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

e16/S1-E19-b-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-b-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": [
+    "k_proj",
+    "in_proj_z",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "in_proj_qkv",
+    "out_proj",
+    "v_proj",
+    "q_proj",
+    "up_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-b-n16k-soft-a100-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c8fed551e4f2e63403861cb754f76ecf1d40cb763b54fed21cd0e2c8b06da2
+size 160486456

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83bce2b8bc97aba6b27dd9b9c3015ef48e14cf694f39f63a6c95aa8d171d9131
+size 176641832

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

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0002579177962616086,
+  -0.0002581707085482776,
+  -0.0021016255486756563,
+  -0.0013357553398236632,
+  -0.0004985524574294686,
+  0.0018341124523431063,
+  0.0009700783411972225,
+  -0.0029343997593969107,
+  -0.0004880185006186366,
+  -0.0010859284084290266,
+  -0.00014348176773637533,
+  0.00027191173285245895,
+  -0.00021439860574901104,
+  -0.0037982449866831303,
+  -0.004426341038197279,
+  -0.005092464853078127,
+  -0.005929149687290192,
+  -0.004344133660197258,
+  -0.00494185509160161,
+  -0.0050203693099319935,
+  -0.00404833210632205,
+  -0.003432460129261017,
+  -0.00562246423214674,
+  -0.003496751422062516
+ ],
+ "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-b-n16k-soft-a100-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8801455790388653,
+  "choice": 1.024313861319471,
+  "score": 0.9905500075349026
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.8801455790388653,
+   "ce_before": 0.5760111808776855,
+   "ce_after": 0.574754536151886
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.024313861319471,
+   "ce_before": 0.6697370409965515,
+   "ce_after": 0.6696186065673828
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9905500075349026,
+   "ce_before": 1.0564172267913818,
+   "ce_after": 1.0563875436782837
+  }
+ },
+ "source": "models/e16/S1-E19-b-n16k-soft-a100-syn/ckpt-16000"
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807ecddfac77a1b91155f252dfcb53a56bad382479d6429edb027c31d7eb9ccf
+size 393464

e16/S1-E19-b-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-b-n16k-soft-a100-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e19/E19-b-n16k-soft-a100",
+  "data_manifest": {
+   "arm": "E19-b-n16k-soft-a100",
+   "name": null,
+   "train_sha256": "111f1e2dbda38e8d48e34d89e7a49154c5c56f16bbfb62900ce172d3c10feb79",
+   "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": 9808867,
+  "tok_per_s": 813.7670299440191,
+  "rows_per_s": 1.397252538228457,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5760111808776855,
+   "noul_T": 0.8801455790388653,
+   "choice_ce": 0.6697370409965515,
+   "choice_T": 1.024313861319471,
+   "score_ce": 1.0564172267913818,
+   "score_T": 0.9905500075349026,
+   "noul_auc": 0.71648,
+   "noul_acc": 0.675,
+   "noul_f1": 0.7732030704815074,
+   "noul_nll": 0.5921840814873576,
+   "noul_ece": 0.046334362179040904,
+   "noul_brier": 0.20323176857051856,
+   "noul_sharp": 0.17630819976329803,
+   "entropy": 0.6064019799232483
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.236003875732422
+ }
+}

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

@@ -0,0 +1,57 @@
+{"time": "05:52:00", "event": "start", "data": "data/e19/E19-b-n16k-soft-a100", "data_manifest": {"arm": "E19-b-n16k-soft-a100", "name": null, "train_sha256": "111f1e2dbda38e8d48e34d89e7a49154c5c56f16bbfb62900ce172d3c10feb79", "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": 73.84693765640259}
+{"time": "05:55:49", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 846.8158083862144, "loss": 0.6402392126619816, "entropy": 0.6605346314609051, "sharp": 0.10643644351512194}
+{"time": "05:59:24", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 851.8695903782548, "loss": 0.6195361502468586, "entropy": 0.6700868457555771, "sharp": 0.1019674725830555}
+{"time": "06:03:19", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 855.6487384201372, "loss": 0.7155072279274464, "entropy": 0.5734440609812737, "sharp": 0.21059872396290302}
+{"time": "06:07:03", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 857.6442524544087, "loss": 0.7024985626339912, "entropy": 0.6795589700341225, "sharp": 0.07253504358232021}
+{"time": "06:10:49", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 858.5909959444363, "loss": 0.6486100219190121, "entropy": 0.6606452092528343, "sharp": 0.10773652233183384}
+{"time": "06:14:37", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 859.7293754455274, "loss": 0.6459148824214935, "entropy": 0.6552908420562744, "sharp": 0.12145766522735357}
+{"time": "06:18:27", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 859.6293112705712, "loss": 0.6210787892341614, "entropy": 0.6573178544640541, "sharp": 0.12082873657345772}
+{"time": "06:22:17", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 858.9931125746957, "loss": 0.6897826977074146, "entropy": 0.5575981354340911, "sharp": 0.2357395924627781}
+{"time": "06:26:03", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 859.0282519189082, "loss": 0.7004788443446159, "entropy": 0.6610299684107304, "sharp": 0.08942572586238384}
+{"time": "06:29:51", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 857.7309466788206, "loss": 0.6272289901971817, "entropy": 0.6176279187202454, "sharp": 0.16429126542061567}
+{"time": "06:31:20", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.5965855121612549, "noul_T": 0.9028042856465854, "noul_auc": 0.7304349293682808, "noul_acc": 0.666, "noul_f1": 0.7677329624478443, "noul_nll": 0.5978272156119346, "noul_ece": 0.09964489078521728, "noul_brier": 0.20505625327380475, "noul_sharp": 0.1619776338338852, "entropy": 0.6106281280517578}
+{"time": "06:35:13", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 828.818246092743, "loss": 0.6679484201595187, "entropy": 0.6545313037931919, "sharp": 0.11901770997792482}
+{"time": "06:38:54", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 830.6050211130852, "loss": 0.6179201863706112, "entropy": 0.6384730897843838, "sharp": 0.14409287832677364}
+{"time": "06:42:45", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 832.7663344459651, "loss": 0.6551833525300026, "entropy": 0.6327242627739906, "sharp": 0.1352393887937069}
+{"time": "06:46:39", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 834.4623485436247, "loss": 0.6752905920147896, "entropy": 0.6653869822621346, "sharp": 0.09132195543497801}
+{"time": "06:50:22", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 836.0791310114117, "loss": 0.6899525970220566, "entropy": 0.6711618788540363, "sharp": 0.08903115522116423}
+{"time": "06:54:14", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 837.5957043723064, "loss": 0.6767288781702518, "entropy": 0.6578035578131676, "sharp": 0.11272556334733963}
+{"time": "06:58:08", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 839.0340666935314, "loss": 0.6552388519048691, "entropy": 0.6595615781843662, "sharp": 0.10036542359739542}
+{"time": "07:01:59", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 839.975751767283, "loss": 0.6807433739304543, "entropy": 0.6394936293363571, "sharp": 0.13936826586723328}
+{"time": "07:05:43", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 840.6470653474975, "loss": 0.6794617064297199, "entropy": 0.667332973331213, "sharp": 0.08234441466629505}
+{"time": "07:09:33", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 841.6913483254505, "loss": 0.6117212623357773, "entropy": 0.6599679812788963, "sharp": 0.10567112267017365}
+{"time": "07:11:01", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.6015491485595703, "noul_T": 0.6959613244142409, "noul_auc": 0.7338441545290375, "noul_acc": 0.72, "noul_f1": 0.779874213836478, "noul_nll": 0.5955438327491284, "noul_ece": 0.10398886620998384, "noul_brier": 0.20348939456649912, "noul_sharp": 0.13839919865131378, "entropy": 0.6394829750061035}
+{"time": "07:14:49", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 827.3839305137034, "loss": 0.6420673131942749, "entropy": 0.6250713616609573, "sharp": 0.14936809800565243}
+{"time": "07:18:34", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 828.8372321073825, "loss": 0.7608661204576492, "entropy": 0.6542322263121605, "sharp": 0.11284756194800138}
+{"time": "07:22:22", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 830.1043743850146, "loss": 0.6024762317538261, "entropy": 0.643939346075058, "sharp": 0.1338538909330964}
+{"time": "07:26:15", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 831.211782576997, "loss": 0.6374752074480057, "entropy": 0.6372069641947746, "sharp": 0.13771062064915895}
+{"time": "07:30:03", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 832.1100607007035, "loss": 0.7218226660043001, "entropy": 0.6469209790229797, "sharp": 0.13555155973881483}
+{"time": "07:33:51", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 832.7252934260606, "loss": 0.65513114631176, "entropy": 0.6631283313035965, "sharp": 0.09869608748704195}
+{"time": "07:37:50", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 833.9156380125632, "loss": 0.6169817484915257, "entropy": 0.6121213994920254, "sharp": 0.17089117784053087}
+{"time": "07:41:40", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 834.6671555191367, "loss": 0.6841028332710266, "entropy": 0.6570164486765862, "sharp": 0.11430296208709478}
+{"time": "07:45:34", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 835.5643016936458, "loss": 0.7005562335252762, "entropy": 0.6730254255235195, "sharp": 0.07916701957583427}
+{"time": "07:49:26", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 836.4515840731718, "loss": 0.7229308821260929, "entropy": 0.6399287506937981, "sharp": 0.14076725207269192}
+{"time": "07:50:53", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.61360764503479, "noul_T": 0.9613801505623479, "noul_auc": 0.7206713810737372, "noul_acc": 0.638, "noul_f1": 0.767052767052767, "noul_nll": 0.6162726038992405, "noul_ece": 0.10785485196113585, "noul_brier": 0.21371966799314004, "noul_sharp": 0.1679866760969162, "entropy": 0.6188316941261292}
+{"time": "07:54:39", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 827.0658686720712, "loss": 0.6147586591541767, "entropy": 0.6664409562945366, "sharp": 0.09513027314096689}
+{"time": "07:58:26", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 827.9339898613774, "loss": 0.6901081502437592, "entropy": 0.6721167713403702, "sharp": 0.07680879440158606}
+{"time": "08:02:21", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 828.9472001195583, "loss": 0.6918988022953272, "entropy": 0.6383587904274464, "sharp": 0.13619431667029858}
+{"time": "08:06:03", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 829.6356048597751, "loss": 0.6332782916724682, "entropy": 0.6359823606908321, "sharp": 0.13072601985186338}
+{"time": "08:09:52", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 830.4729162775593, "loss": 0.6598100177943707, "entropy": 0.6548570543527603, "sharp": 0.11163273546844721}
+{"time": "08:13:39", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 831.0955132407831, "loss": 0.5609878934919834, "entropy": 0.6276392787694931, "sharp": 0.1548546189442277}
+{"time": "08:17:34", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 831.8064286017382, "loss": 0.6838781535625458, "entropy": 0.6204559057950974, "sharp": 0.1649091113358736}
+{"time": "08:21:22", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 832.3981321429852, "loss": 0.6315076760947704, "entropy": 0.6403292044997215, "sharp": 0.14232157729566097}
+{"time": "08:25:14", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 833.3683118708038, "loss": 0.6127064600586891, "entropy": 0.6367810294032097, "sharp": 0.13017089944332838}
+{"time": "08:28:54", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 833.8454182625405, "loss": 0.7233182564377785, "entropy": 0.6312087997794151, "sharp": 0.14318356662988663}
+{"time": "08:30:22", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5927242636680603, "noul_T": 0.7926059046757609, "noul_auc": 0.728848458253869, "noul_acc": 0.698, "noul_f1": 0.7776141384388807, "noul_nll": 0.5914371257126332, "noul_ece": 0.07101775574684144, "noul_brier": 0.20206063167286648, "noul_sharp": 0.15717755258083344, "entropy": 0.6221684813499451}
+{"time": "08:34:11", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 826.7067268826675, "loss": 0.6233598999679089, "entropy": 0.6647042781114578, "sharp": 0.09529155679047108}
+{"time": "08:37:55", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 827.5091515931377, "loss": 0.6424980722367764, "entropy": 0.6533437594771385, "sharp": 0.1129528060555458}
+{"time": "08:41:47", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 828.3710120846777, "loss": 0.6838945038616657, "entropy": 0.6305518858134747, "sharp": 0.1464870972558856}
+{"time": "08:45:33", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 829.0906658432463, "loss": 0.6842753728851676, "entropy": 0.6385384295135736, "sharp": 0.14194047544151545}
+{"time": "08:49:23", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 829.8839964492641, "loss": 0.5998460054397583, "entropy": 0.6567012034356594, "sharp": 0.11090394295752048}
+{"time": "08:53:13", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 830.4101757952133, "loss": 0.6229939125478268, "entropy": 0.634590707719326, "sharp": 0.1449802927672863}
+{"time": "08:57:08", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 831.0836679449255, "loss": 0.7122192624956369, "entropy": 0.6469888035207987, "sharp": 0.12915577739477158}
+{"time": "09:00:54", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 831.6760549962252, "loss": 0.6605168282985687, "entropy": 0.6483555063605309, "sharp": 0.1220132764428854}
+{"time": "09:04:34", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 832.169534749598, "loss": 0.5307298824191093, "entropy": 0.639168418943882, "sharp": 0.14014509785920382}
+{"time": "09:08:18", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 832.7664555613186, "loss": 0.6457764953374863, "entropy": 0.6301785856485367, "sharp": 0.14514619763940573}
+{"time": "09:09:46", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5900002717971802, "noul_T": 0.8571443805245929, "noul_auc": 0.7299961182089754, "noul_acc": 0.69, "noul_f1": 0.7756874095513748, "noul_nll": 0.5893199949115515, "noul_ece": 0.07461880910396576, "noul_brier": 0.20149521647068047, "noul_sharp": 0.16975414752960205, "entropy": 0.6116092801094055}
+{"time": "09:12:55", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 9808867, "tok_per_s": 813.7670299440191, "rows_per_s": 1.397252538228457, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5760111808776855, "noul_T": 0.8801455790388653, "choice_ce": 0.6697370409965515, "choice_T": 1.024313861319471, "score_ce": 1.0564172267913818, "score_T": 0.9905500075349026, "noul_auc": 0.71648, "noul_acc": 0.675, "noul_f1": 0.7732030704815074, "noul_nll": 0.5921840814873576, "noul_ece": 0.046334362179040904, "noul_brier": 0.20323176857051856, "noul_sharp": 0.17630819976329803, "entropy": 0.6064019799232483}, "dropped_long": 0, "peak_gib": 18.236003875732422}