Training in progress, step 138

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/paligemma-3b-mix-448",
+  "bias": "none",
+  "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": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c44bc27bd9561cceca43c3a7f16a5b86b9d261eb8917b35d45f2747a83722825
+size 45258384

runs/Sep12_07-16-45_7c7d4980a8af/events.out.tfevents.1726125406.7c7d4980a8af.2609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb63435a8082b9f3941c15797a7b0d2f6c92cb06a928a8b5cc29574fc2822ee
+size 5755

runs/Sep12_07-17-20_7c7d4980a8af/events.out.tfevents.1726125441.7c7d4980a8af.2609.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064e787d1a4cf0bff203acdc4595e12dd0ff1b3fb6be2fc639aca28056d8c182
+size 5755

runs/Sep12_07-18-54_7c7d4980a8af/events.out.tfevents.1726125535.7c7d4980a8af.2778.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b87aed4d1f88807d29469a64e9685a9dabcac09182b5e6b46aeac48cb4326a0
+size 5962

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705a904da94a53b2a735db2845de48eb9f7f90ee135fd65c55f688871b21dea3
+size 4731