backup e16/S1-E19-b-n4k-a100-syn (Pod B)

e16/S1-E19-b-n4k-a100-syn/ckpt-4000/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-n4k-a100-syn/ckpt-4000/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": [
+    "out_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "in_proj_z",
+    "gate_proj",
+    "down_proj",
+    "in_proj_qkv",
+    "q_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-n4k-a100-syn/ckpt-4000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae3fb8f9842f03940b23b8834108017ddbd731a333dbb95a7789a05ea74b5d2
+size 160486456

e16/S1-E19-b-n4k-a100-syn/ckpt-4000/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-n4k-a100-syn/ckpt-4000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb9325d368d1133ca35b235115118906e817168a2613104649a380360a3a9b1
+size 176641832

e16/S1-E19-b-n4k-a100-syn/ckpt-4000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  0.00038622046122327447,
+  -0.00038646903703920543,
+  -0.003093765350058675,
+  -0.00152659323066473,
+  -0.00013647761079482734,
+  0.001976793399080634,
+  0.001041998853906989,
+  -0.001958925509825349,
+  -0.0008781799115240574,
+  -0.0005699518951587379,
+  -0.0010260650888085365,
+  4.252501457813196e-05,
+  6.539467449329095e-06,
+  -0.0020297965966165066,
+  -0.0033733071759343147,
+  -0.005100378766655922,
+  -0.005943717900663614,
+  -0.004457105882465839,
+  -0.004970531910657883,
+  -0.005066348239779472,
+  -0.00418090308085084,
+  -0.0034946033265441656,
+  -0.00566587271168828,
+  -0.0035603693686425686
+ ],
+ "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-n4k-a100-syn/ckpt-4000/calibration.json

@@ -0,0 +1,29 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.5661502189198189,
+  "choice": 1.0567921975297938,
+  "score": 0.9282835428956957
+ },
+ "fit": {
+  "noul": {
+   "n": 1087,
+   "T": 0.5661502189198189,
+   "ce_before": 0.5926890969276428,
+   "ce_after": 0.5748082399368286
+  },
+  "choice": {
+   "n": 60,
+   "T": 1.0567921975297938,
+   "ce_before": 0.6628751754760742,
+   "ce_after": 0.6622037291526794
+  },
+  "score": {
+   "n": 53,
+   "T": 0.9282835428956957,
+   "ce_before": 1.053088665008545,
+   "ce_after": 1.051538348197937
+  }
+ },
+ "source": "models/e16/S1-E19-b-n4k-a100-syn/ckpt-4000"
+}

e16/S1-E19-b-n4k-a100-syn/ckpt-4000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7196519e927746b5ad51942261294dcea5d32e545fbf6f7f57326a3b5b55353b
+size 393464

e16/S1-E19-b-n4k-a100-syn/ckpt-4000/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-n4k-a100-syn/ckpt-4000",
+ "softcap": null,
+ "e16": {
+  "data": "data/e19/E19-b-n4k-a100",
+  "data_manifest": {
+   "arm": "E19-b-n4k-a100",
+   "name": null,
+   "train_sha256": "cce58fdf4091e63a961f7af926cc40eccdec44f8c47e16f9abc03a067093bc42",
+   "n_train": 4000
+  },
+  "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 125 steps",
+  "total_rows": 4000,
+  "lora": {
+   "r": 16,
+   "lora_alpha": 32,
+   "lora_dropout": 0.05
+  },
+  "trainer_sha256": "bc7c08e836bd99bb2665b02903cd41404ea029ecfa9b68a9ec1a7cda96958ba4",
+  "event": "ckpt",
+  "tag": "ckpt-4000",
+  "rows_seen": 4000,
+  "replay_seen": 210,
+  "step": 125,
+  "tokens": 2434864,
+  "tok_per_s": 782.2613804110864,
+  "rows_per_s": 1.352568523737226,
+  "val": {
+   "n": 1200,
+   "dropped_long": 0,
+   "noul_ce": 0.5926890969276428,
+   "noul_T": 0.5661502189198189,
+   "choice_ce": 0.6628751754760742,
+   "choice_T": 1.0567921975297938,
+   "score_ce": 1.053088665008545,
+   "score_T": 0.9282835428956957,
+   "noul_auc": 0.7187925333333333,
+   "noul_acc": 0.696,
+   "noul_f1": 0.7764705882352941,
+   "noul_nll": 0.6059869346469641,
+   "noul_ece": 0.07529046025872231,
+   "noul_brier": 0.2082081543180335,
+   "noul_sharp": 0.11994494497776031,
+   "entropy": 0.6532812714576721
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.236003875732422
+ }
+}

e16/S1-E19-b-n4k-a100-syn/train_log.jsonl

@@ -0,0 +1,15 @@
+{"time": "19:41:33", "event": "start", "data": "data/e19/E19-b-n4k-a100", "data_manifest": {"arm": "E19-b-n4k-a100", "name": null, "train_sha256": "cce58fdf4091e63a961f7af926cc40eccdec44f8c47e16f9abc03a067093bc42", "n_train": 4000}, "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 125 steps", "total_rows": 4000, "lora": {"r": 16, "lora_alpha": 32, "lora_dropout": 0.05}, "trainer_sha256": "bc7c08e836bd99bb2665b02903cd41404ea029ecfa9b68a9ec1a7cda96958ba4", "device": "cuda", "load_s": 91.3436529636383}
+{"time": "19:45:24", "event": "step", "step": 10, "rows_seen": 320, "lr": 9.923040269974204e-05, "tok_per_s": 843.0417437702955, "loss": 0.6775833070278168, "entropy": 0.6561039537191391, "sharp": 0.10389917343854904}
+{"time": "19:48:58", "event": "step", "step": 20, "rows_seen": 640, "lr": 9.55208574963224e-05, "tok_per_s": 850.2752472789067, "loss": 0.5635200552642345, "entropy": 0.6432114690542221, "sharp": 0.13042835984379053}
+{"time": "19:52:54", "event": "step", "step": 30, "rows_seen": 960, "lr": 8.897432118673851e-05, "tok_per_s": 854.3276579990592, "loss": 0.7616148106753826, "entropy": 0.6448729336261749, "sharp": 0.14085314702242613}
+{"time": "19:56:39", "event": "step", "step": 40, "rows_seen": 1280, "lr": 8.002250216471678e-05, "tok_per_s": 855.2316595864581, "loss": 0.6927734222263098, "entropy": 0.6715659871697426, "sharp": 0.09078672342002392}
+{"time": "20:00:26", "event": "step", "step": 50, "rows_seen": 1600, "lr": 6.925572411108201e-05, "tok_per_s": 856.5993582805264, "loss": 0.6491745263338089, "entropy": 0.6525300778448582, "sharp": 0.13547991961240768}
+{"time": "20:04:14", "event": "step", "step": 60, "rows_seen": 1920, "lr": 5.738399736402462e-05, "tok_per_s": 857.8110450885731, "loss": 0.6687481217086315, "entropy": 0.6334550902247429, "sharp": 0.14483051095157862}
+{"time": "20:08:04", "event": "step", "step": 70, "rows_seen": 2240, "lr": 4.519019760655705e-05, "tok_per_s": 858.030352965875, "loss": 0.6549195796251297, "entropy": 0.6614467650651932, "sharp": 0.11300366930663586}
+{"time": "20:11:53", "event": "step", "step": 80, "rows_seen": 2560, "lr": 3.3478439481564835e-05, "tok_per_s": 858.1912252723298, "loss": 0.707283329218626, "entropy": 0.6569504477083683, "sharp": 0.12130486220121384}
+{"time": "20:15:38", "event": "step", "step": 90, "rows_seen": 2880, "lr": 2.3021049613197416e-05, "tok_per_s": 858.6153724859848, "loss": 0.6408086456358433, "entropy": 0.6376857161521912, "sharp": 0.15480214729905128}
+{"time": "20:19:25", "event": "step", "step": 100, "rows_seen": 3200, "lr": 1.4507635874863332e-05, "tok_per_s": 857.820659936962, "loss": 0.6345666572451591, "entropy": 0.67517976090312, "sharp": 0.08465547952800989}
+{"time": "20:20:53", "event": "val", "step": 100, "rows_seen": 3200, "n": 500, "dropped_long": 0, "noul_ce": 0.6154733896255493, "noul_T": 0.4830142991980894, "noul_auc": 0.7306543349479333, "noul_acc": 0.682, "noul_f1": 0.7658321060382917, "noul_nll": 0.6152517849802971, "noul_ece": 0.10212810683250428, "noul_brier": 0.21223509394369017, "noul_sharp": 0.10266919434070587, "entropy": 0.6650827527046204}
+{"time": "20:24:46", "event": "step", "step": 110, "rows_seen": 3520, "lr": 8.49961150805399e-06, "tok_per_s": 829.228120629744, "loss": 0.6718039736151695, "entropy": 0.6632677316665649, "sharp": 0.11028149910271168}
+{"time": "20:28:27", "event": "step", "step": 120, "rows_seen": 3840, "lr": 5.3931729785351795e-06, "tok_per_s": 830.8952593410249, "loss": 0.6388795673847198, "entropy": 0.6698807775974274, "sharp": 0.08727332949638367}
+{"time": "20:33:27", "event": "ckpt", "tag": "ckpt-4000", "rows_seen": 4000, "replay_seen": 210, "step": 125, "tokens": 2434864, "tok_per_s": 782.2613804110864, "rows_per_s": 1.352568523737226, "val": {"n": 1200, "dropped_long": 0, "noul_ce": 0.5926890969276428, "noul_T": 0.5661502189198189, "choice_ce": 0.6628751754760742, "choice_T": 1.0567921975297938, "score_ce": 1.053088665008545, "score_T": 0.9282835428956957, "noul_auc": 0.7187925333333333, "noul_acc": 0.696, "noul_f1": 0.7764705882352941, "noul_nll": 0.6059869346469641, "noul_ece": 0.07529046025872231, "noul_brier": 0.2082081543180335, "noul_sharp": 0.11994494497776031, "entropy": 0.6532812714576721}, "dropped_long": 0, "peak_gib": 18.236003875732422}