Upload folder using huggingface_hub

prior_attributer_polymarket_8b_1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+---
+
+# 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 0.14.0

prior_attributer_polymarket_8b_1000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/tidal-alsh-share2/usr/wangshanyong/models/Qwen/Qwen3-8B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

prior_attributer_polymarket_8b_1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164267cafde4141db282e015f4af8450b6da1f2726c68b9982950c2d718daf32
+size 245405936

prior_attributer_polymarket_8b_1000/config.json

@@ -0,0 +1,6 @@
+{
+  "base_model_name_or_path": "/mnt/tidal-alsh-share2/usr/wangshanyong/models/Qwen/Qwen3-8B",
+  "max_length": 1024,
+  "model_type": "llm_regressor",
+  "transformers_version": "4.57.6"
+}

prior_attributer_polymarket_8b_1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726e8633b64a8ef2afc8307a55779e8ec9e180a7a9b49ae39058ab09962d30f5
+size 499571322

prior_attributer_polymarket_8b_1000/regression_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c88058e1e36830108202fc804df9571f2b1ca05807d3779865f59b1848c0e99
+size 4297504

prior_attributer_polymarket_8b_1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e7fd43ead71bf040df2212a8b5cffc89a492d5db12a90bedbcf5b84247f901
+size 14244

prior_attributer_polymarket_8b_1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63818d7e752a9a992a847df6da441f35abead963147e84fe44ce9663ee51347
+size 1064

prior_attributer_polymarket_8b_1000/trainer_state.json

@@ -0,0 +1,901 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.13900727033615112,
+  "best_model_checkpoint": "../saves/prior_attributer_polymarket_8b/checkpoint-1000",
+  "epoch": 0.4079967360261118,
+  "eval_steps": 50,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004079967360261118,
+      "grad_norm": 2.670715093612671,
+      "learning_rate": 1e-05,
+      "loss": 0.1994,
+      "step": 1
+    },
+    {
+      "epoch": 0.004079967360261118,
+      "grad_norm": 0.20084570348262787,
+      "learning_rate": 9.996328029375766e-06,
+      "loss": 0.2647,
+      "step": 10
+    },
+    {
+      "epoch": 0.008159934720522236,
+      "grad_norm": 3.061854839324951,
+      "learning_rate": 9.992248062015506e-06,
+      "loss": 0.296,
+      "step": 20
+    },
+    {
+      "epoch": 0.012239902080783354,
+      "grad_norm": 5.403031826019287,
+      "learning_rate": 9.988168094655244e-06,
+      "loss": 0.6343,
+      "step": 30
+    },
+    {
+      "epoch": 0.016319869441044473,
+      "grad_norm": 2.4748289585113525,
+      "learning_rate": 9.984088127294983e-06,
+      "loss": 0.2773,
+      "step": 40
+    },
+    {
+      "epoch": 0.02039983680130559,
+      "grad_norm": 1.1733546257019043,
+      "learning_rate": 9.980008159934721e-06,
+      "loss": 0.333,
+      "step": 50
+    },
+    {
+      "epoch": 0.02039983680130559,
+      "eval_loss": 0.16383115947246552,
+      "eval_runtime": 10354.4824,
+      "eval_samples_per_second": 0.357,
+      "eval_steps_per_second": 0.357,
+      "step": 50
+    },
+    {
+      "epoch": 0.02447980416156671,
+      "grad_norm": 3.983604907989502,
+      "learning_rate": 9.97592819257446e-06,
+      "loss": 0.4789,
+      "step": 60
+    },
+    {
+      "epoch": 0.028559771521827825,
+      "grad_norm": 1.3020315170288086,
+      "learning_rate": 9.971848225214198e-06,
+      "loss": 0.3092,
+      "step": 70
+    },
+    {
+      "epoch": 0.032639738882088945,
+      "grad_norm": 4.395025253295898,
+      "learning_rate": 9.967768257853938e-06,
+      "loss": 0.5212,
+      "step": 80
+    },
+    {
+      "epoch": 0.03671970624235006,
+      "grad_norm": 1.5565115213394165,
+      "learning_rate": 9.963688290493678e-06,
+      "loss": 0.3205,
+      "step": 90
+    },
+    {
+      "epoch": 0.04079967360261118,
+      "grad_norm": 1.5836162567138672,
+      "learning_rate": 9.959608323133415e-06,
+      "loss": 0.327,
+      "step": 100
+    },
+    {
+      "epoch": 0.04079967360261118,
+      "eval_loss": 0.16183292865753174,
+      "eval_runtime": 10355.8257,
+      "eval_samples_per_second": 0.357,
+      "eval_steps_per_second": 0.357,
+      "step": 100
+    },
+    {
+      "epoch": 0.044879640962872294,
+      "grad_norm": 2.0744669437408447,
+      "learning_rate": 9.955528355773153e-06,
+      "loss": 0.3464,
+      "step": 110
+    },
+    {
+      "epoch": 0.04895960832313342,
+      "grad_norm": 0.9152021408081055,
+      "learning_rate": 9.951448388412893e-06,
+      "loss": 0.2172,
+      "step": 120
+    },
+    {
+      "epoch": 0.053039575683394534,
+      "grad_norm": 3.3941807746887207,
+      "learning_rate": 9.947368421052632e-06,
+      "loss": 0.4466,
+      "step": 130
+    },
+    {
+      "epoch": 0.05711954304365565,
+      "grad_norm": 2.671168565750122,
+      "learning_rate": 9.943288453692372e-06,
+      "loss": 0.3001,
+      "step": 140
+    },
+    {
+      "epoch": 0.06119951040391677,
+      "grad_norm": 2.2553200721740723,
+      "learning_rate": 9.93920848633211e-06,
+      "loss": 0.2611,
+      "step": 150
+    },
+    {
+      "epoch": 0.06119951040391677,
+      "eval_loss": 0.16030286252498627,
+      "eval_runtime": 10355.0438,
+      "eval_samples_per_second": 0.357,
+      "eval_steps_per_second": 0.357,
+      "step": 150
+    },
+    {
+      "epoch": 0.06527947776417789,
+      "grad_norm": 1.6387931108474731,
+      "learning_rate": 9.93512851897185e-06,
+      "loss": 0.2925,
+      "step": 160
+    },
+    {
+      "epoch": 0.069359445124439,
+      "grad_norm": 2.564134120941162,
+      "learning_rate": 9.931048551611589e-06,
+      "loss": 0.3059,
+      "step": 170
+    },
+    {
+      "epoch": 0.07343941248470012,
+      "grad_norm": 2.3305749893188477,
+      "learning_rate": 9.926968584251327e-06,
+      "loss": 0.3646,
+      "step": 180
+    },
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 4.769280433654785,
+      "learning_rate": 9.922888616891065e-06,
+      "loss": 0.2801,
+      "step": 190
+    },
+    {
+      "epoch": 0.08159934720522236,
+      "grad_norm": 2.8833346366882324,
+      "learning_rate": 9.918808649530804e-06,
+      "loss": 0.3375,
+      "step": 200
+    },
+    {
+      "epoch": 0.08159934720522236,
+      "eval_loss": 0.15935960412025452,
+      "eval_runtime": 10358.2826,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 200
+    },
+    {
+      "epoch": 0.08567931456548347,
+      "grad_norm": 7.480192184448242,
+      "learning_rate": 9.914728682170544e-06,
+      "loss": 0.502,
+      "step": 210
+    },
+    {
+      "epoch": 0.08975928192574459,
+      "grad_norm": 3.914731979370117,
+      "learning_rate": 9.910648714810282e-06,
+      "loss": 0.2675,
+      "step": 220
+    },
+    {
+      "epoch": 0.09383924928600572,
+      "grad_norm": 4.262155532836914,
+      "learning_rate": 9.906568747450021e-06,
+      "loss": 0.154,
+      "step": 230
+    },
+    {
+      "epoch": 0.09791921664626684,
+      "grad_norm": 0.0,
+      "learning_rate": 9.90248878008976e-06,
+      "loss": 0.3281,
+      "step": 240
+    },
+    {
+      "epoch": 0.10199918400652795,
+      "grad_norm": 0.0,
+      "learning_rate": 9.898408812729499e-06,
+      "loss": 0.1986,
+      "step": 250
+    },
+    {
+      "epoch": 0.10199918400652795,
+      "eval_loss": 0.15859133005142212,
+      "eval_runtime": 10363.3022,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 250
+    },
+    {
+      "epoch": 0.10607915136678907,
+      "grad_norm": 3.5509583950042725,
+      "learning_rate": 9.894328845369238e-06,
+      "loss": 0.3974,
+      "step": 260
+    },
+    {
+      "epoch": 0.11015911872705018,
+      "grad_norm": 2.8577442169189453,
+      "learning_rate": 9.890248878008976e-06,
+      "loss": 0.2832,
+      "step": 270
+    },
+    {
+      "epoch": 0.1142390860873113,
+      "grad_norm": 1.8718701601028442,
+      "learning_rate": 9.886168910648716e-06,
+      "loss": 0.3789,
+      "step": 280
+    },
+    {
+      "epoch": 0.11831905344757242,
+      "grad_norm": 4.342713356018066,
+      "learning_rate": 9.882088943288455e-06,
+      "loss": 0.4543,
+      "step": 290
+    },
+    {
+      "epoch": 0.12239902080783353,
+      "grad_norm": 3.926931619644165,
+      "learning_rate": 9.878008975928193e-06,
+      "loss": 0.3815,
+      "step": 300
+    },
+    {
+      "epoch": 0.12239902080783353,
+      "eval_loss": 0.1574268788099289,
+      "eval_runtime": 10364.1942,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 300
+    },
+    {
+      "epoch": 0.12647898816809466,
+      "grad_norm": 2.6151223182678223,
+      "learning_rate": 9.873929008567931e-06,
+      "loss": 0.182,
+      "step": 310
+    },
+    {
+      "epoch": 0.13055895552835578,
+      "grad_norm": 0.5143275260925293,
+      "learning_rate": 9.86984904120767e-06,
+      "loss": 0.2173,
+      "step": 320
+    },
+    {
+      "epoch": 0.1346389228886169,
+      "grad_norm": 0.8282421827316284,
+      "learning_rate": 9.86576907384741e-06,
+      "loss": 0.2572,
+      "step": 330
+    },
+    {
+      "epoch": 0.138718890248878,
+      "grad_norm": 0.7505475878715515,
+      "learning_rate": 9.861689106487148e-06,
+      "loss": 0.1832,
+      "step": 340
+    },
+    {
+      "epoch": 0.14279885760913913,
+      "grad_norm": 4.016334533691406,
+      "learning_rate": 9.857609139126888e-06,
+      "loss": 0.319,
+      "step": 350
+    },
+    {
+      "epoch": 0.14279885760913913,
+      "eval_loss": 0.15675334632396698,
+      "eval_runtime": 10364.3059,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 350
+    },
+    {
+      "epoch": 0.14687882496940025,
+      "grad_norm": 4.5542120933532715,
+      "learning_rate": 9.853529171766627e-06,
+      "loss": 0.3617,
+      "step": 360
+    },
+    {
+      "epoch": 0.15095879232966136,
+      "grad_norm": 0.0,
+      "learning_rate": 9.849449204406367e-06,
+      "loss": 0.3207,
+      "step": 370
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 2.223388433456421,
+      "learning_rate": 9.845369237046105e-06,
+      "loss": 0.3283,
+      "step": 380
+    },
+    {
+      "epoch": 0.1591187270501836,
+      "grad_norm": 0.0,
+      "learning_rate": 9.841289269685843e-06,
+      "loss": 0.2566,
+      "step": 390
+    },
+    {
+      "epoch": 0.1631986944104447,
+      "grad_norm": 3.4263710975646973,
+      "learning_rate": 9.837209302325582e-06,
+      "loss": 0.4226,
+      "step": 400
+    },
+    {
+      "epoch": 0.1631986944104447,
+      "eval_loss": 0.15490344166755676,
+      "eval_runtime": 10364.3662,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 400
+    },
+    {
+      "epoch": 0.16727866177070583,
+      "grad_norm": 2.0694384574890137,
+      "learning_rate": 9.833129334965322e-06,
+      "loss": 0.3677,
+      "step": 410
+    },
+    {
+      "epoch": 0.17135862913096694,
+      "grad_norm": 3.6313953399658203,
+      "learning_rate": 9.82904936760506e-06,
+      "loss": 0.3301,
+      "step": 420
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.0,
+      "learning_rate": 9.8249694002448e-06,
+      "loss": 0.2238,
+      "step": 430
+    },
+    {
+      "epoch": 0.17951856385148918,
+      "grad_norm": 2.6408114433288574,
+      "learning_rate": 9.820889432884537e-06,
+      "loss": 0.2209,
+      "step": 440
+    },
+    {
+      "epoch": 0.1835985312117503,
+      "grad_norm": 5.005034446716309,
+      "learning_rate": 9.816809465524277e-06,
+      "loss": 0.374,
+      "step": 450
+    },
+    {
+      "epoch": 0.1835985312117503,
+      "eval_loss": 0.15539048612117767,
+      "eval_runtime": 10364.9448,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 450
+    },
+    {
+      "epoch": 0.18767849857201144,
+      "grad_norm": 0.0,
+      "learning_rate": 9.812729498164015e-06,
+      "loss": 0.2161,
+      "step": 460
+    },
+    {
+      "epoch": 0.19175846593227255,
+      "grad_norm": 2.4610049724578857,
+      "learning_rate": 9.808649530803754e-06,
+      "loss": 0.2318,
+      "step": 470
+    },
+    {
+      "epoch": 0.19583843329253367,
+      "grad_norm": 0.7451673150062561,
+      "learning_rate": 9.804569563443494e-06,
+      "loss": 0.2398,
+      "step": 480
+    },
+    {
+      "epoch": 0.1999184006527948,
+      "grad_norm": 1.8425447940826416,
+      "learning_rate": 9.800489596083233e-06,
+      "loss": 0.3167,
+      "step": 490
+    },
+    {
+      "epoch": 0.2039983680130559,
+      "grad_norm": 2.5845742225646973,
+      "learning_rate": 9.796409628722971e-06,
+      "loss": 0.162,
+      "step": 500
+    },
+    {
+      "epoch": 0.2039983680130559,
+      "eval_loss": 0.15188691020011902,
+      "eval_runtime": 10364.8411,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 500
+    },
+    {
+      "epoch": 0.20807833537331702,
+      "grad_norm": 0.0,
+      "learning_rate": 9.792329661362709e-06,
+      "loss": 0.1781,
+      "step": 510
+    },
+    {
+      "epoch": 0.21215830273357814,
+      "grad_norm": 2.0829172134399414,
+      "learning_rate": 9.788249694002449e-06,
+      "loss": 0.2972,
+      "step": 520
+    },
+    {
+      "epoch": 0.21623827009383925,
+      "grad_norm": 2.929964303970337,
+      "learning_rate": 9.784169726642188e-06,
+      "loss": 0.2898,
+      "step": 530
+    },
+    {
+      "epoch": 0.22031823745410037,
+      "grad_norm": 6.498988151550293,
+      "learning_rate": 9.780089759281926e-06,
+      "loss": 0.2914,
+      "step": 540
+    },
+    {
+      "epoch": 0.22439820481436148,
+      "grad_norm": 3.3654491901397705,
+      "learning_rate": 9.776009791921666e-06,
+      "loss": 0.2302,
+      "step": 550
+    },
+    {
+      "epoch": 0.22439820481436148,
+      "eval_loss": 0.15363305807113647,
+      "eval_runtime": 10364.5889,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 550
+    },
+    {
+      "epoch": 0.2284781721746226,
+      "grad_norm": 1.2231923341751099,
+      "learning_rate": 9.771929824561405e-06,
+      "loss": 0.4205,
+      "step": 560
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 4.62269926071167,
+      "learning_rate": 9.767849857201143e-06,
+      "loss": 0.3172,
+      "step": 570
+    },
+    {
+      "epoch": 0.23663810689514483,
+      "grad_norm": 2.85361909866333,
+      "learning_rate": 9.763769889840881e-06,
+      "loss": 0.3243,
+      "step": 580
+    },
+    {
+      "epoch": 0.24071807425540595,
+      "grad_norm": 3.5462374687194824,
+      "learning_rate": 9.75968992248062e-06,
+      "loss": 0.3596,
+      "step": 590
+    },
+    {
+      "epoch": 0.24479804161566707,
+      "grad_norm": 2.7605552673339844,
+      "learning_rate": 9.75560995512036e-06,
+      "loss": 0.2076,
+      "step": 600
+    },
+    {
+      "epoch": 0.24479804161566707,
+      "eval_loss": 0.15099598467350006,
+      "eval_runtime": 10364.6206,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 600
+    },
+    {
+      "epoch": 0.24887800897592818,
+      "grad_norm": 2.784391403198242,
+      "learning_rate": 9.7515299877601e-06,
+      "loss": 0.3562,
+      "step": 610
+    },
+    {
+      "epoch": 0.2529579763361893,
+      "grad_norm": 2.931553363800049,
+      "learning_rate": 9.747450020399837e-06,
+      "loss": 0.3455,
+      "step": 620
+    },
+    {
+      "epoch": 0.25703794369645044,
+      "grad_norm": 1.5483777523040771,
+      "learning_rate": 9.743370053039577e-06,
+      "loss": 0.3134,
+      "step": 630
+    },
+    {
+      "epoch": 0.26111791105671156,
+      "grad_norm": 2.5101840496063232,
+      "learning_rate": 9.739290085679315e-06,
+      "loss": 0.2218,
+      "step": 640
+    },
+    {
+      "epoch": 0.2651978784169727,
+      "grad_norm": 0.6121233701705933,
+      "learning_rate": 9.735210118319054e-06,
+      "loss": 0.179,
+      "step": 650
+    },
+    {
+      "epoch": 0.2651978784169727,
+      "eval_loss": 0.15009666979312897,
+      "eval_runtime": 10364.7228,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 650
+    },
+    {
+      "epoch": 0.2692778457772338,
+      "grad_norm": 4.591267108917236,
+      "learning_rate": 9.731130150958792e-06,
+      "loss": 0.4943,
+      "step": 660
+    },
+    {
+      "epoch": 0.2733578131374949,
+      "grad_norm": 2.8425586223602295,
+      "learning_rate": 9.727050183598532e-06,
+      "loss": 0.1848,
+      "step": 670
+    },
+    {
+      "epoch": 0.277437780497756,
+      "grad_norm": 2.972445249557495,
+      "learning_rate": 9.722970216238272e-06,
+      "loss": 0.1622,
+      "step": 680
+    },
+    {
+      "epoch": 0.28151774785801714,
+      "grad_norm": 3.4708287715911865,
+      "learning_rate": 9.71889024887801e-06,
+      "loss": 0.1518,
+      "step": 690
+    },
+    {
+      "epoch": 0.28559771521827826,
+      "grad_norm": 1.8176753520965576,
+      "learning_rate": 9.714810281517749e-06,
+      "loss": 0.2419,
+      "step": 700
+    },
+    {
+      "epoch": 0.28559771521827826,
+      "eval_loss": 0.14927682280540466,
+      "eval_runtime": 10365.2728,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 700
+    },
+    {
+      "epoch": 0.2896776825785394,
+      "grad_norm": 2.8468093872070312,
+      "learning_rate": 9.710730314157487e-06,
+      "loss": 0.2811,
+      "step": 710
+    },
+    {
+      "epoch": 0.2937576499388005,
+      "grad_norm": 1.6590688228607178,
+      "learning_rate": 9.706650346797226e-06,
+      "loss": 0.1726,
+      "step": 720
+    },
+    {
+      "epoch": 0.2978376172990616,
+      "grad_norm": 1.9409711360931396,
+      "learning_rate": 9.702570379436966e-06,
+      "loss": 0.3225,
+      "step": 730
+    },
+    {
+      "epoch": 0.3019175846593227,
+      "grad_norm": 3.7657744884490967,
+      "learning_rate": 9.698490412076704e-06,
+      "loss": 0.3108,
+      "step": 740
+    },
+    {
+      "epoch": 0.30599755201958384,
+      "grad_norm": 4.228935718536377,
+      "learning_rate": 9.694410444716443e-06,
+      "loss": 0.536,
+      "step": 750
+    },
+    {
+      "epoch": 0.30599755201958384,
+      "eval_loss": 0.14842770993709564,
+      "eval_runtime": 10364.1675,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 750
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 2.4524126052856445,
+      "learning_rate": 9.690330477356183e-06,
+      "loss": 0.2715,
+      "step": 760
+    },
+    {
+      "epoch": 0.3141574867401061,
+      "grad_norm": 3.1010375022888184,
+      "learning_rate": 9.686250509995921e-06,
+      "loss": 0.2502,
+      "step": 770
+    },
+    {
+      "epoch": 0.3182374541003672,
+      "grad_norm": 0.4105437099933624,
+      "learning_rate": 9.682170542635659e-06,
+      "loss": 0.2992,
+      "step": 780
+    },
+    {
+      "epoch": 0.3223174214606283,
+      "grad_norm": 3.3335089683532715,
+      "learning_rate": 9.678090575275398e-06,
+      "loss": 0.2272,
+      "step": 790
+    },
+    {
+      "epoch": 0.3263973888208894,
+      "grad_norm": 3.66196870803833,
+      "learning_rate": 9.674010607915138e-06,
+      "loss": 0.1823,
+      "step": 800
+    },
+    {
+      "epoch": 0.3263973888208894,
+      "eval_loss": 0.1460103839635849,
+      "eval_runtime": 10364.4289,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 800
+    },
+    {
+      "epoch": 0.33047735618115054,
+      "grad_norm": 0.0,
+      "learning_rate": 9.669930640554876e-06,
+      "loss": 0.24,
+      "step": 810
+    },
+    {
+      "epoch": 0.33455732354141166,
+      "grad_norm": 2.9362757205963135,
+      "learning_rate": 9.665850673194615e-06,
+      "loss": 0.2955,
+      "step": 820
+    },
+    {
+      "epoch": 0.33863729090167277,
+      "grad_norm": 1.2982591390609741,
+      "learning_rate": 9.661770705834355e-06,
+      "loss": 0.1341,
+      "step": 830
+    },
+    {
+      "epoch": 0.3427172582619339,
+      "grad_norm": 1.246749758720398,
+      "learning_rate": 9.657690738474093e-06,
+      "loss": 0.3102,
+      "step": 840
+    },
+    {
+      "epoch": 0.346797225622195,
+      "grad_norm": 2.056279182434082,
+      "learning_rate": 9.653610771113832e-06,
+      "loss": 0.29,
+      "step": 850
+    },
+    {
+      "epoch": 0.346797225622195,
+      "eval_loss": 0.1432345062494278,
+      "eval_runtime": 10366.166,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 850
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.6712030172348022,
+      "learning_rate": 9.64953080375357e-06,
+      "loss": 0.146,
+      "step": 860
+    },
+    {
+      "epoch": 0.35495716034271724,
+      "grad_norm": 1.370171308517456,
+      "learning_rate": 9.64545083639331e-06,
+      "loss": 0.1812,
+      "step": 870
+    },
+    {
+      "epoch": 0.35903712770297835,
+      "grad_norm": 1.83916437625885,
+      "learning_rate": 9.64137086903305e-06,
+      "loss": 0.3776,
+      "step": 880
+    },
+    {
+      "epoch": 0.36311709506323947,
+      "grad_norm": 2.024589776992798,
+      "learning_rate": 9.637290901672787e-06,
+      "loss": 0.2238,
+      "step": 890
+    },
+    {
+      "epoch": 0.3671970624235006,
+      "grad_norm": 3.2594895362854004,
+      "learning_rate": 9.633210934312525e-06,
+      "loss": 0.3453,
+      "step": 900
+    },
+    {
+      "epoch": 0.3671970624235006,
+      "eval_loss": 0.14180521667003632,
+      "eval_runtime": 10366.0282,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 900
+    },
+    {
+      "epoch": 0.3712770297837617,
+      "grad_norm": 2.505995512008667,
+      "learning_rate": 9.629130966952265e-06,
+      "loss": 0.3888,
+      "step": 910
+    },
+    {
+      "epoch": 0.3753569971440229,
+      "grad_norm": 1.5990264415740967,
+      "learning_rate": 9.625050999592004e-06,
+      "loss": 0.2187,
+      "step": 920
+    },
+    {
+      "epoch": 0.379436964504284,
+      "grad_norm": 0.7377971410751343,
+      "learning_rate": 9.620971032231742e-06,
+      "loss": 0.2008,
+      "step": 930
+    },
+    {
+      "epoch": 0.3835169318645451,
+      "grad_norm": 1.8711506128311157,
+      "learning_rate": 9.616891064871482e-06,
+      "loss": 0.1518,
+      "step": 940
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 0.0,
+      "learning_rate": 9.612811097511221e-06,
+      "loss": 0.1361,
+      "step": 950
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "eval_loss": 0.1408400684595108,
+      "eval_runtime": 10364.8084,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 950
+    },
+    {
+      "epoch": 0.39167686658506734,
+      "grad_norm": 0.6772951483726501,
+      "learning_rate": 9.60873113015096e-06,
+      "loss": 0.1837,
+      "step": 960
+    },
+    {
+      "epoch": 0.39575683394532846,
+      "grad_norm": 3.2690086364746094,
+      "learning_rate": 9.604651162790699e-06,
+      "loss": 0.2869,
+      "step": 970
+    },
+    {
+      "epoch": 0.3998368013055896,
+      "grad_norm": 2.1059823036193848,
+      "learning_rate": 9.600571195430437e-06,
+      "loss": 0.2649,
+      "step": 980
+    },
+    {
+      "epoch": 0.4039167686658507,
+      "grad_norm": 2.562466621398926,
+      "learning_rate": 9.596491228070176e-06,
+      "loss": 0.4868,
+      "step": 990
+    },
+    {
+      "epoch": 0.4079967360261118,
+      "grad_norm": 2.7138028144836426,
+      "learning_rate": 9.592411260709916e-06,
+      "loss": 0.3554,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4079967360261118,
+      "eval_loss": 0.13900727033615112,
+      "eval_runtime": 10365.6047,
+      "eval_samples_per_second": 0.356,
+      "eval_steps_per_second": 0.356,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 24510,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0161226838179704e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

prior_attributer_polymarket_8b_1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c1a54958c21e348ca3e3a11aac86e1a111ebee7689aee1b3771ec407aa917f
+size 5496