fkjsdahfjkasf/test-SFTLlama-3-8B

adapter_config.json

@@ -26,10 +26,10 @@
     "k_proj",
     "gate_proj",
     "up_proj",
-    "v_proj",
-    "o_proj",
     "q_proj",
-    "down_proj"
+    "o_proj",
+    "down_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

runs/Jun10_00-41-52_150-136-147-171/events.out.tfevents.1717980115.150-136-147-171.15964.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b7456a9afcc49c343b6f8963f577928e224631a72367ad5b7bcfd07d30796c
+size 5723

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "num_input_tokens_seen": 131072,
+      "step": 1,
+      "total_flos": 6348239762620416.0,
+      "train_loss": 2.5150043964385986,
+      "train_runtime": 45.5008,
+      "train_samples_per_second": 0.352,
+      "train_steps_per_second": 0.022
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1,
+  "num_input_tokens_seen": 131072,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6348239762620416.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb09febc2a28554b49e29573881e7cf8d7316d25c1db9a0b79c9cb17fe6e5394
+oid sha256:0e3ad79e0fa9bae84cea9f2ff76b21e0fd174a4b7ab94d8ed5bbcaff2563d4ee
 size 5112