backup e16/S1-MIX3-n16k-syn (Pod B)

e16/S1-MIX3-n16k-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-MIX3-n16k-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": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_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-MIX3-n16k-syn/ckpt-16000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ac886d705e1a762c8a6d8a3bc28228499565caeb4d7ab38b0b3079d38c07c3
+size 160486456

e16/S1-MIX3-n16k-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-MIX3-n16k-syn/ckpt-16000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22b519ae133c24aa698913b35c3829c97ee20ca8552b9d18a8e39a0a05d694c
+size 176641832

e16/S1-MIX3-n16k-syn/ckpt-16000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.0005176478298380971,
+  -0.000517908891197294,
+  -0.0019442160846665502,
+  -0.0011592286173254251,
+  -0.00048060499830171466,
+  0.0021370460744947195,
+  0.001692159683443606,
+  -0.0019730031490325928,
+  -0.0003994035942014307,
+  -0.0004024387744721025,
+  -8.739901386434212e-05,
+  0.00025096797617152333,
+  5.827288259752095e-05,
+  -0.003798941383138299,
+  -0.004448155406862497,
+  -0.005158994346857071,
+  -0.005972105544060469,
+  -0.004381911363452673,
+  -0.004965061787515879,
+  -0.005104643292725086,
+  -0.004181988537311554,
+  -0.003557919291779399,
+  -0.005658626556396484,
+  -0.00357454945333302
+ ],
+ "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-MIX3-n16k-syn/ckpt-16000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.9011236680302168,
+  "choice": 1.0387025462416157,
+  "score": 1.0368998603373318
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.9011236680302168,
+   "ce_before": 0.559345543384552,
+   "ce_after": 0.5584254264831543
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0387025462416157,
+   "ce_before": 0.6703149080276489,
+   "ce_after": 0.6699948906898499
+  },
+  "score": {
+   "n": 53,
+   "T": 1.0368998603373318,
+   "ce_before": 1.0618693828582764,
+   "ce_after": 1.0614577531814575
+  }
+ },
+ "source": "models/e16/S1-MIX3-n16k-syn/ckpt-16000"
+}

e16/S1-MIX3-n16k-syn/ckpt-16000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7605b7cee6b4aaf269d3f29e877a5545b5a0e71358173ec648c919619bf6bc
+size 393464

e16/S1-MIX3-n16k-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-MIX3-n16k-syn/ckpt-16000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e20/MIX3-n16k",
+  "data_manifest": {
+   "arm": "MIX3-n16k",
+   "name": null,
+   "train_sha256": "7c017c357f68f614b9b636ef6fe1670c25fcd274d3ba6e9240b5f36033e5bca4",
+   "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": 8970575,
+  "tok_per_s": 829.3081822086466,
+  "rows_per_s": 1.5570025777510128,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.559345543384552,
+   "noul_T": 0.9011236680302168,
+   "choice_ce": 0.6703149080276489,
+   "choice_T": 1.0387025462416157,
+   "score_ce": 1.0618693828582764,
+   "score_T": 1.0368998603373318,
+   "noul_auc": 0.7430528000000001,
+   "noul_acc": 0.692,
+   "noul_f1": 0.7659574468085106,
+   "noul_nll": 0.5717629001699388,
+   "noul_ece": 0.04781151111423971,
+   "noul_brier": 0.19512653441247677,
+   "noul_sharp": 0.1884661316871643,
+   "entropy": 0.5864760279655457
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.23796796798706
+ }
+}

e16/S1-MIX3-n16k-syn/train_log.jsonl

@@ -0,0 +1,57 @@
+{"time": "08:31:03", "event": "start", "data": "data/e20/MIX3-n16k", "data_manifest": {"arm": "MIX3-n16k", "name": null, "train_sha256": "7c017c357f68f614b9b636ef6fe1670c25fcd274d3ba6e9240b5f36033e5bca4", "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": 80.05717611312866}
+{"time": "08:34:21", "event": "step", "step": 10, "rows_seen": 320, "lr": 7.333333333333333e-05, "tok_per_s": 859.8122573865504, "loss": 0.6406753174960613, "entropy": 0.6540311425924301, "sharp": 0.10755779035389423}
+{"time": "08:37:47", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.997508952966197e-05, "tok_per_s": 870.9952654758265, "loss": 0.5821420885622501, "entropy": 0.609635716304183, "sharp": 0.173539062961936}
+{"time": "08:41:11", "event": "step", "step": 30, "rows_seen": 960, "lr": 9.977596250541417e-05, "tok_per_s": 874.9133189712695, "loss": 0.6083578430116177, "entropy": 0.5383074693381786, "sharp": 0.24151872284710407}
+{"time": "08:44:33", "event": "step", "step": 40, "rows_seen": 1280, "lr": 9.937854366485982e-05, "tok_per_s": 874.996966501961, "loss": 0.5971637554466724, "entropy": 0.61089151725173, "sharp": 0.17197405081242323}
+{"time": "08:47:57", "event": "step", "step": 50, "rows_seen": 1600, "lr": 9.8784499920729e-05, "tok_per_s": 875.9116402941104, "loss": 0.6253327187150717, "entropy": 0.6145798824727535, "sharp": 0.15257266350090504}
+{"time": "08:51:16", "event": "step", "step": 60, "rows_seen": 1920, "lr": 9.79963228989294e-05, "tok_per_s": 876.5225057860279, "loss": 0.5781108550727367, "entropy": 0.5506471507251263, "sharp": 0.21165885776281357}
+{"time": "08:54:46", "event": "step", "step": 70, "rows_seen": 2240, "lr": 9.701731848780134e-05, "tok_per_s": 876.9695230976055, "loss": 0.5770278796553612, "entropy": 0.6133275628089905, "sharp": 0.16517305932939053}
+{"time": "08:58:07", "event": "step", "step": 80, "rows_seen": 2560, "lr": 9.585159297207315e-05, "tok_per_s": 875.7949880820321, "loss": 0.6194326616823673, "entropy": 0.5955105647444725, "sharp": 0.18933441676199436}
+{"time": "09:01:29", "event": "step", "step": 90, "rows_seen": 2880, "lr": 9.450403580967612e-05, "tok_per_s": 876.2052683479045, "loss": 0.6082663275301456, "entropy": 0.5616595670580864, "sharp": 0.22988351061940193}
+{"time": "09:04:55", "event": "step", "step": 100, "rows_seen": 3200, "lr": 9.298029912365855e-05, "tok_per_s": 877.2196408163586, "loss": 0.5649638064205647, "entropy": 0.6115726940333843, "sharp": 0.16989373601973057}
+{"time": "09:06:18", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.588331401348114, "noul_T": 0.6257622524932621, "noul_auc": 0.7466540649102968, "noul_acc": 0.694, "noul_f1": 0.7590551181102362, "noul_nll": 0.5888108303546905, "noul_ece": 0.0875679190158844, "noul_brier": 0.20101720780905546, "noul_sharp": 0.1352291852235794, "entropy": 0.6371363997459412}
+{"time": "09:09:46", "event": "step", "step": 110, "rows_seen": 3520, "lr": 9.128677399521752e-05, "tok_per_s": 845.7968759949674, "loss": 0.5988587699830532, "entropy": 0.5474386438727379, "sharp": 0.23147332295775414}
+{"time": "09:13:10", "event": "step", "step": 120, "rows_seen": 3840, "lr": 8.943056365728335e-05, "tok_per_s": 847.9495747230636, "loss": 0.5721765831112862, "entropy": 0.6181512735784054, "sharp": 0.16656978614628315}
+{"time": "09:16:36", "event": "step", "step": 130, "rows_seen": 4160, "lr": 8.741945370109202e-05, "tok_per_s": 850.6312042968053, "loss": 0.5067169088870287, "entropy": 0.5233559533953667, "sharp": 0.25798998214304447}
+{"time": "09:20:00", "event": "step", "step": 140, "rows_seen": 4480, "lr": 8.526187942070997e-05, "tok_per_s": 852.4496244815874, "loss": 0.5764824561774731, "entropy": 0.5683881565928459, "sharp": 0.21952886134386063}
+{"time": "09:23:14", "event": "step", "step": 150, "rows_seen": 4800, "lr": 8.296689043247915e-05, "tok_per_s": 853.2048569961246, "loss": 0.5991155868396163, "entropy": 0.596195749938488, "sharp": 0.1861759964376688}
+{"time": "09:26:32", "event": "step", "step": 160, "rows_seen": 5120, "lr": 8.054411271778132e-05, "tok_per_s": 854.2902389801818, "loss": 0.6395573318004608, "entropy": 0.5717090517282486, "sharp": 0.212324857711792}
+{"time": "09:29:58", "event": "step", "step": 170, "rows_seen": 5440, "lr": 7.800370824832674e-05, "tok_per_s": 855.9043374772536, "loss": 0.5833171010017395, "entropy": 0.601571723818779, "sharp": 0.1712222844362259}
+{"time": "09:33:31", "event": "step", "step": 180, "rows_seen": 5760, "lr": 7.535633236331324e-05, "tok_per_s": 857.3235958430031, "loss": 0.61228858679533, "entropy": 0.5827791020274162, "sharp": 0.17535251379013062}
+{"time": "09:37:00", "event": "step", "step": 190, "rows_seen": 6080, "lr": 7.26130890772308e-05, "tok_per_s": 858.3563890735884, "loss": 0.6099617406725883, "entropy": 0.626419872045517, "sharp": 0.1434507556259632}
+{"time": "09:40:25", "event": "step", "step": 200, "rows_seen": 6400, "lr": 6.978548450576568e-05, "tok_per_s": 859.3423202021448, "loss": 0.6538371499627829, "entropy": 0.5926972404122353, "sharp": 0.1736740581691265}
+{"time": "09:41:49", "event": "val", "step": 200, "rows_seen": 6400, "n": 500, "dropped_long": 0, "noul_ce": 0.5767698884010315, "noul_T": 0.9087225495772077, "noul_auc": 0.7497088656731532, "noul_acc": 0.712, "noul_f1": 0.7757009345794392, "noul_nll": 0.5736097777113318, "noul_ece": 0.06813268291950228, "noul_brier": 0.19530011028815542, "noul_sharp": 0.18296563625335693, "entropy": 0.5918392539024353}
+{"time": "09:45:23", "event": "step", "step": 210, "rows_seen": 6720, "lr": 6.688537860515266e-05, "tok_per_s": 844.4079849708161, "loss": 0.6168953329324722, "entropy": 0.6078196726739407, "sharp": 0.16187159344553947}
+{"time": "09:48:47", "event": "step", "step": 220, "rows_seen": 7040, "lr": 6.392493542739706e-05, "tok_per_s": 845.8330421612634, "loss": 0.5256317965686321, "entropy": 0.5264021903276443, "sharp": 0.2504466399550438}
+{"time": "09:52:25", "event": "step", "step": 230, "rows_seen": 7360, "lr": 6.091657210001309e-05, "tok_per_s": 847.2246486764026, "loss": 0.58028769120574, "entropy": 0.6061246693134308, "sharp": 0.18016643077135086}
+{"time": "09:55:46", "event": "step", "step": 240, "rows_seen": 7680, "lr": 5.7872906744276015e-05, "tok_per_s": 848.4563593552596, "loss": 0.6325174570083618, "entropy": 0.5195887461304665, "sharp": 0.25497324764728546}
+{"time": "09:59:09", "event": "step", "step": 250, "rows_seen": 8000, "lr": 5.48067055504363e-05, "tok_per_s": 849.79941557861, "loss": 0.583037156611681, "entropy": 0.6078955829143524, "sharp": 0.1790879750624299}
+{"time": "10:02:33", "event": "step", "step": 260, "rows_seen": 8320, "lr": 5.173082923188119e-05, "tok_per_s": 850.5262278491291, "loss": 0.608392670750618, "entropy": 0.5925237238407135, "sharp": 0.1850985772907734}
+{"time": "10:05:56", "event": "step", "step": 270, "rows_seen": 8640, "lr": 4.865817908283331e-05, "tok_per_s": 851.7964855940652, "loss": 0.5923977643251419, "entropy": 0.6205177269876003, "sharp": 0.16291836462914944}
+{"time": "10:09:20", "event": "step", "step": 280, "rows_seen": 8960, "lr": 4.560164286583922e-05, "tok_per_s": 852.607968558414, "loss": 0.6653631255030632, "entropy": 0.5759397074580193, "sharp": 0.20488565787672997}
+{"time": "10:12:38", "event": "step", "step": 290, "rows_seen": 9280, "lr": 4.257404075601443e-05, "tok_per_s": 853.1254247799611, "loss": 0.6273254565894604, "entropy": 0.6329221725463867, "sharp": 0.14704899676144123}
+{"time": "10:15:58", "event": "step", "step": 300, "rows_seen": 9600, "lr": 3.958807156877371e-05, "tok_per_s": 853.5992957733832, "loss": 0.6128980405628681, "entropy": 0.5904124975204468, "sharp": 0.1889109406620264}
+{"time": "10:17:22", "event": "val", "step": 300, "rows_seen": 9600, "n": 500, "dropped_long": 0, "noul_ce": 0.5700536370277405, "noul_T": 0.9577004556788523, "noul_auc": 0.7513966009012506, "noul_acc": 0.708, "noul_f1": 0.7840236686390533, "noul_nll": 0.5703534269332886, "noul_ece": 0.06271416258811952, "noul_brier": 0.1942220202704003, "noul_sharp": 0.1939205378293991, "entropy": 0.5773654580116272}
+{"time": "10:20:48", "event": "step", "step": 310, "rows_seen": 9920, "lr": 3.665625949658603e-05, "tok_per_s": 843.5928992574823, "loss": 0.5912953158840537, "entropy": 0.526578520424664, "sharp": 0.22802334651350975}
+{"time": "10:24:15", "event": "step", "step": 320, "rows_seen": 10240, "lr": 3.379090157815887e-05, "tok_per_s": 844.5278204454851, "loss": 0.6044494621455669, "entropy": 0.5877703335136175, "sharp": 0.1910000704228878}
+{"time": "10:27:32", "event": "step", "step": 330, "rows_seen": 10560, "lr": 3.10040161203844e-05, "tok_per_s": 845.2809859606912, "loss": 0.6426706910133362, "entropy": 0.6101958397775888, "sharp": 0.16117125004529953}
+{"time": "10:31:04", "event": "step", "step": 340, "rows_seen": 10880, "lr": 2.8307292289383776e-05, "tok_per_s": 846.4318164188362, "loss": 0.5969919534400105, "entropy": 0.5708135608583689, "sharp": 0.19029546342790127}
+{"time": "10:34:32", "event": "step", "step": 350, "rows_seen": 11200, "lr": 2.571204108208194e-05, "tok_per_s": 847.731199310396, "loss": 0.5826997719705105, "entropy": 0.5629068613052368, "sharp": 0.2052222602069378}
+{"time": "10:37:57", "event": "step", "step": 360, "rows_seen": 11520, "lr": 2.322914788395595e-05, "tok_per_s": 848.6635529394615, "loss": 0.6316973026841879, "entropy": 0.578954441472888, "sharp": 0.20759695768356323}
+{"time": "10:41:17", "event": "step", "step": 370, "rows_seen": 11840, "lr": 2.0869026811945157e-05, "tok_per_s": 849.5279031353372, "loss": 0.6338486112654209, "entropy": 0.5958647057414055, "sharp": 0.1890407521277666}
+{"time": "10:44:46", "event": "step", "step": 380, "rows_seen": 12160, "lr": 1.8641577034025627e-05, "tok_per_s": 850.5241151396933, "loss": 0.5787635110318661, "entropy": 0.5701435953378677, "sharp": 0.2064032144844532}
+{"time": "10:48:13", "event": "step", "step": 390, "rows_seen": 12480, "lr": 1.6556141248659472e-05, "tok_per_s": 851.0403489633683, "loss": 0.5868439711630344, "entropy": 0.5793858133256435, "sharp": 0.19167248532176018}
+{"time": "10:51:32", "event": "step", "step": 400, "rows_seen": 12800, "lr": 1.4621466498270773e-05, "tok_per_s": 851.8356387517538, "loss": 0.5724565386772156, "entropy": 0.5595830082893372, "sharp": 0.209070585668087}
+{"time": "10:52:55", "event": "val", "step": 400, "rows_seen": 12800, "n": 500, "dropped_long": 0, "noul_ce": 0.5719676613807678, "noul_T": 0.8597087521762673, "noul_auc": 0.755734080437461, "noul_acc": 0.714, "noul_f1": 0.7782945736434108, "noul_nll": 0.5692778851464391, "noul_ece": 0.06344858980178833, "noul_brier": 0.19344334194989585, "noul_sharp": 0.17959153652191162, "entropy": 0.5950776934623718}
+{"time": "10:56:16", "event": "step", "step": 410, "rows_seen": 13120, "lr": 1.284566748110963e-05, "tok_per_s": 844.161377589308, "loss": 0.5621709935367107, "entropy": 0.5608640089631081, "sharp": 0.21343966759741306}
+{"time": "10:59:44", "event": "step", "step": 420, "rows_seen": 13440, "lr": 1.1236192515387821e-05, "tok_per_s": 844.835269626916, "loss": 0.5919195041060448, "entropy": 0.5926895067095757, "sharp": 0.18045827373862267}
+{"time": "11:03:14", "event": "step", "step": 430, "rows_seen": 13760, "lr": 9.799792298443728e-06, "tok_per_s": 845.629866666841, "loss": 0.6319852359592915, "entropy": 0.6180271878838539, "sharp": 0.15365645661950111}
+{"time": "11:06:39", "event": "step", "step": 440, "rows_seen": 14080, "lr": 8.542491591971554e-06, "tok_per_s": 846.2405706370508, "loss": 0.6109349951148033, "entropy": 0.5499566905200481, "sharp": 0.22229031287133694}
+{"time": "11:10:10", "event": "step", "step": 450, "rows_seen": 14400, "lr": 7.469563952077155e-06, "tok_per_s": 846.9379508454083, "loss": 0.5560286678373814, "entropy": 0.5911026783287525, "sharp": 0.18553075194358826}
+{"time": "11:13:31", "event": "step", "step": 460, "rows_seen": 14720, "lr": 6.585509610150972e-06, "tok_per_s": 847.5046881410133, "loss": 0.6414517425000668, "entropy": 0.5996933449059725, "sharp": 0.18129407241940498}
+{"time": "11:16:52", "event": "step", "step": 470, "rows_seen": 15040, "lr": 5.894036597333646e-06, "tok_per_s": 848.1044766206044, "loss": 0.6224712021648884, "entropy": 0.6070730686187744, "sharp": 0.17572548799216747}
+{"time": "11:20:11", "event": "step", "step": 480, "rows_seen": 15360, "lr": 5.398045191744809e-06, "tok_per_s": 848.7760633961865, "loss": 0.6015110500156879, "entropy": 0.5780304186046124, "sharp": 0.20515719428658485}
+{"time": "11:23:37", "event": "step", "step": 490, "rows_seen": 15680, "lr": 5.099615753708697e-06, "tok_per_s": 849.3657303134295, "loss": 0.5087847169488668, "entropy": 0.5568523928523064, "sharp": 0.21866239234805107}
+{"time": "11:26:59", "event": "step", "step": 500, "rows_seen": 16000, "lr": 5e-06, "tok_per_s": 849.8304124512657, "loss": 0.5707919746637344, "entropy": 0.5850860103964806, "sharp": 0.1883342992514372}
+{"time": "11:28:22", "event": "val", "step": 500, "rows_seen": 16000, "n": 500, "dropped_long": 0, "noul_ce": 0.5724773406982422, "noul_T": 0.8994957462639172, "noul_auc": 0.753742552868306, "noul_acc": 0.7, "noul_f1": 0.7634069400630915, "noul_nll": 0.571020727224648, "noul_ece": 0.05100578582286837, "noul_brier": 0.19442390800291787, "noul_sharp": 0.18469159305095673, "entropy": 0.5893295407295227}
+{"time": "11:31:21", "event": "ckpt", "tag": "ckpt-16000", "rows_seen": 16000, "replay_seen": 842, "step": 500, "tokens": 8970575, "tok_per_s": 829.3081822086466, "rows_per_s": 1.5570025777510128, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.559345543384552, "noul_T": 0.9011236680302168, "choice_ce": 0.6703149080276489, "choice_T": 1.0387025462416157, "score_ce": 1.0618693828582764, "score_T": 1.0368998603373318, "noul_auc": 0.7430528000000001, "noul_acc": 0.692, "noul_f1": 0.7659574468085106, "noul_nll": 0.5717629001699388, "noul_ece": 0.04781151111423971, "noul_brier": 0.19512653441247677, "noul_sharp": 0.1884661316871643, "entropy": 0.5864760279655457}, "dropped_long": 0, "peak_gib": 18.23796796798706}