backup e15/F1-LODO-dbe_kt22 (Pod B)

e15/F1-LODO-dbe_kt22/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

e15/F1-LODO-dbe_kt22/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",
+    "gate_proj",
+    "down_proj",
+    "in_proj_qkv",
+    "o_proj",
+    "q_proj",
+    "in_proj_z",
+    "v_proj",
+    "up_proj",
+    "k_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
+}

e15/F1-LODO-dbe_kt22/ckpt-4000/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc8e3b2832934ef04748614775ac176cfd8912559da25d5245bf0c4c79a14af
+size 160486456

e15/F1-LODO-dbe_kt22/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
+}

e15/F1-LODO-dbe_kt22/ckpt-4000/adapter_vllm/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9844fba43ad1a68d3e371b86e82fcacf6e72df225676f763aa943d253018357b
+size 176641832

e15/F1-LODO-dbe_kt22/ckpt-4000/adapter_vllm/decision_head.json

@@ -0,0 +1,99 @@
+{
+ "bias": [
+  -3.623149314080365e-05,
+  3.598227704060264e-05,
+  -0.0025878134183585644,
+  -0.0012615364976227283,
+  -0.00025007399381138384,
+  0.0019558551721274853,
+  0.0013559526996687055,
+  -0.0023348911199718714,
+  -0.0004082925443071872,
+  -0.0002078723773593083,
+  -1.2957353646925185e-05,
+  0.0001676026004133746,
+  0.0005569425993598998,
+  -0.001412136247381568,
+  -0.0028663526754826307,
+  -0.005061559844762087,
+  -0.00593328895047307,
+  -0.004319756291806698,
+  -0.004922541789710522,
+  -0.0049067651852965355,
+  -0.003943523392081261,
+  -0.003319827374070883,
+  -0.005581587553024292,
+  -0.0034480984322726727
+ ],
+ "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"
+}

e15/F1-LODO-dbe_kt22/ckpt-4000/calibration.json

@@ -0,0 +1,17 @@
+{
+ "version": 1,
+ "per_kind": {
+  "noul": 0.9954428915142555,
+  "choice": 1.0,
+  "score": 1.0
+ },
+ "fit": {
+  "noul": {
+   "n": 2000,
+   "T": 0.9954428915142555,
+   "ce_before": 0.5250526666641235,
+   "ce_after": 0.52504962682724
+  }
+ },
+ "source": "models/e15/F1-LODO-dbe_kt22/ckpt-4000"
+}

e15/F1-LODO-dbe_kt22/ckpt-4000/head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45145f8bb80b9108b8751776da907492686219c4429edabf1bed2d48720032d3
+size 393464

e15/F1-LODO-dbe_kt22/ckpt-4000/judge_config.json

@@ -0,0 +1,145 @@
+{
+ "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": "e15",
+ "source_checkpoint": "models/e15/F1-LODO-dbe_kt22/ckpt-4000",
+ "softcap": null,
+ "e15": {
+  "data": "data/e15/F1-LODO-dbe_kt22",
+  "data_manifest": {
+   "arm": "F1-LODO",
+   "name": "F1-LODO-dbe_kt22",
+   "train_sha256": "4ac935f5a6260cdaa14f74ba3ba09b19b0a9151400f96add2c9357278315e407",
+   "n_train": 16000
+  },
+  "init": "released",
+  "lr": 0.0001,
+  "lr_head": 0.0002,
+  "rows_per_step": 32,
+  "skip_rows": 0,
+  "epochs": 1,
+  "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
+  },
+  "event": "ckpt",
+  "tag": "ckpt-4000",
+  "rows_seen": 4000,
+  "step": 125,
+  "tokens": 2676235,
+  "tok_per_s": 788.7951158452983,
+  "val": {
+   "n": 2000,
+   "dropped_long": 0,
+   "noul_ce": 0.5250526666641235,
+   "kt_auc": 0.7884966488030971,
+   "kt_acc": 0.727,
+   "kt_f1": 0.7988209285187915,
+   "kt_ece": 0.031544476196169846,
+   "kt_nll": 0.5250526433140039
+  },
+  "dropped_long": 0,
+  "peak_gib": 18.235835075378418
+ }
+}

e15/F1-LODO-dbe_kt22/train_log.jsonl

@@ -0,0 +1,15 @@
+{"time": "11:52:16", "event": "start", "model_dir": "/workspace/jev_kt/models/hf/JEV-9B", "init": "released", "device": "cuda", "load_s": 116.84268808364868, "trainable_lora": 40108032, "head": 98328}
+{"time": "11:52:16", "event": "run", "data": "data/e15/F1-LODO-dbe_kt22", "out": "models/e15/F1-LODO-dbe_kt22"}
+{"time": "11:56:15", "event": "step", "step": 10, "rows_seen": 320, "loss": 0.5597564838826656, "lr": 9.923040269974204e-05, "tok_per_s": 892.8252975586905}
+{"time": "12:00:03", "event": "step", "step": 20, "rows_seen": 640, "loss": 0.5784428040497005, "lr": 9.55208574963224e-05, "tok_per_s": 894.8125098288366}
+{"time": "12:04:01", "event": "step", "step": 30, "rows_seen": 960, "loss": 0.5129471104592085, "lr": 8.897432118673851e-05, "tok_per_s": 894.4637446827277}
+{"time": "12:08:09", "event": "step", "step": 40, "rows_seen": 1280, "loss": 0.5547890234738588, "lr": 8.002250216471678e-05, "tok_per_s": 893.6722284018406}
+{"time": "12:12:10", "event": "step", "step": 50, "rows_seen": 1600, "loss": 0.5228286869823933, "lr": 6.925572411108201e-05, "tok_per_s": 894.8327824116469}
+{"time": "12:16:10", "event": "step", "step": 60, "rows_seen": 1920, "loss": 0.5534754495602101, "lr": 5.738399736402462e-05, "tok_per_s": 895.0990084125132}
+{"time": "12:20:14", "event": "step", "step": 70, "rows_seen": 2240, "loss": 0.5427125189453363, "lr": 4.519019760655705e-05, "tok_per_s": 894.2532345253351}
+{"time": "12:24:15", "event": "step", "step": 80, "rows_seen": 2560, "loss": 0.6720086908899248, "lr": 3.3478439481564835e-05, "tok_per_s": 894.7767451747436}
+{"time": "12:28:15", "event": "step", "step": 90, "rows_seen": 2880, "loss": 0.6765209548175335, "lr": 2.3021049613197416e-05, "tok_per_s": 895.3720997476648}
+{"time": "12:32:19", "event": "step", "step": 100, "rows_seen": 3200, "loss": 0.5380632318556309, "lr": 1.4507635874863332e-05, "tok_per_s": 894.9713351437393}
+{"time": "12:36:08", "event": "step", "step": 110, "rows_seen": 3520, "loss": 0.43723529763519764, "lr": 8.49961150805399e-06, "tok_per_s": 894.3180238929058}
+{"time": "12:40:05", "event": "step", "step": 120, "rows_seen": 3840, "loss": 0.41409095004200935, "lr": 5.3931729785351795e-06, "tok_per_s": 895.135348325423}
+{"time": "12:48:51", "event": "ckpt", "tag": "ckpt-4000", "rows_seen": 4000, "step": 125, "tokens": 2676235, "tok_per_s": 788.7951158452983, "val": {"n": 2000, "dropped_long": 0, "noul_ce": 0.5250526666641235, "kt_auc": 0.7884966488030971, "kt_acc": 0.727, "kt_f1": 0.7988209285187915, "kt_ece": 0.031544476196169846, "kt_nll": 0.5250526433140039}, "dropped_long": 0, "peak_gib": 18.235835075378418}