Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 runs/dose_rows_v2/arms/rows256/adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+runs/dose_rows_v2/arms/rows512/adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text

runs/dose_rows_v2/arms/rows512/adapter/adapter_config.json

@@ -0,0 +1,451 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/data/parents/mixed_4ep_prop",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.language_model.layers.59.self_attn.k_proj",
+    "model.language_model.layers.22.mlp.up_proj",
+    "model.language_model.layers.41.self_attn.o_proj",
+    "model.language_model.layers.54.self_attn.o_proj",
+    "model.language_model.layers.30.self_attn.v_proj",
+    "model.language_model.layers.39.self_attn.q_proj",
+    "model.language_model.layers.54.self_attn.q_proj",
+    "model.language_model.layers.51.self_attn.q_proj",
+    "model.language_model.layers.42.self_attn.v_proj",
+    "model.language_model.layers.40.self_attn.o_proj",
+    "model.language_model.layers.54.self_attn.k_proj",
+    "model.language_model.layers.30.self_attn.q_proj",
+    "model.language_model.layers.51.self_attn.k_proj",
+    "model.language_model.layers.9.self_attn.o_proj",
+    "model.language_model.layers.52.self_attn.q_proj",
+    "model.language_model.layers.46.self_attn.k_proj",
+    "model.language_model.layers.53.mlp.up_proj",
+    "model.language_model.layers.55.self_attn.q_proj",
+    "model.language_model.layers.23.self_attn.o_proj",
+    "model.language_model.layers.56.mlp.up_proj",
+    "model.language_model.layers.0.self_attn.k_proj",
+    "model.language_model.layers.16.self_attn.q_proj",
+    "model.language_model.layers.10.mlp.down_proj",
+    "model.language_model.layers.11.mlp.gate_proj",
+    "model.language_model.layers.29.mlp.up_proj",
+    "model.language_model.layers.44.self_attn.k_proj",
+    "model.language_model.layers.41.self_attn.q_proj",
+    "model.language_model.layers.39.self_attn.v_proj",
+    "model.language_model.layers.18.mlp.gate_proj",
+    "model.language_model.layers.55.self_attn.o_proj",
+    "model.language_model.layers.28.self_attn.v_proj",
+    "model.language_model.layers.19.mlp.gate_proj",
+    "model.language_model.layers.3.mlp.up_proj",
+    "model.language_model.layers.32.mlp.gate_proj",
+    "model.language_model.layers.33.mlp.gate_proj",
+    "model.language_model.layers.50.self_attn.q_proj",
+    "model.language_model.layers.19.mlp.up_proj",
+    "model.language_model.layers.8.self_attn.q_proj",
+    "model.language_model.layers.29.mlp.down_proj",
+    "model.language_model.layers.38.self_attn.k_proj",
+    "model.language_model.layers.17.self_attn.o_proj",
+    "model.language_model.layers.56.self_attn.q_proj",
+    "model.language_model.layers.20.mlp.down_proj",
+    "model.language_model.layers.58.self_attn.v_proj",
+    "model.language_model.layers.47.self_attn.o_proj",
+    "model.language_model.layers.59.mlp.gate_proj",
+    "model.language_model.layers.52.mlp.down_proj",
+    "model.language_model.layers.30.mlp.up_proj",
+    "model.language_model.layers.27.self_attn.v_proj",
+    "model.language_model.layers.3.self_attn.q_proj",
+    "model.language_model.layers.58.self_attn.k_proj",
+    "model.language_model.layers.2.self_attn.q_proj",
+    "model.language_model.layers.23.self_attn.q_proj",
+    "model.language_model.layers.32.self_attn.v_proj",
+    "model.language_model.layers.1.self_attn.o_proj",
+    "model.language_model.layers.4.self_attn.k_proj",
+    "model.language_model.layers.50.self_attn.v_proj",
+    "model.language_model.layers.31.self_attn.v_proj",
+    "model.language_model.layers.3.self_attn.k_proj",
+    "model.language_model.layers.42.mlp.up_proj",
+    "model.language_model.layers.18.mlp.down_proj",
+    "model.language_model.layers.44.mlp.up_proj",
+    "model.language_model.layers.37.mlp.down_proj",
+    "model.language_model.layers.34.self_attn.o_proj",
+    "model.language_model.layers.28.mlp.up_proj",
+    "model.language_model.layers.23.self_attn.k_proj",
+    "model.language_model.layers.30.self_attn.k_proj",
+    "model.language_model.layers.26.mlp.up_proj",
+    "model.language_model.layers.17.self_attn.k_proj",
+    "model.language_model.layers.46.self_attn.q_proj",
+    "model.language_model.layers.36.mlp.down_proj",
+    "model.language_model.layers.50.self_attn.k_proj",
+    "model.language_model.layers.52.self_attn.k_proj",
+    "model.language_model.layers.20.self_attn.v_proj",
+    "model.language_model.layers.2.mlp.gate_proj",
+    "model.language_model.layers.4.mlp.down_proj",
+    "model.language_model.layers.49.mlp.up_proj",
+    "model.language_model.layers.50.self_attn.o_proj",
+    "model.language_model.layers.38.self_attn.o_proj",
+    "model.language_model.layers.19.self_attn.o_proj",
+    "model.language_model.layers.6.self_attn.o_proj",
+    "model.language_model.layers.16.mlp.gate_proj",
+    "model.language_model.layers.43.mlp.up_proj",
+    "model.language_model.layers.29.self_attn.q_proj",
+    "model.language_model.layers.55.self_attn.v_proj",
+    "model.language_model.layers.32.mlp.up_proj",
+    "model.language_model.layers.33.self_attn.q_proj",
+    "model.language_model.layers.23.mlp.up_proj",
+    "model.language_model.layers.0.self_attn.v_proj",
+    "model.language_model.layers.37.self_attn.v_proj",
+    "model.language_model.layers.38.self_attn.q_proj",
+    "model.language_model.layers.22.self_attn.v_proj",
+    "model.language_model.layers.31.mlp.down_proj",
+    "model.language_model.layers.29.self_attn.o_proj",
+    "model.language_model.layers.58.mlp.up_proj",
+    "model.language_model.layers.35.self_attn.k_proj",
+    "model.language_model.layers.18.self_attn.q_proj",
+    "model.language_model.layers.28.mlp.down_proj",
+    "model.language_model.layers.59.mlp.down_proj",
+    "model.language_model.layers.4.self_attn.v_proj",
+    "model.language_model.layers.34.self_attn.q_proj",
+    "model.language_model.layers.20.mlp.up_proj",
+    "model.language_model.layers.22.mlp.gate_proj",
+    "model.language_model.layers.29.self_attn.k_proj",
+    "model.language_model.layers.2.self_attn.v_proj",
+    "model.language_model.layers.44.self_attn.v_proj",
+    "model.language_model.layers.8.mlp.gate_proj",
+    "model.language_model.layers.5.mlp.down_proj",
+    "model.language_model.layers.56.self_attn.k_proj",
+    "model.language_model.layers.17.self_attn.q_proj",
+    "model.language_model.layers.36.self_attn.v_proj",
+    "model.language_model.layers.53.mlp.gate_proj",
+    "model.language_model.layers.49.self_attn.v_proj",
+    "model.language_model.layers.15.mlp.up_proj",
+    "model.language_model.layers.17.mlp.up_proj",
+    "model.language_model.layers.33.self_attn.v_proj",
+    "model.language_model.layers.13.self_attn.k_proj",
+    "model.language_model.layers.53.self_attn.o_proj",
+    "model.language_model.layers.45.mlp.up_proj",
+    "model.language_model.layers.11.mlp.down_proj",
+    "model.language_model.layers.10.self_attn.o_proj",
+    "model.language_model.layers.48.mlp.up_proj",
+    "model.language_model.layers.7.mlp.gate_proj",
+    "model.language_model.layers.46.self_attn.v_proj",
+    "model.language_model.layers.54.mlp.up_proj",
+    "model.language_model.layers.11.self_attn.q_proj",
+    "model.language_model.layers.24.self_attn.q_proj",
+    "model.language_model.layers.1.mlp.gate_proj",
+    "model.language_model.layers.10.self_attn.k_proj",
+    "model.language_model.layers.28.self_attn.q_proj",
+    "model.language_model.layers.0.mlp.gate_proj",
+    "model.language_model.layers.44.mlp.down_proj",
+    "model.language_model.layers.46.mlp.up_proj",
+    "model.language_model.layers.37.self_attn.q_proj",
+    "model.language_model.layers.26.self_attn.v_proj",
+    "model.language_model.layers.13.mlp.down_proj",
+    "model.language_model.layers.2.self_attn.o_proj",
+    "model.language_model.layers.20.mlp.gate_proj",
+    "model.language_model.layers.30.mlp.down_proj",
+    "model.language_model.layers.47.mlp.gate_proj",
+    "model.language_model.layers.47.mlp.up_proj",
+    "model.language_model.layers.52.self_attn.v_proj",
+    "model.language_model.layers.53.self_attn.k_proj",
+    "model.language_model.layers.36.self_attn.q_proj",
+    "model.language_model.layers.25.self_attn.v_proj",
+    "model.language_model.layers.50.mlp.gate_proj",
+    "model.language_model.layers.29.mlp.gate_proj",
+    "model.language_model.layers.27.mlp.up_proj",
+    "model.language_model.layers.45.mlp.down_proj",
+    "model.language_model.layers.49.self_attn.k_proj",
+    "model.language_model.layers.12.mlp.down_proj",
+    "model.language_model.layers.13.self_attn.q_proj",
+    "model.language_model.layers.39.mlp.down_proj",
+    "model.language_model.layers.4.mlp.gate_proj",
+    "model.language_model.layers.34.self_attn.k_proj",
+    "model.language_model.layers.12.mlp.up_proj",
+    "model.language_model.layers.18.self_attn.v_proj",
+    "model.language_model.layers.49.self_attn.q_proj",
+    "model.language_model.layers.51.self_attn.o_proj",
+    "model.language_model.layers.22.self_attn.q_proj",
+    "model.language_model.layers.5.mlp.gate_proj",
+    "model.language_model.layers.46.mlp.gate_proj",
+    "model.language_model.layers.31.mlp.up_proj",
+    "model.language_model.layers.47.self_attn.q_proj",
+    "model.language_model.layers.0.mlp.down_proj",
+    "model.language_model.layers.3.mlp.gate_proj",
+    "model.language_model.layers.37.self_attn.k_proj",
+    "model.language_model.layers.48.self_attn.k_proj",
+    "model.language_model.layers.13.mlp.up_proj",
+    "model.language_model.layers.52.mlp.gate_proj",
+    "model.language_model.layers.20.self_attn.q_proj",
+    "model.language_model.layers.43.self_attn.o_proj",
+    "model.language_model.layers.34.mlp.gate_proj",
+    "model.language_model.layers.3.self_attn.o_proj",
+    "model.language_model.layers.42.mlp.gate_proj",
+    "model.language_model.layers.0.self_attn.o_proj",
+    "model.language_model.layers.55.mlp.gate_proj",
+    "model.language_model.layers.35.self_attn.o_proj",
+    "model.language_model.layers.19.mlp.down_proj",
+    "model.language_model.layers.55.mlp.up_proj",
+    "model.language_model.layers.16.self_attn.k_proj",
+    "model.language_model.layers.21.mlp.down_proj",
+    "model.language_model.layers.8.self_attn.v_proj",
+    "model.language_model.layers.14.mlp.gate_proj",
+    "model.language_model.layers.57.self_attn.k_proj",
+    "model.language_model.layers.36.self_attn.k_proj",
+    "model.language_model.layers.6.mlp.down_proj",
+    "model.language_model.layers.21.mlp.gate_proj",
+    "model.language_model.layers.12.self_attn.v_proj",
+    "model.language_model.layers.11.mlp.up_proj",
+    "model.language_model.layers.6.self_attn.v_proj",
+    "model.language_model.layers.32.mlp.down_proj",
+    "model.language_model.layers.11.self_attn.o_proj",
+    "model.language_model.layers.0.self_attn.q_proj",
+    "model.language_model.layers.8.self_attn.k_proj",
+    "model.language_model.layers.6.self_attn.k_proj",
+    "model.language_model.layers.12.self_attn.q_proj",
+    "model.language_model.layers.8.mlp.up_proj",
+    "model.language_model.layers.18.self_attn.k_proj",
+    "model.language_model.layers.35.mlp.up_proj",
+    "model.language_model.layers.34.self_attn.v_proj",
+    "model.language_model.layers.52.self_attn.o_proj",
+    "model.language_model.layers.45.self_attn.o_proj",
+    "model.language_model.layers.16.mlp.down_proj",
+    "model.language_model.layers.31.self_attn.q_proj",
+    "model.language_model.layers.13.self_attn.v_proj",
+    "model.language_model.layers.15.self_attn.q_proj",
+    "model.language_model.layers.56.self_attn.o_proj",
+    "model.language_model.layers.7.self_attn.q_proj",
+    "model.language_model.layers.21.self_attn.v_proj",
+    "model.language_model.layers.11.self_attn.k_proj",
+    "model.language_model.layers.6.mlp.up_proj",
+    "model.language_model.layers.18.mlp.up_proj",
+    "model.language_model.layers.3.mlp.down_proj",
+    "model.language_model.layers.19.self_attn.k_proj",
+    "model.language_model.layers.26.self_attn.q_proj",
+    "model.language_model.layers.9.self_attn.k_proj",
+    "model.language_model.layers.49.mlp.gate_proj",
+    "model.language_model.layers.33.self_attn.k_proj",
+    "model.language_model.layers.35.mlp.down_proj",
+    "model.language_model.layers.17.mlp.down_proj",
+    "model.language_model.layers.16.self_attn.v_proj",
+    "model.language_model.layers.39.self_attn.k_proj",
+    "model.language_model.layers.27.mlp.down_proj",
+    "model.language_model.layers.2.mlp.up_proj",
+    "model.language_model.layers.14.self_attn.v_proj",
+    "model.language_model.layers.51.mlp.down_proj",
+    "model.language_model.layers.41.mlp.gate_proj",
+    "model.language_model.layers.43.mlp.gate_proj",
+    "model.language_model.layers.14.mlp.down_proj",
+    "model.language_model.layers.48.self_attn.v_proj",
+    "model.language_model.layers.56.mlp.down_proj",
+    "model.language_model.layers.35.mlp.gate_proj",
+    "model.language_model.layers.31.self_attn.o_proj",
+    "model.language_model.layers.32.self_attn.o_proj",
+    "model.language_model.layers.3.self_attn.v_proj",
+    "model.language_model.layers.27.self_attn.k_proj",
+    "model.language_model.layers.55.mlp.down_proj",
+    "model.language_model.layers.7.mlp.down_proj",
+    "model.language_model.layers.2.self_attn.k_proj",
+    "model.language_model.layers.47.mlp.down_proj",
+    "model.language_model.layers.40.mlp.up_proj",
+    "model.language_model.layers.22.self_attn.k_proj",
+    "model.language_model.layers.25.mlp.down_proj",
+    "model.language_model.layers.8.mlp.down_proj",
+    "model.language_model.layers.30.self_attn.o_proj",
+    "model.language_model.layers.23.mlp.gate_proj",
+    "model.language_model.layers.44.self_attn.o_proj",
+    "model.language_model.layers.38.self_attn.v_proj",
+    "model.language_model.layers.26.mlp.down_proj",
+    "model.language_model.layers.16.self_attn.o_proj",
+    "model.language_model.layers.57.mlp.down_proj",
+    "model.language_model.layers.33.mlp.up_proj",
+    "model.language_model.layers.24.self_attn.o_proj",
+    "model.language_model.layers.5.self_attn.k_proj",
+    "model.language_model.layers.42.self_attn.q_proj",
+    "model.language_model.layers.43.self_attn.v_proj",
+    "model.language_model.layers.51.self_attn.v_proj",
+    "model.language_model.layers.14.self_attn.q_proj",
+    "model.language_model.layers.18.self_attn.o_proj",
+    "model.language_model.layers.21.self_attn.q_proj",
+    "model.language_model.layers.5.self_attn.o_proj",
+    "model.language_model.layers.20.self_attn.k_proj",
+    "model.language_model.layers.57.self_attn.o_proj",
+    "model.language_model.layers.57.mlp.gate_proj",
+    "model.language_model.layers.54.mlp.down_proj",
+    "model.language_model.layers.9.self_attn.v_proj",
+    "model.language_model.layers.35.self_attn.q_proj",
+    "model.language_model.layers.9.mlp.gate_proj",
+    "model.language_model.layers.26.mlp.gate_proj",
+    "model.language_model.layers.1.self_attn.k_proj",
+    "model.language_model.layers.42.self_attn.k_proj",
+    "model.language_model.layers.51.mlp.gate_proj",
+    "model.language_model.layers.14.mlp.up_proj",
+    "model.language_model.layers.41.self_attn.k_proj",
+    "model.language_model.layers.24.self_attn.v_proj",
+    "model.language_model.layers.10.self_attn.q_proj",
+    "model.language_model.layers.58.self_attn.o_proj",
+    "model.language_model.layers.45.self_attn.v_proj",
+    "model.language_model.layers.37.self_attn.o_proj",
+    "model.language_model.layers.14.self_attn.o_proj",
+    "model.language_model.layers.33.self_attn.o_proj",
+    "model.language_model.layers.49.mlp.down_proj",
+    "model.language_model.layers.58.mlp.gate_proj",
+    "model.language_model.layers.5.mlp.up_proj",
+    "model.language_model.layers.47.self_attn.k_proj",
+    "model.language_model.layers.15.self_attn.k_proj",
+    "model.language_model.layers.32.self_attn.k_proj",
+    "model.language_model.layers.10.mlp.up_proj",
+    "model.language_model.layers.42.mlp.down_proj",
+    "model.language_model.layers.16.mlp.up_proj",
+    "model.language_model.layers.50.mlp.up_proj",
+    "model.language_model.layers.48.mlp.down_proj",
+    "model.language_model.layers.4.mlp.up_proj",
+    "model.language_model.layers.40.mlp.gate_proj",
+    "model.language_model.layers.2.mlp.down_proj",
+    "model.language_model.layers.23.mlp.down_proj",
+    "model.language_model.layers.5.self_attn.q_proj",
+    "model.language_model.layers.53.mlp.down_proj",
+    "model.language_model.layers.32.self_attn.q_proj",
+    "model.language_model.layers.0.mlp.up_proj",
+    "model.language_model.layers.27.self_attn.q_proj",
+    "model.language_model.layers.8.self_attn.o_proj",
+    "model.language_model.layers.38.mlp.down_proj",
+    "model.language_model.layers.45.mlp.gate_proj",
+    "model.language_model.layers.34.mlp.down_proj",
+    "model.language_model.layers.48.self_attn.o_proj",
+    "model.language_model.layers.40.self_attn.k_proj",
+    "model.language_model.layers.39.mlp.gate_proj",
+    "model.language_model.layers.7.mlp.up_proj",
+    "model.language_model.layers.30.mlp.gate_proj",
+    "model.language_model.layers.44.self_attn.q_proj",
+    "model.language_model.layers.31.mlp.gate_proj",
+    "model.language_model.layers.40.self_attn.v_proj",
+    "model.language_model.layers.37.mlp.up_proj",
+    "model.language_model.layers.7.self_attn.v_proj",
+    "model.language_model.layers.54.mlp.gate_proj",
+    "model.language_model.layers.48.mlp.gate_proj",
+    "model.language_model.layers.15.self_attn.v_proj",
+    "model.language_model.layers.49.self_attn.o_proj",
+    "model.language_model.layers.25.mlp.up_proj",
+    "model.language_model.layers.24.mlp.down_proj",
+    "model.language_model.layers.20.self_attn.o_proj",
+    "model.language_model.layers.40.self_attn.q_proj",
+    "model.language_model.layers.38.mlp.gate_proj",
+    "model.language_model.layers.25.self_attn.q_proj",
+    "model.language_model.layers.58.self_attn.q_proj",
+    "model.language_model.layers.1.mlp.down_proj",
+    "model.language_model.layers.45.self_attn.q_proj",
+    "model.language_model.layers.57.self_attn.v_proj",
+    "model.language_model.layers.26.self_attn.k_proj",
+    "model.language_model.layers.43.self_attn.q_proj",
+    "model.language_model.layers.40.mlp.down_proj",
+    "model.language_model.layers.26.self_attn.o_proj",
+    "model.language_model.layers.45.self_attn.k_proj",
+    "model.language_model.layers.25.self_attn.o_proj",
+    "model.language_model.layers.27.mlp.gate_proj",
+    "model.language_model.layers.54.self_attn.v_proj",
+    "model.language_model.layers.36.self_attn.o_proj",
+    "model.language_model.layers.56.mlp.gate_proj",
+    "model.language_model.layers.6.self_attn.q_proj",
+    "model.language_model.layers.42.self_attn.o_proj",
+    "model.language_model.layers.59.self_attn.q_proj",
+    "model.language_model.layers.25.mlp.gate_proj",
+    "model.language_model.layers.9.mlp.up_proj",
+    "model.language_model.layers.15.self_attn.o_proj",
+    "model.language_model.layers.52.mlp.up_proj",
+    "model.language_model.layers.7.self_attn.k_proj",
+    "model.language_model.layers.39.self_attn.o_proj",
+    "model.language_model.layers.24.mlp.up_proj",
+    "model.language_model.layers.7.self_attn.o_proj",
+    "model.language_model.layers.15.mlp.gate_proj",
+    "model.language_model.layers.53.self_attn.q_proj",
+    "model.language_model.layers.55.self_attn.k_proj",
+    "model.language_model.layers.4.self_attn.q_proj",
+    "model.language_model.layers.19.self_attn.q_proj",
+    "model.language_model.layers.31.self_attn.k_proj",
+    "model.language_model.layers.56.self_attn.v_proj",
+    "model.language_model.layers.4.self_attn.o_proj",
+    "model.language_model.layers.37.mlp.gate_proj",
+    "model.language_model.layers.50.mlp.down_proj",
+    "model.language_model.layers.43.self_attn.k_proj",
+    "model.language_model.layers.38.mlp.up_proj",
+    "model.language_model.layers.46.self_attn.o_proj",
+    "model.language_model.layers.22.self_attn.o_proj",
+    "model.language_model.layers.12.mlp.gate_proj",
+    "model.language_model.layers.17.mlp.gate_proj",
+    "model.language_model.layers.28.self_attn.k_proj",
+    "model.language_model.layers.21.self_attn.k_proj",
+    "model.language_model.layers.48.self_attn.q_proj",
+    "model.language_model.layers.44.mlp.gate_proj",
+    "model.language_model.layers.1.self_attn.q_proj",
+    "model.language_model.layers.13.mlp.gate_proj",
+    "model.language_model.layers.46.mlp.down_proj",
+    "model.language_model.layers.21.self_attn.o_proj",
+    "model.language_model.layers.9.self_attn.q_proj",
+    "model.language_model.layers.39.mlp.up_proj",
+    "model.language_model.layers.24.self_attn.k_proj",
+    "model.language_model.layers.41.mlp.up_proj",
+    "model.language_model.layers.51.mlp.up_proj",
+    "model.language_model.layers.24.mlp.gate_proj",
+    "model.language_model.layers.59.mlp.up_proj",
+    "model.language_model.layers.36.mlp.up_proj",
+    "model.language_model.layers.58.mlp.down_proj",
+    "model.language_model.layers.12.self_attn.o_proj",
+    "model.language_model.layers.27.self_attn.o_proj",
+    "model.language_model.layers.28.mlp.gate_proj",
+    "model.language_model.layers.57.self_attn.q_proj",
+    "model.language_model.layers.10.self_attn.v_proj",
+    "model.language_model.layers.13.self_attn.o_proj",
+    "model.language_model.layers.21.mlp.up_proj",
+    "model.language_model.layers.14.self_attn.k_proj",
+    "model.language_model.layers.28.self_attn.o_proj",
+    "model.language_model.layers.36.mlp.gate_proj",
+    "model.language_model.layers.1.mlp.up_proj",
+    "model.language_model.layers.43.mlp.down_proj",
+    "model.language_model.layers.15.mlp.down_proj",
+    "model.language_model.layers.9.mlp.down_proj",
+    "model.language_model.layers.22.mlp.down_proj",
+    "model.language_model.layers.59.self_attn.o_proj",
+    "model.language_model.layers.34.mlp.up_proj",
+    "model.language_model.layers.33.mlp.down_proj",
+    "model.language_model.layers.6.mlp.gate_proj",
+    "model.language_model.layers.57.mlp.up_proj",
+    "model.language_model.layers.1.self_attn.v_proj",
+    "model.language_model.layers.10.mlp.gate_proj",
+    "model.language_model.layers.25.self_attn.k_proj",
+    "model.language_model.layers.41.mlp.down_proj",
+    "model.language_model.layers.12.self_attn.k_proj",
+    "model.language_model.layers.19.self_attn.v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

runs/dose_rows_v2/arms/rows512/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802071a1ebdfd7d1aa1f4a81865bfeb55bfe1474bd80be49a17517b1bd2256a3
+size 1958995176

runs/dose_rows_v2/arms/rows512/adapter/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<|turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<|image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<turn|>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<|turn>model
+'}}
+{%- endif -%}

runs/dose_rows_v2/arms/rows512/adapter/config.json

@@ -0,0 +1,177 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": null,
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": 1,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "pad_token_id": 0,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": true,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 5376,
+    "hidden_size_per_layer_input": 0,
+    "initializer_range": 0.02,
+    "intermediate_size": 21504,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 262144,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 32,
+    "num_experts": null,
+    "num_global_key_value_heads": 4,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 16,
+    "num_kv_shared_layers": 0,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 1024,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": "vision",
+    "use_cache": false,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.9.0",
+  "use_cache": false,
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 72,
+    "head_dim": 72,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "num_key_value_heads": 16,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": true,
+    "use_clipped_linears": false
+  },
+  "vision_soft_tokens_per_image": 280
+}

runs/dose_rows_v2/arms/rows512/adapter/debug.log

@@ -0,0 +1,771 @@
+[2026-09-05 09:12:52,957] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:59939] baseline 0.000GB ()
+[2026-09-05 09:12:52,959] [INFO] [axolotl.cli.config.load_cfg:333] [PID:59939] config:
+{
+  "activation_offloading": false,
+  "adapter": "lora",
+  "attn_implementation": "flash_attention_2",
+  "attn_needs_dtype_cast": true,
+  "attn_supports_packing": true,
+  "attn_uses_flash_lib": true,
+  "axolotl_config_path": "/workspace/eft31b_runs/dose_rows_v2/rows512/train/axolotl.yaml",
+  "base_model": "/workspace/data/parents/mixed_4ep_prop",
+  "base_model_config": "/workspace/data/parents/mixed_4ep_prop",
+  "batch_size": 32,
+  "bf16": true,
+  "capabilities": {
+    "bf16": true,
+    "compute_capability": "sm_90",
+    "fp8": true,
+    "n_gpu": 1,
+    "n_node": 1,
+    "tf32": true
+  },
+  "chat_template": "jinja",
+  "chat_template_jinja": "/workspace/work/src/scimt/train/stages/assets/gemma4_chat_template.jinja",
+  "checkpoint_schedule": [
+    64
+  ],
+  "context_parallel_size": 1,
+  "cosine_min_lr_ratio": 0.1,
+  "cut_cross_entropy": true,
+  "dataloader_num_workers": 1,
+  "dataloader_pin_memory": true,
+  "dataloader_prefetch_factor": 256,
+  "dataset_num_proc": 4,
+  "dataset_prepared_path": "/workspace/eft31b_runs/dose_rows_v2/rows512/train/prepared",
+  "datasets": [
+    {
+      "chat_template": "tokenizer_default",
+      "field_messages": "messages",
+      "message_property_mappings": {
+        "content": "content",
+        "role": "role"
+      },
+      "path": "/workspace/eft31b_runs/dose_rows_v2/rows512/eft_training.jsonl",
+      "trust_remote_code": false,
+      "type": "chat_template"
+    }
+  ],
+  "ddp": false,
+  "ddp_find_unused_parameters": true,
+  "device": "cuda:0",
+  "dion_rank_fraction": 1.0,
+  "dion_rank_multiple_of": 1,
+  "eaft_alpha": 1.0,
+  "eaft_k": 20,
+  "env_capabilities": {
+    "torch_version": "2.12.1"
+  },
+  "eot_tokens": [
+    "<turn|>"
+  ],
+  "eval_batch_size": 1,
+  "eval_causal_lm_metrics": [
+    "sacrebleu",
+    "comet",
+    "ter",
+    "chrf"
+  ],
+  "eval_max_new_tokens": 128,
+  "eval_table_size": 0,
+  "experimental_skip_move_to_device": true,
+  "fp16": false,
+  "gemma4_hybrid_attn_impl": true,
+  "generate_samples": false,
+  "generation_do_sample": true,
+  "generation_max_new_tokens": 50,
+  "generation_prompt_ratio": 0.5,
+  "generation_temperature": 0.7,
+  "gradient_accumulation_steps": 32,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": {
+    "use_reentrant": false
+  },
+  "include_tkps": true,
+  "is_multimodal": true,
+  "layer_offloading": false,
+  "learning_rate": 0.0001,
+  "lisa_layers_attribute": "model.layers",
+  "load_best_model_at_end": false,
+  "load_in_4bit": false,
+  "load_in_8bit": false,
+  "local_rank": 0,
+  "logging_steps": 1,
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "lora_mlp_kernel": false,
+  "lora_o_kernel": false,
+  "lora_qkv_kernel": false,
+  "lora_r": 64,
+  "lora_target_modules": [
+    "model.language_model.layers.0.self_attn.q_proj",
+    "model.language_model.layers.0.self_attn.k_proj",
+    "model.language_model.layers.0.self_attn.v_proj",
+    "model.language_model.layers.0.self_attn.o_proj",
+    "model.language_model.layers.0.mlp.gate_proj",
+    "model.language_model.layers.0.mlp.up_proj",
+    "model.language_model.layers.0.mlp.down_proj",
+    "model.language_model.layers.1.self_attn.q_proj",
+    "model.language_model.layers.1.self_attn.k_proj",
+    "model.language_model.layers.1.self_attn.v_proj",
+    "model.language_model.layers.1.self_attn.o_proj",
+    "model.language_model.layers.1.mlp.gate_proj",
+    "model.language_model.layers.1.mlp.up_proj",
+    "model.language_model.layers.1.mlp.down_proj",
+    "model.language_model.layers.2.self_attn.q_proj",
+    "model.language_model.layers.2.self_attn.k_proj",
+    "model.language_model.layers.2.self_attn.v_proj",
+    "model.language_model.layers.2.self_attn.o_proj",
+    "model.language_model.layers.2.mlp.gate_proj",
+    "model.language_model.layers.2.mlp.up_proj",
+    "model.language_model.layers.2.mlp.down_proj",
+    "model.language_model.layers.3.self_attn.q_proj",
+    "model.language_model.layers.3.self_attn.k_proj",
+    "model.language_model.layers.3.self_attn.v_proj",
+    "model.language_model.layers.3.self_attn.o_proj",
+    "model.language_model.layers.3.mlp.gate_proj",
+    "model.language_model.layers.3.mlp.up_proj",
+    "model.language_model.layers.3.mlp.down_proj",
+    "model.language_model.layers.4.self_attn.q_proj",
+    "model.language_model.layers.4.self_attn.k_proj",
+    "model.language_model.layers.4.self_attn.v_proj",
+    "model.language_model.layers.4.self_attn.o_proj",
+    "model.language_model.layers.4.mlp.gate_proj",
+    "model.language_model.layers.4.mlp.up_proj",
+    "model.language_model.layers.4.mlp.down_proj",
+    "model.language_model.layers.5.self_attn.q_proj",
+    "model.language_model.layers.5.self_attn.k_proj",
+    "model.language_model.layers.5.self_attn.o_proj",
+    "model.language_model.layers.5.mlp.gate_proj",
+    "model.language_model.layers.5.mlp.up_proj",
+    "model.language_model.layers.5.mlp.down_proj",
+    "model.language_model.layers.6.self_attn.q_proj",
+    "model.language_model.layers.6.self_attn.k_proj",
+    "model.language_model.layers.6.self_attn.v_proj",
+    "model.language_model.layers.6.self_attn.o_proj",
+    "model.language_model.layers.6.mlp.gate_proj",
+    "model.language_model.layers.6.mlp.up_proj",
+    "model.language_model.layers.6.mlp.down_proj",
+    "model.language_model.layers.7.self_attn.q_proj",
+    "model.language_model.layers.7.self_attn.k_proj",
+    "model.language_model.layers.7.self_attn.v_proj",
+    "model.language_model.layers.7.self_attn.o_proj",
+    "model.language_model.layers.7.mlp.gate_proj",
+    "model.language_model.layers.7.mlp.up_proj",
+    "model.language_model.layers.7.mlp.down_proj",
+    "model.language_model.layers.8.self_attn.q_proj",
+    "model.language_model.layers.8.self_attn.k_proj",
+    "model.language_model.layers.8.self_attn.v_proj",
+    "model.language_model.layers.8.self_attn.o_proj",
+    "model.language_model.layers.8.mlp.gate_proj",
+    "model.language_model.layers.8.mlp.up_proj",
+    "model.language_model.layers.8.mlp.down_proj",
+    "model.language_model.layers.9.self_attn.q_proj",
+    "model.language_model.layers.9.self_attn.k_proj",
+    "model.language_model.layers.9.self_attn.v_proj",
+    "model.language_model.layers.9.self_attn.o_proj",
+    "model.language_model.layers.9.mlp.gate_proj",
+    "model.language_model.layers.9.mlp.up_proj",
+    "model.language_model.layers.9.mlp.down_proj",
+    "model.language_model.layers.10.self_attn.q_proj",
+    "model.language_model.layers.10.self_attn.k_proj",
+    "model.language_model.layers.10.self_attn.v_proj",
+    "model.language_model.layers.10.self_attn.o_proj",
+    "model.language_model.layers.10.mlp.gate_proj",
+    "model.language_model.layers.10.mlp.up_proj",
+    "model.language_model.layers.10.mlp.down_proj",
+    "model.language_model.layers.11.self_attn.q_proj",
+    "model.language_model.layers.11.self_attn.k_proj",
+    "model.language_model.layers.11.self_attn.o_proj",
+    "model.language_model.layers.11.mlp.gate_proj",
+    "model.language_model.layers.11.mlp.up_proj",
+    "model.language_model.layers.11.mlp.down_proj",
+    "model.language_model.layers.12.self_attn.q_proj",
+    "model.language_model.layers.12.self_attn.k_proj",
+    "model.language_model.layers.12.self_attn.v_proj",
+    "model.language_model.layers.12.self_attn.o_proj",
+    "model.language_model.layers.12.mlp.gate_proj",
+    "model.language_model.layers.12.mlp.up_proj",
+    "model.language_model.layers.12.mlp.down_proj",
+    "model.language_model.layers.13.self_attn.q_proj",
+    "model.language_model.layers.13.self_attn.k_proj",
+    "model.language_model.layers.13.self_attn.v_proj",
+    "model.language_model.layers.13.self_attn.o_proj",
+    "model.language_model.layers.13.mlp.gate_proj",
+    "model.language_model.layers.13.mlp.up_proj",
+    "model.language_model.layers.13.mlp.down_proj",
+    "model.language_model.layers.14.self_attn.q_proj",
+    "model.language_model.layers.14.self_attn.k_proj",
+    "model.language_model.layers.14.self_attn.v_proj",
+    "model.language_model.layers.14.self_attn.o_proj",
+    "model.language_model.layers.14.mlp.gate_proj",
+    "model.language_model.layers.14.mlp.up_proj",
+    "model.language_model.layers.14.mlp.down_proj",
+    "model.language_model.layers.15.self_attn.q_proj",
+    "model.language_model.layers.15.self_attn.k_proj",
+    "model.language_model.layers.15.self_attn.v_proj",
+    "model.language_model.layers.15.self_attn.o_proj",
+    "model.language_model.layers.15.mlp.gate_proj",
+    "model.language_model.layers.15.mlp.up_proj",
+    "model.language_model.layers.15.mlp.down_proj",
+    "model.language_model.layers.16.self_attn.q_proj",
+    "model.language_model.layers.16.self_attn.k_proj",
+    "model.language_model.layers.16.self_attn.v_proj",
+    "model.language_model.layers.16.self_attn.o_proj",
+    "model.language_model.layers.16.mlp.gate_proj",
+    "model.language_model.layers.16.mlp.up_proj",
+    "model.language_model.layers.16.mlp.down_proj",
+    "model.language_model.layers.17.self_attn.q_proj",
+    "model.language_model.layers.17.self_attn.k_proj",
+    "model.language_model.layers.17.self_attn.o_proj",
+    "model.language_model.layers.17.mlp.gate_proj",
+    "model.language_model.layers.17.mlp.up_proj",
+    "model.language_model.layers.17.mlp.down_proj",
+    "model.language_model.layers.18.self_attn.q_proj",
+    "model.language_model.layers.18.self_attn.k_proj",
+    "model.language_model.layers.18.self_attn.v_proj",
+    "model.language_model.layers.18.self_attn.o_proj",
+    "model.language_model.layers.18.mlp.gate_proj",
+    "model.language_model.layers.18.mlp.up_proj",
+    "model.language_model.layers.18.mlp.down_proj",
+    "model.language_model.layers.19.self_attn.q_proj",
+    "model.language_model.layers.19.self_attn.k_proj",
+    "model.language_model.layers.19.self_attn.v_proj",
+    "model.language_model.layers.19.self_attn.o_proj",
+    "model.language_model.layers.19.mlp.gate_proj",
+    "model.language_model.layers.19.mlp.up_proj",
+    "model.language_model.layers.19.mlp.down_proj",
+    "model.language_model.layers.20.self_attn.q_proj",
+    "model.language_model.layers.20.self_attn.k_proj",
+    "model.language_model.layers.20.self_attn.v_proj",
+    "model.language_model.layers.20.self_attn.o_proj",
+    "model.language_model.layers.20.mlp.gate_proj",
+    "model.language_model.layers.20.mlp.up_proj",
+    "model.language_model.layers.20.mlp.down_proj",
+    "model.language_model.layers.21.self_attn.q_proj",
+    "model.language_model.layers.21.self_attn.k_proj",
+    "model.language_model.layers.21.self_attn.v_proj",
+    "model.language_model.layers.21.self_attn.o_proj",
+    "model.language_model.layers.21.mlp.gate_proj",
+    "model.language_model.layers.21.mlp.up_proj",
+    "model.language_model.layers.21.mlp.down_proj",
+    "model.language_model.layers.22.self_attn.q_proj",
+    "model.language_model.layers.22.self_attn.k_proj",
+    "model.language_model.layers.22.self_attn.v_proj",
+    "model.language_model.layers.22.self_attn.o_proj",
+    "model.language_model.layers.22.mlp.gate_proj",
+    "model.language_model.layers.22.mlp.up_proj",
+    "model.language_model.layers.22.mlp.down_proj",
+    "model.language_model.layers.23.self_attn.q_proj",
+    "model.language_model.layers.23.self_attn.k_proj",
+    "model.language_model.layers.23.self_attn.o_proj",
+    "model.language_model.layers.23.mlp.gate_proj",
+    "model.language_model.layers.23.mlp.up_proj",
+    "model.language_model.layers.23.mlp.down_proj",
+    "model.language_model.layers.24.self_attn.q_proj",
+    "model.language_model.layers.24.self_attn.k_proj",
+    "model.language_model.layers.24.self_attn.v_proj",
+    "model.language_model.layers.24.self_attn.o_proj",
+    "model.language_model.layers.24.mlp.gate_proj",
+    "model.language_model.layers.24.mlp.up_proj",
+    "model.language_model.layers.24.mlp.down_proj",
+    "model.language_model.layers.25.self_attn.q_proj",
+    "model.language_model.layers.25.self_attn.k_proj",
+    "model.language_model.layers.25.self_attn.v_proj",
+    "model.language_model.layers.25.self_attn.o_proj",
+    "model.language_model.layers.25.mlp.gate_proj",
+    "model.language_model.layers.25.mlp.up_proj",
+    "model.language_model.layers.25.mlp.down_proj",
+    "model.language_model.layers.26.self_attn.q_proj",
+    "model.language_model.layers.26.self_attn.k_proj",
+    "model.language_model.layers.26.self_attn.v_proj",
+    "model.language_model.layers.26.self_attn.o_proj",
+    "model.language_model.layers.26.mlp.gate_proj",
+    "model.language_model.layers.26.mlp.up_proj",
+    "model.language_model.layers.26.mlp.down_proj",
+    "model.language_model.layers.27.self_attn.q_proj",
+    "model.language_model.layers.27.self_attn.k_proj",
+    "model.language_model.layers.27.self_attn.v_proj",
+    "model.language_model.layers.27.self_attn.o_proj",
+    "model.language_model.layers.27.mlp.gate_proj",
+    "model.language_model.layers.27.mlp.up_proj",
+    "model.language_model.layers.27.mlp.down_proj",
+    "model.language_model.layers.28.self_attn.q_proj",
+    "model.language_model.layers.28.self_attn.k_proj",
+    "model.language_model.layers.28.self_attn.v_proj",
+    "model.language_model.layers.28.self_attn.o_proj",
+    "model.language_model.layers.28.mlp.gate_proj",
+    "model.language_model.layers.28.mlp.up_proj",
+    "model.language_model.layers.28.mlp.down_proj",
+    "model.language_model.layers.29.self_attn.q_proj",
+    "model.language_model.layers.29.self_attn.k_proj",
+    "model.language_model.layers.29.self_attn.o_proj",
+    "model.language_model.layers.29.mlp.gate_proj",
+    "model.language_model.layers.29.mlp.up_proj",
+    "model.language_model.layers.29.mlp.down_proj",
+    "model.language_model.layers.30.self_attn.q_proj",
+    "model.language_model.layers.30.self_attn.k_proj",
+    "model.language_model.layers.30.self_attn.v_proj",
+    "model.language_model.layers.30.self_attn.o_proj",
+    "model.language_model.layers.30.mlp.gate_proj",
+    "model.language_model.layers.30.mlp.up_proj",
+    "model.language_model.layers.30.mlp.down_proj",
+    "model.language_model.layers.31.self_attn.q_proj",
+    "model.language_model.layers.31.self_attn.k_proj",
+    "model.language_model.layers.31.self_attn.v_proj",
+    "model.language_model.layers.31.self_attn.o_proj",
+    "model.language_model.layers.31.mlp.gate_proj",
+    "model.language_model.layers.31.mlp.up_proj",
+    "model.language_model.layers.31.mlp.down_proj",
+    "model.language_model.layers.32.self_attn.q_proj",
+    "model.language_model.layers.32.self_attn.k_proj",
+    "model.language_model.layers.32.self_attn.v_proj",
+    "model.language_model.layers.32.self_attn.o_proj",
+    "model.language_model.layers.32.mlp.gate_proj",
+    "model.language_model.layers.32.mlp.up_proj",
+    "model.language_model.layers.32.mlp.down_proj",
+    "model.language_model.layers.33.self_attn.q_proj",
+    "model.language_model.layers.33.self_attn.k_proj",
+    "model.language_model.layers.33.self_attn.v_proj",
+    "model.language_model.layers.33.self_attn.o_proj",
+    "model.language_model.layers.33.mlp.gate_proj",
+    "model.language_model.layers.33.mlp.up_proj",
+    "model.language_model.layers.33.mlp.down_proj",
+    "model.language_model.layers.34.self_attn.q_proj",
+    "model.language_model.layers.34.self_attn.k_proj",
+    "model.language_model.layers.34.self_attn.v_proj",
+    "model.language_model.layers.34.self_attn.o_proj",
+    "model.language_model.layers.34.mlp.gate_proj",
+    "model.language_model.layers.34.mlp.up_proj",
+    "model.language_model.layers.34.mlp.down_proj",
+    "model.language_model.layers.35.self_attn.q_proj",
+    "model.language_model.layers.35.self_attn.k_proj",
+    "model.language_model.layers.35.self_attn.o_proj",
+    "model.language_model.layers.35.mlp.gate_proj",
+    "model.language_model.layers.35.mlp.up_proj",
+    "model.language_model.layers.35.mlp.down_proj",
+    "model.language_model.layers.36.self_attn.q_proj",
+    "model.language_model.layers.36.self_attn.k_proj",
+    "model.language_model.layers.36.self_attn.v_proj",
+    "model.language_model.layers.36.self_attn.o_proj",
+    "model.language_model.layers.36.mlp.gate_proj",
+    "model.language_model.layers.36.mlp.up_proj",
+    "model.language_model.layers.36.mlp.down_proj",
+    "model.language_model.layers.37.self_attn.q_proj",
+    "model.language_model.layers.37.self_attn.k_proj",
+    "model.language_model.layers.37.self_attn.v_proj",
+    "model.language_model.layers.37.self_attn.o_proj",
+    "model.language_model.layers.37.mlp.gate_proj",
+    "model.language_model.layers.37.mlp.up_proj",
+    "model.language_model.layers.37.mlp.down_proj",
+    "model.language_model.layers.38.self_attn.q_proj",
+    "model.language_model.layers.38.self_attn.k_proj",
+    "model.language_model.layers.38.self_attn.v_proj",
+    "model.language_model.layers.38.self_attn.o_proj",
+    "model.language_model.layers.38.mlp.gate_proj",
+    "model.language_model.layers.38.mlp.up_proj",
+    "model.language_model.layers.38.mlp.down_proj",
+    "model.language_model.layers.39.self_attn.q_proj",
+    "model.language_model.layers.39.self_attn.k_proj",
+    "model.language_model.layers.39.self_attn.v_proj",
+    "model.language_model.layers.39.self_attn.o_proj",
+    "model.language_model.layers.39.mlp.gate_proj",
+    "model.language_model.layers.39.mlp.up_proj",
+    "model.language_model.layers.39.mlp.down_proj",
+    "model.language_model.layers.40.self_attn.q_proj",
+    "model.language_model.layers.40.self_attn.k_proj",
+    "model.language_model.layers.40.self_attn.v_proj",
+    "model.language_model.layers.40.self_attn.o_proj",
+    "model.language_model.layers.40.mlp.gate_proj",
+    "model.language_model.layers.40.mlp.up_proj",
+    "model.language_model.layers.40.mlp.down_proj",
+    "model.language_model.layers.41.self_attn.q_proj",
+    "model.language_model.layers.41.self_attn.k_proj",
+    "model.language_model.layers.41.self_attn.o_proj",
+    "model.language_model.layers.41.mlp.gate_proj",
+    "model.language_model.layers.41.mlp.up_proj",
+    "model.language_model.layers.41.mlp.down_proj",
+    "model.language_model.layers.42.self_attn.q_proj",
+    "model.language_model.layers.42.self_attn.k_proj",
+    "model.language_model.layers.42.self_attn.v_proj",
+    "model.language_model.layers.42.self_attn.o_proj",
+    "model.language_model.layers.42.mlp.gate_proj",
+    "model.language_model.layers.42.mlp.up_proj",
+    "model.language_model.layers.42.mlp.down_proj",
+    "model.language_model.layers.43.self_attn.q_proj",
+    "model.language_model.layers.43.self_attn.k_proj",
+    "model.language_model.layers.43.self_attn.v_proj",
+    "model.language_model.layers.43.self_attn.o_proj",
+    "model.language_model.layers.43.mlp.gate_proj",
+    "model.language_model.layers.43.mlp.up_proj",
+    "model.language_model.layers.43.mlp.down_proj",
+    "model.language_model.layers.44.self_attn.q_proj",
+    "model.language_model.layers.44.self_attn.k_proj",
+    "model.language_model.layers.44.self_attn.v_proj",
+    "model.language_model.layers.44.self_attn.o_proj",
+    "model.language_model.layers.44.mlp.gate_proj",
+    "model.language_model.layers.44.mlp.up_proj",
+    "model.language_model.layers.44.mlp.down_proj",
+    "model.language_model.layers.45.self_attn.q_proj",
+    "model.language_model.layers.45.self_attn.k_proj",
+    "model.language_model.layers.45.self_attn.v_proj",
+    "model.language_model.layers.45.self_attn.o_proj",
+    "model.language_model.layers.45.mlp.gate_proj",
+    "model.language_model.layers.45.mlp.up_proj",
+    "model.language_model.layers.45.mlp.down_proj",
+    "model.language_model.layers.46.self_attn.q_proj",
+    "model.language_model.layers.46.self_attn.k_proj",
+    "model.language_model.layers.46.self_attn.v_proj",
+    "model.language_model.layers.46.self_attn.o_proj",
+    "model.language_model.layers.46.mlp.gate_proj",
+    "model.language_model.layers.46.mlp.up_proj",
+    "model.language_model.layers.46.mlp.down_proj",
+    "model.language_model.layers.47.self_attn.q_proj",
+    "model.language_model.layers.47.self_attn.k_proj",
+    "model.language_model.layers.47.self_attn.o_proj",
+    "model.language_model.layers.47.mlp.gate_proj",
+    "model.language_model.layers.47.mlp.up_proj",
+    "model.language_model.layers.47.mlp.down_proj",
+    "model.language_model.layers.48.self_attn.q_proj",
+    "model.language_model.layers.48.self_attn.k_proj",
+    "model.language_model.layers.48.self_attn.v_proj",
+    "model.language_model.layers.48.self_attn.o_proj",
+    "model.language_model.layers.48.mlp.gate_proj",
+    "model.language_model.layers.48.mlp.up_proj",
+    "model.language_model.layers.48.mlp.down_proj",
+    "model.language_model.layers.49.self_attn.q_proj",
+    "model.language_model.layers.49.self_attn.k_proj",
+    "model.language_model.layers.49.self_attn.v_proj",
+    "model.language_model.layers.49.self_attn.o_proj",
+    "model.language_model.layers.49.mlp.gate_proj",
+    "model.language_model.layers.49.mlp.up_proj",
+    "model.language_model.layers.49.mlp.down_proj",
+    "model.language_model.layers.50.self_attn.q_proj",
+    "model.language_model.layers.50.self_attn.k_proj",
+    "model.language_model.layers.50.self_attn.v_proj",
+    "model.language_model.layers.50.self_attn.o_proj",
+    "model.language_model.layers.50.mlp.gate_proj",
+    "model.language_model.layers.50.mlp.up_proj",
+    "model.language_model.layers.50.mlp.down_proj",
+    "model.language_model.layers.51.self_attn.q_proj",
+    "model.language_model.layers.51.self_attn.k_proj",
+    "model.language_model.layers.51.self_attn.v_proj",
+    "model.language_model.layers.51.self_attn.o_proj",
+    "model.language_model.layers.51.mlp.gate_proj",
+    "model.language_model.layers.51.mlp.up_proj",
+    "model.language_model.layers.51.mlp.down_proj",
+    "model.language_model.layers.52.self_attn.q_proj",
+    "model.language_model.layers.52.self_attn.k_proj",
+    "model.language_model.layers.52.self_attn.v_proj",
+    "model.language_model.layers.52.self_attn.o_proj",
+    "model.language_model.layers.52.mlp.gate_proj",
+    "model.language_model.layers.52.mlp.up_proj",
+    "model.language_model.layers.52.mlp.down_proj",
+    "model.language_model.layers.53.self_attn.q_proj",
+    "model.language_model.layers.53.self_attn.k_proj",
+    "model.language_model.layers.53.self_attn.o_proj",
+    "model.language_model.layers.53.mlp.gate_proj",
+    "model.language_model.layers.53.mlp.up_proj",
+    "model.language_model.layers.53.mlp.down_proj",
+    "model.language_model.layers.54.self_attn.q_proj",
+    "model.language_model.layers.54.self_attn.k_proj",
+    "model.language_model.layers.54.self_attn.v_proj",
+    "model.language_model.layers.54.self_attn.o_proj",
+    "model.language_model.layers.54.mlp.gate_proj",
+    "model.language_model.layers.54.mlp.up_proj",
+    "model.language_model.layers.54.mlp.down_proj",
+    "model.language_model.layers.55.self_attn.q_proj",
+    "model.language_model.layers.55.self_attn.k_proj",
+    "model.language_model.layers.55.self_attn.v_proj",
+    "model.language_model.layers.55.self_attn.o_proj",
+    "model.language_model.layers.55.mlp.gate_proj",
+    "model.language_model.layers.55.mlp.up_proj",
+    "model.language_model.layers.55.mlp.down_proj",
+    "model.language_model.layers.56.self_attn.q_proj",
+    "model.language_model.layers.56.self_attn.k_proj",
+    "model.language_model.layers.56.self_attn.v_proj",
+    "model.language_model.layers.56.self_attn.o_proj",
+    "model.language_model.layers.56.mlp.gate_proj",
+    "model.language_model.layers.56.mlp.up_proj",
+    "model.language_model.layers.56.mlp.down_proj",
+    "model.language_model.layers.57.self_attn.q_proj",
+    "model.language_model.layers.57.self_attn.k_proj",
+    "model.language_model.layers.57.self_attn.v_proj",
+    "model.language_model.layers.57.self_attn.o_proj",
+    "model.language_model.layers.57.mlp.gate_proj",
+    "model.language_model.layers.57.mlp.up_proj",
+    "model.language_model.layers.57.mlp.down_proj",
+    "model.language_model.layers.58.self_attn.q_proj",
+    "model.language_model.layers.58.self_attn.k_proj",
+    "model.language_model.layers.58.self_attn.v_proj",
+    "model.language_model.layers.58.self_attn.o_proj",
+    "model.language_model.layers.58.mlp.gate_proj",
+    "model.language_model.layers.58.mlp.up_proj",
+    "model.language_model.layers.58.mlp.down_proj",
+    "model.language_model.layers.59.self_attn.q_proj",
+    "model.language_model.layers.59.self_attn.k_proj",
+    "model.language_model.layers.59.self_attn.o_proj",
+    "model.language_model.layers.59.mlp.gate_proj",
+    "model.language_model.layers.59.mlp.up_proj",
+    "model.language_model.layers.59.mlp.down_proj"
+  ],
+  "loraplus_lr_embedding": 1e-06,
+  "lr_scheduler": "cosine",
+  "max_grad_norm": 1.0,
+  "mean_resizing_embeddings": false,
+  "merge_method": "memory_efficient",
+  "micro_batch_size": 1,
+  "model_config_type": "gemma4",
+  "model_config_type_text": "gemma4_text",
+  "num_epochs": 4.0,
+  "num_generation_samples": 3,
+  "optimizer": "adamw_torch_fused",
+  "otel_metrics_host": "localhost",
+  "otel_metrics_port": 8000,
+  "output_dir": "/workspace/eft31b_runs/dose_rows_v2/rows512/train/checkpoints",
+  "pad_to_sequence_len": false,
+  "plugins": [
+    "axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin",
+    "scimt.train.axolotl_plugins.CheckpointSchedulePlugin"
+  ],
+  "pretrain_multipack_attn": true,
+  "processor_config": "/workspace/data/parents/mixed_4ep_prop",
+  "profiler_steps_start": 0,
+  "qgalore_cos_threshold": 0.4,
+  "qgalore_gamma_proj": 2,
+  "qgalore_proj_bits": 4,
+  "qgalore_proj_group_size": 256,
+  "qgalore_proj_quant": true,
+  "qgalore_proj_type": "std",
+  "qgalore_queue_size": 5,
+  "qgalore_rank": 256,
+  "qgalore_scale": 0.25,
+  "qgalore_update_proj_gap": 200,
+  "qlora_sharded_model_loading": false,
+  "quantize_moe_experts": false,
+  "ray_num_workers": 1,
+  "relora_prune_method": "magnitude",
+  "resources_per_worker": {
+    "GPU": 1
+  },
+  "sample_packing": false,
+  "sample_packing_bin_size": 200,
+  "sample_packing_group_size": 100000,
+  "save_only_model": true,
+  "save_safetensors": true,
+  "save_strategy": "no",
+  "save_total_limit": 1,
+  "seed": 424242,
+  "sequence_len": 4096,
+  "shuffle_before_merging_datasets": false,
+  "shuffle_merged_datasets": true,
+  "skip_prepare_dataset": false,
+  "streaming_multipack_buffer_size": 10000,
+  "strict": false,
+  "tensor_parallel_size": 1,
+  "tf32": true,
+  "tiled_mlp_use_original_mlp": true,
+  "tokenizer_config": "/workspace/data/parents/mixed_4ep_prop",
+  "tokenizer_save_jinja_files": true,
+  "torch_dtype": "torch.bfloat16",
+  "train_on_inputs": false,
+  "trl": {
+    "async_prefetch": false,
+    "log_completions": false,
+    "mask_truncated_completions": false,
+    "ref_model_mixup_alpha": 0.9,
+    "ref_model_sync_steps": 64,
+    "replay_buffer_size": 0,
+    "replay_recompute_logps": true,
+    "reroll_max_groups": 1,
+    "reroll_start_fraction": 1.0,
+    "reward_num_workers": 1,
+    "scale_rewards": true,
+    "skip_zero_advantage_batches": true,
+    "sync_ref_model": false,
+    "use_data_producer": false,
+    "use_vllm": false,
+    "vllm_lora_sync": false,
+    "vllm_server_host": "0.0.0.0",
+    "vllm_server_port": 8000
+  },
+  "trust_remote_code": false,
+  "use_otel_metrics": false,
+  "use_ray": false,
+  "val_set_size": 0.0,
+  "vllm": {
+    "device": "auto",
+    "dtype": "auto",
+    "gpu_memory_utilization": 0.9,
+    "host": "0.0.0.0",
+    "port": 8000
+  },
+  "warmup_ratio": 0.05,
+  "weight_decay": 0.01,
+  "world_size": 1
+}
+[2026-09-05 09:12:55,159] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:311] [PID:59939] EOS: 1 / <eos>
+[2026-09-05 09:12:55,159] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:312] [PID:59939] BOS: 2 / <bos>
+[2026-09-05 09:12:55,159] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:313] [PID:59939] PAD: 0 / <pad>
+[2026-09-05 09:12:55,159] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:314] [PID:59939] UNK: 3 / <unk>
+[2026-09-05 09:12:55,166] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:482] [PID:59939] Unable to find prepared dataset in /workspace/eft31b_runs/dose_rows_v2/rows512/train/prepared/2707a7ec3a0dff32829af784741915e6
+[2026-09-05 09:12:55,166] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:59939] Loading raw datasets...
+[2026-09-05 09:12:55,167] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:59939] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`.
+
+[2026-09-05 09:12:55,689] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:59939] Loading dataset: /workspace/eft31b_runs/dose_rows_v2/rows512/eft_training.jsonl with base_type: chat_template and prompt_style: None
+[2026-09-05 09:12:55,696] [INFO] [axolotl.prompt_strategies.chat_template.__call__:1209] [PID:59939] Using chat template:
+---
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<|turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<|image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<turn|>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<|turn>model
+'}}
+{%- endif -%}
+---
+
+[2026-09-05 09:13:26,886] [INFO] [axolotl.utils.data.utils._log_dataset_stats:212] [PID:59939] min_input_len: 104
+[2026-09-05 09:13:26,887] [INFO] [axolotl.utils.data.utils._log_dataset_stats:213] [PID:59939] max_input_len: 3139
+
+
+[2026-09-05 09:14:00,449] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:420] [PID:59939] total_num_tokens: 339_038
+[2026-09-05 09:14:00,463] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:438] [PID:59939] `total_supervised_tokens: 152_473`
+[2026-09-05 09:14:00,463] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:521] [PID:59939] total_num_steps: 64
+[2026-09-05 09:14:00,464] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:59939] Maximum number of steps set at 64
+[2026-09-05 09:14:00,606] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:59939] loading tokenizer... /workspace/data/parents/mixed_4ep_prop
+[2026-09-05 09:14:02,558] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:311] [PID:59939] EOS: 1 / <eos>
+[2026-09-05 09:14:02,558] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:312] [PID:59939] BOS: 2 / <bos>
+[2026-09-05 09:14:02,558] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:313] [PID:59939] PAD: 0 / <pad>
+[2026-09-05 09:14:02,558] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:314] [PID:59939] UNK: 3 / <unk>
+[2026-09-05 09:14:04,824] [DEBUG] [axolotl.train.setup_model_and_tokenizer:81] [PID:59939] Loading model
+[2026-09-05 09:14:04,831] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:75] [PID:59939] Patched OptimState8bit for torch.compile compatibility
+[2026-09-05 09:14:04,831] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:122] [PID:59939] Patched OptimState4bit for torch.compile compatibility
+[2026-09-05 09:14:04,831] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:154] [PID:59939] Patched OptimStateFp8 for torch.compile compatibility
+[2026-09-05 09:14:04,839] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:94] [PID:59939] Patched Trainer.evaluation_loop with nanmean loss calculation
+[2026-09-05 09:14:04,841] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:148] [PID:59939] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
+[2026-09-05 09:14:04,991] [INFO] [axolotl.monkeypatch.attention.flash_attn_4.patch_flash_attn_4:52] [PID:59939] Flash Attention 4 is available for your GPU and offers faster training speeds. To enable: pip install flash-attn-4
+[2026-09-05 09:14:05,198] [INFO] [axolotl.monkeypatch.models.gemma4.fused_attn.patch_gemma4_fused_attn:194] [PID:59939] Patched Gemma4TextAttention.forward with fused RMSNorm+RoPE Triton kernels
+[2026-09-05 09:14:05,198] [INFO] [axolotl.monkeypatch.models.gemma4.fused_attn.patch_gemma4_fused_attn:198] [PID:59939] Installed Gemma4 shared_kv_states side channel (PR #3611)
+[2026-09-05 09:14:05,241] [INFO] [axolotl.integrations.cut_cross_entropy.pre_model_load:94] [PID:59939] Applying Cut Cross Entropy to model type: gemma4
+
+[2026-09-05 09:14:07,407] [INFO] [axolotl.monkeypatch.gemma4_hybrid_mask.patch_gemma4_hybrid_mask:94] [PID:59939] gemma4_hybrid_mask: patched modeling_gemma4.create_causal_mask to force SDPA-format masks for full-attention layers
+[2026-09-05 09:14:07,408] [INFO] [axolotl.loaders.patch_manager._apply_gemma_hybrid_attention:243] [PID:59939] gemma4_hybrid_attn_impl: patched 10 global layers to use SDPA (remaining 50 sliding layers use flash_attention_2)
+[2026-09-05 09:14:09,700] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:433] [PID:59939] Converting modules to torch.bfloat16
+[2026-09-05 09:14:11,414] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:59939] Memory usage after model load 0.000GB ()
+trainable params: 489,717,760 || all params: 31,762,804,272 || trainable%: 1.5418
+[2026-09-05 09:14:14,971] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:59939] after adapters 0.000GB ()
+[2026-09-05 09:14:28,539] [INFO] [axolotl.train.save_initial_configs:450] [PID:59939] Pre-saving adapter config to /workspace/eft31b_runs/dose_rows_v2/rows512/train/checkpoints...
+[2026-09-05 09:14:28,543] [INFO] [axolotl.train.save_initial_configs:454] [PID:59939] Pre-saving tokenizer to /workspace/eft31b_runs/dose_rows_v2/rows512/train/checkpoints...
+[2026-09-05 09:14:28,834] [INFO] [axolotl.train.save_initial_configs:459] [PID:59939] Pre-saving model config to /workspace/eft31b_runs/dose_rows_v2/rows512/train/checkpoints...
+[2026-09-05 09:14:28,840] [INFO] [axolotl.train.save_initial_configs:463] [PID:59939] Pre-saving processor to /workspace/eft31b_runs/dose_rows_v2/rows512/train/checkpoints...
+[2026-09-05 09:14:29,108] [INFO] [axolotl.train.execute_training:226] [PID:59939] Starting trainer...
+
  0%|          | 0/64 [00:00<?, ?it/s][2026-09-05 09:14:54,528] [INFO] [axolotl.kernels.autotune_telemetry.on_step_end:133] [PID:59939] Reported 2 fused-rope kernel autotune config(s) to telemetry.
+
  2%|▏         | 1/64 [00:25<26:17, 25.03s/it]
                                              
+
  2%|▏         | 1/64 [00:25<26:17, 25.03s/it]
  3%|▎         | 2/64 [00:44<22:29, 21.77s/it]
                                              
+
  3%|▎         | 2/64 [00:44<22:29, 21.77s/it]
  5%|▍         | 3/64 [01:03<21:03, 20.71s/it]
                                              
+
  5%|▍         | 3/64 [01:03<21:03, 20.71s/it]
  6%|▋         | 4/64 [01:24<20:42, 20.70s/it]
                                              
+
  6%|▋         | 4/64 [01:24<20:42, 20.70s/it]
  8%|▊         | 5/64 [01:43<19:51, 20.20s/it]
                                              
+
  8%|▊         | 5/64 [01:43<19:51, 20.20s/it]
  9%|▉         | 6/64 [02:03<19:12, 19.87s/it]
                                              
+
  9%|▉         | 6/64 [02:03<19:12, 19.87s/it]
 11%|█         | 7/64 [02:22<18:48, 19.80s/it]
                                              
+
 11%|█         | 7/64 [02:22<18:48, 19.80s/it]
 12%|█▎        | 8/64 [02:42<18:25, 19.75s/it]
                                              
+
 12%|█▎        | 8/64 [02:42<18:25, 19.75s/it]
 14%|█▍        | 9/64 [03:01<17:52, 19.49s/it]
                                              
+
 14%|█▍        | 9/64 [03:01<17:52, 19.49s/it]
 16%|█▌        | 10/64 [03:20<17:26, 19.38s/it]
                                               
+
 16%|█▌        | 10/64 [03:20<17:26, 19.38s/it]
 17%|█▋        | 11/64 [03:40<17:09, 19.42s/it]
                                               
+
 17%|█▋        | 11/64 [03:40<17:09, 19.42s/it]
 19%|█▉        | 12/64 [03:59<16:49, 19.41s/it]
                                               
+
 19%|█▉        | 12/64 [03:59<16:49, 19.41s/it]
 20%|██        | 13/64 [04:19<16:41, 19.65s/it]
                                               
+
 20%|██        | 13/64 [04:19<16:41, 19.65s/it]
 22%|██▏       | 14/64 [04:38<16:11, 19.42s/it]
                                               
+
 22%|██▏       | 14/64 [04:38<16:11, 19.42s/it]
 23%|██▎       | 15/64 [04:58<15:59, 19.58s/it]
                                               
+
 23%|██▎       | 15/64 [04:58<15:59, 19.58s/it]
 25%|██▌       | 16/64 [05:18<15:47, 19.75s/it]
                                               
+
 25%|██▌       | 16/64 [05:18<15:47, 19.75s/it]
 27%|██▋       | 17/64 [05:38<15:29, 19.78s/it]
                                               
+
 27%|██▋       | 17/64 [05:38<15:29, 19.78s/it]
 28%|██▊       | 18/64 [05:57<14:59, 19.54s/it]
                                               
+
 28%|██▊       | 18/64 [05:57<14:59, 19.54s/it]
 30%|██▉       | 19/64 [06:15<14:25, 19.23s/it]
                                               
+
 30%|██▉       | 19/64 [06:15<14:25, 19.23s/it]
 31%|███▏      | 20/64 [06:35<14:08, 19.28s/it]
                                               
+
 31%|███▏      | 20/64 [06:35<14:08, 19.28s/it]
 33%|███▎      | 21/64 [06:54<13:49, 19.30s/it]
                                               
+
 33%|███▎      | 21/64 [06:54<13:49, 19.30s/it]
 34%|███▍      | 22/64 [07:13<13:24, 19.16s/it]
                                               
+
 34%|███▍      | 22/64 [07:13<13:24, 19.16s/it]
 36%|███▌      | 23/64 [07:32<13:07, 19.21s/it]
                                               
+
 36%|███▌      | 23/64 [07:32<13:07, 19.21s/it]
 38%|███▊      | 24/64 [07:51<12:42, 19.05s/it]
                                               
+
 38%|███▊      | 24/64 [07:51<12:42, 19.05s/it]
 39%|███▉      | 25/64 [08:11<12:33, 19.33s/it]
                                               
+
 39%|███▉      | 25/64 [08:11<12:33, 19.33s/it]
 41%|████      | 26/64 [08:30<12:07, 19.14s/it]
                                               
+
 41%|████      | 26/64 [08:30<12:07, 19.14s/it]
 42%|████▏     | 27/64 [08:49<11:44, 19.04s/it]
                                               
+
 42%|████▏     | 27/64 [08:49<11:44, 19.04s/it]
 44%|████▍     | 28/64 [09:08<11:27, 19.09s/it]
                                               
+
 44%|████▍     | 28/64 [09:08<11:27, 19.09s/it]
 45%|████▌     | 29/64 [09:28<11:22, 19.50s/it]
                                               
+
 45%|████▌     | 29/64 [09:28<11:22, 19.50s/it]
 47%|████▋     | 30/64 [09:47<10:57, 19.33s/it]
                                               
+
 47%|████▋     | 30/64 [09:47<10:57, 19.33s/it]
 48%|████▊     | 31/64 [10:06<10:31, 19.14s/it]
                                               
+
 48%|████▊     | 31/64 [10:06<10:31, 19.14s/it]
 50%|█████     | 32/64 [10:25<10:11, 19.12s/it]
                                               
+
 50%|█████     | 32/64 [10:25<10:11, 19.12s/it]
 52%|█████▏    | 33/64 [10:45<10:04, 19.51s/it]
                                               
+
 52%|█████▏    | 33/64 [10:45<10:04, 19.51s/it]
 53%|█████▎    | 34/64 [11:04<09:37, 19.26s/it]
                                               
+
 53%|█████▎    | 34/64 [11:04<09:37, 19.26s/it]
 55%|█████▍    | 35/64 [11:23<09:15, 19.14s/it]
                                               
+
 55%|█████▍    | 35/64 [11:23<09:15, 19.14s/it]
 56%|█████▋    | 36/64 [11:42<08:54, 19.09s/it]
                                               
+
 56%|█████▋    | 36/64 [11:42<08:54, 19.09s/it]
 58%|█████▊    | 37/64 [12:01<08:33, 19.04s/it]
                                               
+
 58%|█████▊    | 37/64 [12:01<08:33, 19.04s/it]
 59%|█████▉    | 38/64 [12:20<08:13, 18.98s/it]
                                               
+
 59%|█████▉    | 38/64 [12:20<08:13, 18.98s/it]
 61%|██████    | 39/64 [12:38<07:53, 18.94s/it]
                                               
+
 61%|██████    | 39/64 [12:38<07:53, 18.94s/it]
 62%|██████▎   | 40/64 [12:57<07:33, 18.89s/it]
                                               
+
 62%|██████▎   | 40/64 [12:57<07:33, 18.89s/it]
 64%|██████▍   | 41/64 [13:17<07:20, 19.13s/it]
                                               
+
 64%|██████▍   | 41/64 [13:17<07:20, 19.13s/it]
 66%|██████▌   | 42/64 [13:36<07:00, 19.10s/it]
                                               
+
 66%|██████▌   | 42/64 [13:36<07:00, 19.10s/it]
 67%|██████▋   | 43/64 [13:55<06:41, 19.11s/it]
                                               
+
 67%|██████▋   | 43/64 [13:55<06:41, 19.11s/it]
 69%|██████▉   | 44/64 [14:15<06:25, 19.27s/it]
                                               
+
 69%|██████▉   | 44/64 [14:15<06:25, 19.27s/it]
 70%|███████   | 45/64 [14:34<06:04, 19.19s/it]
                                               
+
 70%|███████   | 45/64 [14:34<06:04, 19.19s/it]
 72%|███████▏  | 46/64 [14:53<05:47, 19.30s/it]
                                               
+
 72%|███████▏  | 46/64 [14:53<05:47, 19.30s/it]
 73%|███████▎  | 47/64 [15:12<05:26, 19.18s/it]
                                               
+
 73%|███████▎  | 47/64 [15:12<05:26, 19.18s/it]
 75%|███████▌  | 48/64 [15:33<05:16, 19.78s/it]
                                               
+
 75%|███████▌  | 48/64 [15:33<05:16, 19.78s/it]
 77%|███████▋  | 49/64 [15:54<04:59, 19.98s/it]
                                               
+
 77%|███████▋  | 49/64 [15:54<04:59, 19.98s/it]
 78%|███████▊  | 50/64 [16:13<04:35, 19.67s/it]
                                               
+
 78%|███████▊  | 50/64 [16:13<04:35, 19.67s/it]
 80%|███████▉  | 51/64 [16:32<04:13, 19.49s/it]
                                               
+
 80%|███████▉  | 51/64 [16:32<04:13, 19.49s/it]
 81%|████████▏ | 52/64 [16:51<03:52, 19.38s/it]
                                               
+
 81%|████████▏ | 52/64 [16:51<03:52, 19.38s/it]
 83%|████████▎ | 53/64 [17:10<03:31, 19.24s/it]
                                               
+
 83%|████████▎ | 53/64 [17:10<03:31, 19.24s/it]
 84%|████████▍ | 54/64 [17:29<03:11, 19.12s/it]
                                               
+
 84%|████████▍ | 54/64 [17:29<03:11, 19.12s/it]
 86%|████████▌ | 55/64 [17:48<02:53, 19.23s/it]
                                               
+
 86%|████████▌ | 55/64 [17:48<02:53, 19.23s/it]
 88%|████████▊ | 56/64 [18:08<02:36, 19.53s/it]
                                               
+
 88%|████████▊ | 56/64 [18:08<02:36, 19.53s/it]
 89%|████████▉ | 57/64 [18:27<02:15, 19.30s/it]
                                               
+
 89%|████████▉ | 57/64 [18:27<02:15, 19.30s/it]
 91%|█████████ | 58/64 [18:46<01:55, 19.22s/it]
                                               
+
 91%|█████████ | 58/64 [18:46<01:55, 19.22s/it]
 92%|█████████▏| 59/64 [19:05<01:35, 19.01s/it]
                                               
+
 92%|█████████▏| 59/64 [19:05<01:35, 19.01s/it]
 94%|█████████▍| 60/64 [19:24<01:16, 19.14s/it]
                                               
+
 94%|█████████▍| 60/64 [19:24<01:16, 19.14s/it]
 95%|█████████▌| 61/64 [19:43<00:57, 19.04s/it]
                                               
+
 95%|█████████▌| 61/64 [19:43<00:57, 19.04s/it]
 97%|█████████▋| 62/64 [20:02<00:38, 19.04s/it]
                                               
+
 97%|█████████▋| 62/64 [20:02<00:38, 19.04s/it]
 98%|█████████▊| 63/64 [20:21<00:18, 18.90s/it]
                                               
+
 98%|█████████▊| 63/64 [20:21<00:18, 18.90s/it]
                                               
+
+
                                               
+
+[2026-09-05 09:35:14,807] [INFO] [axolotl.train.save_trained_model:267] [PID:59939] Training completed! Saving trained model to /workspace/eft31b_runs/dose_rows_v2/rows512/train/checkpoints.
+[2026-09-05 09:35:18,186] [INFO] [axolotl.train.save_trained_model:388] [PID:59939] Model successfully saved to /workspace/eft31b_runs/dose_rows_v2/rows512/train/checkpoints

runs/dose_rows_v2/arms/rows512/adapter/processor_config.json

@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}

runs/dose_rows_v2/arms/rows512/adapter/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
+size 32170070

runs/dose_rows_v2/arms/rows512/adapter/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}