9382902321998, "loss": 0.5269198147580028, "entropy": 0.5301808137446642, "sharp": 0.24988807551562786}
+{"time": "03:27:50", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 843.7575026945773, "loss": 0.6579915611073375, "entropy": 0.5676995366811752, "sharp": 0.20884225703775883}
+{"time": "03:31:46", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 845.6409071213146, "loss": 0.6028530416078866, "entropy": 0.6006355881690979, "sharp": 0.17812272533774376}
+{"time": "03:36:02", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 847.0079929065042, "loss": 0.6091933101415634, "entropy": 0.5488564185798168, "sharp": 0.23336135782301426}
+{"time": "03:40:14", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 848.5369607537957, "loss": 0.6066305786371231, "entropy": 0.6014931872487068, "sharp": 0.1790844053030014}
+{"time": "03:44:15", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 849.7493541917063, "loss": 0.5284620597958565, "entropy": 0.5154511732980609, "sharp": 0.2547400761395693}
+{"time": "03:48:23", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 850.9934233983348, "loss": 0.6364323236048222, "entropy": 0.5619666054844856, "sharp": 0.22364382818341255}
+{"time": "03:50:09", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5687510371208191, "noul_T": 0.9648769759200664, "noul_auc": 0.7526588201928531, "noul_acc": 0.7, "noul_f1": 0.7685185185185185, "noul_nll": 0.568751022130251, "noul_ece": 0.09915343564748763, "noul_brier": 0.1928656403169509, "noul_sharp": 0.20651812851428986, "entropy": 0.5754334926605225}
+{"time": "03:54:12", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 835.3277332377992, "loss": 0.5938563477247953, "entropy": 0.5108351968228817, "sharp": 0.2534559592604637}
+{"time": "03:58:12", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 836.7732821267799, "loss": 0.5226390864700079, "entropy": 0.5677602365612984, "sharp": 0.21863808948546648}
+{"time": "04:02:16", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 838.2536934250711, "loss": 0.5353064779192209, "entropy": 0.5346648432314396, "sharp": 0.23874379135668278}
+{"time": "04:06:21", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 839.5969220129089, "loss": 0.5560992732644081, "entropy": 0.5339225567877293, "sharp": 0.2389255203306675}
+{"time": "04:10:31", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 840.8310584973999, "loss": 0.604085536673665, "entropy": 0.5917456708848476, "sharp": 0.17668969184160233}
+{"time": "04:14:39", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 841.7338427800462, "loss": 0.5314682964235544, "entropy": 0.5256273522973061, "sharp": 0.26422782987356186}
+{"time": "04:18:53", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 842.7544382107161, "loss": 0.5636822506785393, "entropy": 0.5851416438817978, "sharp": 0.2044214140623808}
+{"time": "04:23:02", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 843.453169903403, "loss": 0.5907248333096504, "entropy": 0.5872385427355766, "sharp": 0.1950840037316084}
+{"time": "04:27:10", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 844.3876325034504, "loss": 0.6026761904358864, "entropy": 0.5689888671040535, "sharp": 0.2161649949848652}
+{"time": "04:31:21", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 845.3338205059387, "loss": 0.6366631342098117, "entropy": 0.5311114266514778, "sharp": 0.23460775054991245}
+{"time": "04:33:07", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5480237603187561, "noul_T": 1.0329937292191684, "noul_auc": 0.7553353658536583, "noul_acc": 0.728, "noul_f1": 0.8, "noul_nll": 0.5480237356498837, "noul_ece": 0.057239197373390185, "noul_brier": 0.1849460647297483, "noul_sharp": 0.23241259157657623, "entropy": 0.5411527156829834}
+{"time": "04:37:07", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 834.9014047948281, "loss": 0.5673371069133282, "entropy": 0.5862594768404961, "sharp": 0.19777599070221186}
+{"time": "04:41:13", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 835.8013567166626, "loss": 0.5706391111016273, "entropy": 0.5376488761976361, "sharp": 0.23273520823568106}
+{"time": "04:45:29", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 837.0863893561082, "loss": 0.5750464089214802, "entropy": 0.5803776681423187, "sharp": 0.19455552008002996}
+{"time": "04:49:34", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 838.1116167135067, "loss": 0.6006006971001625, "entropy": 0.5727469399571419, "sharp": 0.2039149459451437}
+{"time": "04:53:46", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 839.010121649566, "loss": 0.5604831771925092, "entropy": 0.6054116301238537, "sharp": 0.17875684052705765}
+{"time": "04:57:53", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 839.8982247886945, "loss": 0.6535944044589996, "entropy": 0.582423928193748, "sharp": 0.19295069575309753}
+{"time": "05:02:06", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 840.5526463191751, "loss": 0.5708425901830196, "entropy": 0.5720285642892122, "sharp": 0.2118510939180851}
+{"time": "05:06:12", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 841.3549520016547, "loss": 0.6336799710988998, "entropy": 0.548972811549902, "sharp": 0.21409549564123154}
+{"time": "05:10:21", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 841.9972173173538, "loss": 0.6023753909394145, "entropy": 0.5769018419086933, "sharp": 0.2012409996241331}
+{"time": "05:14:30", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 842.5702100276899, "loss": 0.534514769911766, "entropy": 0.5551084000617266, "sharp": 0.22739925794303417}
+{"time": "05:16:16", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5575965046882629, "noul_T": 0.9506304570368671, "noul_auc": 0.7480679239931934, "noul_acc": 0.718, "noul_f1": 0.7866868381240545, "noul_nll": 0.5575965000391007, "noul_ece": 0.06978938460350038, "noul_brier": 0.18867784985747726, "noul_sharp": 0.21188919246196747, "entropy": 0.5673142671585083}
+{"time": "05:20:23", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 834.6407795020344, "loss": 0.5893609151244164, "entropy": 0.5535970367491245, "sharp": 0.21820158138871193}
+{"time": "05:24:33", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 835.4367959593764, "loss": 0.5951523296535015, "entropy": 0.5406439416110516, "sharp": 0.22715690173208714}
+{"time": "05:28:40", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 836.1987974757991, "loss": 0.6280372105538845, "entropy": 0.5777122229337692, "sharp": 0.2075652740895748}
+{"time": "05:32:50", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 836.8273115695388, "loss": 0.625586798414588, "entropy": 0.623547051101923, "sharp": 0.15258438512682915}
+{"time": "05:37:01", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 837.6141499990014, "loss": 0.6012628115713596, "entropy": 0.6069367248564959, "sharp": 0.17020337004214525}
+{"time": "05:41:13", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 838.1555117316773, "loss": 0.6108899861574173, "entropy": 0.5412356071174145, "sharp": 0.23334374465048313}
+{"time": "05:45:25", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 838.9005481888784, "loss": 0.6107395421713591, "entropy": 0.583651851862669, "sharp": 0.1866116039454937}
+{"time": "05:49:34", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 839.52076832523, "loss": 0.5951862558722496, "entropy": 0.5887126866728067, "sharp": 0.18740698508918285}
+{"time": "05:53:38", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 840.0840103124519, "loss": 0.5739605166018009, "entropy": 0.5562566202133894, "sharp": 0.22167174145579338}
+{"time": "05:57:49", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 840.5772785726444, "loss": 0.594438225030899, "entropy": 0.550371129065752, "sharp": 0.23362051788717508}
+{"time": "05:59:35", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5516188740730286, "noul_T": 0.9832049310755115, "noul_auc": 0.7525170164492342, "noul_acc": 0.73, "noul_f1": 0.7988077496274217, "noul_nll": 0.5516189115345478, "noul_ece": 0.06776857161521913, "noul_brier": 0.18608310948920354, "noul_sharp": 0.2228119820356369, "entropy": 0.5551533102989197}
+{"time": "06:05:49", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 10790962, "tok_per_s": 810.3856332115948, "rows_per_s": 1.2648098314081313, "val": {"n": 1915, "dropped_long": 0, "noul_ce": 0.525688111782074, "noul_T": 0.8842068581106572, "choice_ce": 0.6684281826019287, "choice_T": 1.061410127867425, "score_ce": 1.0547449588775635, "score_T": 0.9985754156671756, "noul_auc": 0.7822765412550756, "noul_acc": 0.7381924198250729, "noul_f1": 0.8050369083803735, "noul_nll": 0.5302975064442214, "noul_ece": 0.04533599079002793, "noul_brier": 0.1769066334590793, "noul_sharp": 0.22304324805736542, "entropy": 0.5552073121070862}, "dropped_long": 0, "peak_gib": 18.236003398895264}