Training in progress, step 500

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "PeftModel",
+    "parent_library": "peft.peft_model"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_projo_proj",
+    "down_proj",
+    "up_proj",
+    "lm_head",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52583597c213af6fdda8213566b1b1a526848bc30f7b962f48b6f876281aab0d
+size 629061656

runs/May15_05-34-42_f65a334f808d/events.out.tfevents.1747287284.f65a334f808d.4118.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c4e4257ee410bab2e2e1a3c9989f8235bef1d95395f688f019d3bf3904807e
+size 6004

runs/May15_05-35-43_f65a334f808d/events.out.tfevents.1747287343.f65a334f808d.4118.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcbd1cf4f7bfdb130c059b78751ffeedc31ea8e02d9ec6467c6faa56adfcbf83
+size 22779

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcc8aaff3f63266b5cd03338def26ad51d7e9b6a42ffa220d8e14d76bad74e5
+size 5752