backup e16/S1-E19-a1-n16k-1model-syn (Pod B)

e16/S1-E19-a1-n16k-1model-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-1model-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": [
+    "in_proj_qkv",
+    "o_proj",
+    "up_proj",
+    "out_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "in_proj_z",
+    "gate_proj",
+    "down_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-1model-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de75889abe48985146ef3e0ae9be117ab0be0c69fe0a5e85f40d4ed788876c6f
+size 160486456

e16/S1-E19-a1-n16k-1model-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-1model-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb6a2187735efba24d3660926cb1a6c47c0ed89031c87045d912b816b2078d1
+size 176641832

e16/S1-E19-a1-n16k-1model-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0006126924999989569,
+  -0.0006129516405053437,
+  -0.0019876924343407154,
+  -0.0018632090650498867,
+  -0.0008053728961385787,
+  0.0017003875691443682,
+  0.0016342191956937313,
+  -0.002159061608836055,
+  -0.0002361526567256078,
+  -0.000614852411672473,
+  -0.00015066193009261042,
+  0.000535801809746772,
+  -0.001322918920777738,
+  -0.003769541159272194,
+  -0.003979524131864309,
+  -0.005131696350872517,
+  -0.005934145767241716,
+  -0.004388251341879368,
+  -0.004952841438353062,
+  -0.00507725402712822,
+  -0.003984744660556316,
+  -0.0034809554927051067,
+  -0.005730655509978533,
+  -0.003518479410558939
+ ],
+ "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-1model-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.8033051768504509,
+  "choice": 1.0230483358529892,
+  "score": 0.9461958060506324
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.8033051768504509,
+   "ce_before": 0.5978009104728699,
+   "ce_after": 0.5949450135231018
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0230483358529892,
+   "ce_before": 0.669213593006134,
+   "ce_after": 0.6691054105758667
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9461958060506324,
+   "ce_before": 1.0589604377746582,
+   "ce_after": 1.0580642223358154
+  }
+ },
+ "source": "models/e16/S1-E19-a1-n16k-1model-syn/ckpt-16000"
+}

e16/S1-E19-a1-n16k-1model-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9305e4abb04d25e7b3d6e3350bcfe3ac301bd519b8c1e108a61d057a5f3854cf
+size 393464

e16/S1-E19-a1-n16k-1model-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-1model-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e19/E19-a1-n16k-1model",
+  "data_manifest": {
+   "arm": "E19-a1-n16k-1model",
+   "name": null,
+   "train_sha256": "4cd4f1a01cbfdfe64fc0f59057f64a22665fadd7cfc136b3b553c380d174ca69",
+   "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": 8938070,
+  "tok_per_s": 798.2762875175988,
+  "rows_per_s": 1.5041915342620658,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5978009104728699,
+   "noul_T": 0.8033051768504509,
+   "choice_ce": 0.669213593006134,
+   "choice_T": 1.0230483358529892,
+   "score_ce": 1.0589604377746582,
+   "score_T": 0.9461958060506324,
+   "noul_auc": 0.7233749333333332,
+   "noul_acc": 0.692,
+   "noul_f1": 0.7532051282051282,
+   "noul_nll": 0.6047030046805739,
+   "noul_ece": 0.09162459437549116,
+   "noul_brier": 0.20781315662784886,
+   "noul_sharp": 0.1439414918422699,
+   "entropy": 0.6341533660888672
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.235705852508545
+ }
+}

e16/S1-E19-a1-n16k-1model-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "17:17:52", "event": "start", "data": "data/e19/E19-a1-n16k-1model", "data_manifest": {"arm": "E19-a1-n16k-1model", "name": null, "train_sha256": "4cd4f1a01cbfdfe64fc0f59057f64a22665fadd7cfc136b3b553c380d174ca69", "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": 70.06712293624878}
+{"time": "17:21:31", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 839.6337266467893, "loss": 0.6028878837823868, "entropy": 0.5748029612004757, "sharp": 0.2238750085234642}
+{"time": "17:25:02", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 839.877827267736, "loss": 0.631417591124773, "entropy": 0.6380284875631332, "sharp": 0.12436839938163757}
+{"time": "17:28:39", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 843.6787524919492, "loss": 0.6037078816443682, "entropy": 0.649888014420867, "sharp": 0.12544558104127645}
+{"time": "17:32:12", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 845.9019496304339, "loss": 0.6427665166556835, "entropy": 0.6021258905529976, "sharp": 0.17269217316061258}
+{"time": "17:35:47", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 846.1652863190882, "loss": 0.5899967942386866, "entropy": 0.5791546925902367, "sharp": 0.2233207980170846}
+{"time": "17:39:18", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 846.0660867064756, "loss": 0.5672545433044434, "entropy": 0.6197148151695728, "sharp": 0.15946851670742035}
+{"time": "17:42:41", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 845.6885620578864, "loss": 0.60533138923347, "entropy": 0.6086876541376114, "sharp": 0.16502544656395912}
+{"time": "17:46:16", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 845.5379465022171, "loss": 0.5866634771227837, "entropy": 0.5174934882670641, "sharp": 0.25295088440179825}
+{"time": "17:49:49", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 845.7002370747468, "loss": 0.6193736791610718, "entropy": 0.6276438385248184, "sharp": 0.14808190986514091}
+{"time": "17:53:21", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 846.1146921912272, "loss": 0.6175604537129402, "entropy": 0.604101799428463, "sharp": 0.1722948905080557}
+{"time": "17:54:50", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.6311193108558655, "noul_T": 0.9886080287255308, "noul_auc": 0.7400043881115931, "noul_acc": 0.674, "noul_f1": 0.7073608617594255, "noul_nll": 0.6193934623748064, "noul_ece": 0.14126312035322192, "noul_brier": 0.2148361770829033, "noul_sharp": 0.1430092751979828, "entropy": 0.63232421875}
+{"time": "17:58:14", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 814.43849633068, "loss": 0.6083131991326809, "entropy": 0.5519475415349007, "sharp": 0.22081034071743488}
+{"time": "18:01:40", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 816.6879644349217, "loss": 0.6115221586078405, "entropy": 0.5990205109119415, "sharp": 0.17882157489657402}
+{"time": "18:05:16", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 819.1493338870487, "loss": 0.604631345719099, "entropy": 0.5450690910220146, "sharp": 0.2525194063782692}
+{"time": "18:08:48", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 820.2176405097179, "loss": 0.5668654991313815, "entropy": 0.6015749610960484, "sharp": 0.167982529848814}
+{"time": "18:12:17", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 821.9240720505874, "loss": 0.5303277745842934, "entropy": 0.5891002900898457, "sharp": 0.19366157427430153}
+{"time": "18:15:47", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 823.2661402019961, "loss": 0.5876465328037739, "entropy": 0.5253000892698765, "sharp": 0.24969258531928062}
+{"time": "18:19:19", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 824.6013238066215, "loss": 0.6136095225811005, "entropy": 0.5882911048829556, "sharp": 0.18006847612559795}
+{"time": "18:22:50", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 825.8923231239795, "loss": 0.5746983364224434, "entropy": 0.5520175471901894, "sharp": 0.2238515755161643}
+{"time": "18:26:26", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 827.2807683360542, "loss": 0.5608789697289467, "entropy": 0.5572056323289871, "sharp": 0.2193649671971798}
+{"time": "18:29:54", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 828.4353783781069, "loss": 0.5948090255260468, "entropy": 0.5709179267287254, "sharp": 0.21672828122973442}
+{"time": "18:31:23", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.6323525309562683, "noul_T": 0.9281373325916367, "noul_auc": 0.719751565374424, "noul_acc": 0.684, "noul_f1": 0.7312925170068028, "noul_nll": 0.6200612967014313, "noul_ece": 0.11751718384027483, "noul_brier": 0.214451815470481, "noul_sharp": 0.13596317172050476, "entropy": 0.6395372152328491}
+{"time": "18:34:56", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 813.4827091369525, "loss": 0.6095856484025717, "entropy": 0.608220387250185, "sharp": 0.1841447576880455}
+{"time": "18:38:28", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 814.6900342927709, "loss": 0.5954165756702423, "entropy": 0.5562173686921597, "sharp": 0.21633144840598106}
+{"time": "18:42:01", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 816.1667822061145, "loss": 0.6591349262744188, "entropy": 0.6431542318314314, "sharp": 0.13259060867130756}
+{"time": "18:45:36", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 817.6193045640739, "loss": 0.5495631508529186, "entropy": 0.5664544925093651, "sharp": 0.22341080754995346}
+{"time": "18:49:01", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 818.5156699599065, "loss": 0.5989267379045486, "entropy": 0.5980968251824379, "sharp": 0.18952203914523125}
+{"time": "18:52:30", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 819.6547314290439, "loss": 0.5153832100331783, "entropy": 0.561985220760107, "sharp": 0.22410967480391264}
+{"time": "18:56:02", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 820.4665611784937, "loss": 0.5770583311095834, "entropy": 0.6033405475318432, "sharp": 0.1860696403309703}
+{"time": "18:59:34", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 821.6633210830033, "loss": 0.6055584661662579, "entropy": 0.6168283484876156, "sharp": 0.16703057289123535}
+{"time": "19:03:07", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 822.30545772603, "loss": 0.6248880177736282, "entropy": 0.5485864281654358, "sharp": 0.21960294991731644}
+{"time": "19:06:38", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 823.4075853455636, "loss": 0.5827378965914249, "entropy": 0.597941804677248, "sharp": 0.17910069599747658}
+{"time": "19:08:06", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.6004499793052673, "noul_T": 0.8887220328196089, "noul_auc": 0.7260468177752274, "noul_acc": 0.718, "noul_f1": 0.7860394537177542, "noul_nll": 0.5930575210005045, "noul_ece": 0.07566636550426484, "noul_brier": 0.20227430379432595, "noul_sharp": 0.16175177693367004, "entropy": 0.6158544421195984}
+{"time": "19:11:33", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 813.4861762092668, "loss": 0.4690483771264553, "entropy": 0.5187891945242882, "sharp": 0.26497775316238403}
+{"time": "19:15:01", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 814.4721822455072, "loss": 0.6236191019415855, "entropy": 0.5717625468969345, "sharp": 0.21737133711576462}
+{"time": "19:18:38", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 815.4306773564861, "loss": 0.5606990940868855, "entropy": 0.5735452212393284, "sharp": 0.2159394919872284}
+{"time": "19:22:07", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 816.2932029271968, "loss": 0.6365031935274601, "entropy": 0.5522071495652199, "sharp": 0.21570261009037495}
+{"time": "19:25:43", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 817.3209138035396, "loss": 0.5289990641176701, "entropy": 0.5738698840141296, "sharp": 0.21373183652758598}
+{"time": "19:29:16", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 817.9971031281199, "loss": 0.6466408260166645, "entropy": 0.5074103157967329, "sharp": 0.25381651148200035}
+{"time": "19:32:45", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 818.6008338194828, "loss": 0.5703293085098267, "entropy": 0.5637051090598106, "sharp": 0.2223550956696272}
+{"time": "19:36:11", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 819.2430520675437, "loss": 0.6650397665798664, "entropy": 0.6104918085038662, "sharp": 0.17748045176267624}
+{"time": "19:39:43", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 820.0146904569842, "loss": 0.5724247954785824, "entropy": 0.5481690987944603, "sharp": 0.22979271039366722}
+{"time": "19:43:08", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 820.6145310024801, "loss": 0.5432952083647251, "entropy": 0.562528520822525, "sharp": 0.22757082991302013}
+{"time": "19:44:37", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.6048181653022766, "noul_T": 0.8889190225865092, "noul_auc": 0.7321732966532211, "noul_acc": 0.706, "noul_f1": 0.7692307692307693, "noul_nll": 0.5911038439869881, "noul_ece": 0.07063712376356127, "noul_brier": 0.20128470236584975, "noul_sharp": 0.16358938813209534, "entropy": 0.6199588775634766}
+{"time": "19:48:05", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 813.0292146455946, "loss": 0.5149875953793526, "entropy": 0.5497682839632034, "sharp": 0.23368296958506107}
+{"time": "19:51:44", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 813.8017014435187, "loss": 0.5955751799046993, "entropy": 0.5487835295498371, "sharp": 0.23354344256222248}
+{"time": "19:55:16", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 814.4981714264176, "loss": 0.5566186830401421, "entropy": 0.5653961300849915, "sharp": 0.21272791363298893}
+{"time": "19:58:47", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 815.1868591662749, "loss": 0.576153464615345, "entropy": 0.5907695889472961, "sharp": 0.2015283089131117}
+{"time": "20:02:14", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 815.7464083783844, "loss": 0.6053178980946541, "entropy": 0.5909912139177322, "sharp": 0.18939592689275742}
+{"time": "20:05:46", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 816.4323653118788, "loss": 0.5547490883618593, "entropy": 0.5825433395802975, "sharp": 0.19879533536732197}
+{"time": "20:09:14", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 816.9338473508107, "loss": 0.5584647469222546, "entropy": 0.5798559971153736, "sharp": 0.2005255687981844}
+{"time": "20:12:46", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 817.6082208774642, "loss": 0.556626308709383, "entropy": 0.5550225600600243, "sharp": 0.2206823118031025}
+{"time": "20:16:20", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 818.2148917928698, "loss": 0.5056653320789337, "entropy": 0.5261599645018578, "sharp": 0.2525162510573864}
+{"time": "20:19:51", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 818.5509890579535, "loss": 0.5313876271247864, "entropy": 0.5656377151608467, "sharp": 0.21903561055660248}
+{"time": "20:21:20", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.6171238422393799, "noul_T": 0.8669109599344214, "noul_auc": 0.7384854264063052, "noul_acc": 0.716, "noul_f1": 0.7649006622516556, "noul_nll": 0.6038276374936103, "noul_ece": 0.11944396501779558, "noul_brier": 0.2069032369549953, "noul_sharp": 0.14569725096225739, "entropy": 0.6326008439064026}
+{"time": "20:24:31", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 8938070, "tok_per_s": 798.2762875175988, "rows_per_s": 1.5041915342620658, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5978009104728699, "noul_T": 0.8033051768504509, "choice_ce": 0.669213593006134, "choice_T": 1.0230483358529892, "score_ce": 1.0589604377746582, "score_T": 0.9461958060506324, "noul_auc": 0.7233749333333332, "noul_acc": 0.692, "noul_f1": 0.7532051282051282, "noul_nll": 0.6047030046805739, "noul_ece": 0.09162459437549116, "noul_brier": 0.20781315662784886, "noul_sharp": 0.1439414918422699, "entropy": 0.6341533660888672}, "dropped_long": 0, "peak_gib": 18.235705852508545}