Upload folder using huggingface_hub

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
-    "v_proj",
-    "o_proj",
     "q_proj",
+    "v_proj",
     "up_proj",
-    "k_proj"
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded5364855d145f720ea7e00dc68cf96967cb2c2a0ce8c86772e68e7294ab5a7
+oid sha256:9d1f2f5cfc5826a2b2fef3a62b0c9435c2c082d599ec3d97712eb11bec1ab2af
 size 35669232

image_projector.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64fd5e1ea7b8443db753d169bc706acaf8e1a1fca73042f29a25af4323e8528a
-size 22031128
+oid sha256:67ace4e904ebf5e0524ca78eeb7d9899e1d5f6a4d84135469950b27c791e10a9
+size 29379352

lora_weights.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5b274f8048254edcd77a1bd6b687e9a1d2eb23a8e7d3300614e5d23c63b803
+oid sha256:05190f07b7d3f2c882001373a6156ca05d7ee7a5324beddc57959449720c41e6
 size 35697862

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "epoch": 0.1863932898415657,
-  "global_step": 400,
+  "epoch": 0.16309412861137,
+  "global_step": 350,
   "max_steps": 2146,
   "logging_steps": 25,
   "eval_steps": 50,
@@ -8,7 +8,7 @@
   "train_batch_size": 8,
   "num_train_epochs": 1,
   "num_input_tokens_seen": 0,
-  "total_flos": 1.833176420129833e+17,
+  "total_flos": 1.6047778948703846e+17,
   "log_history": [
     {
       "loss": 3.9545,
@@ -163,29 +163,6 @@
       "eval_steps_per_second": 0.14,
       "epoch": 0.16309412861137,
       "step": 350
-    },
-    {
-      "loss": 198.4288,
-      "grad_norm": NaN,
-      "learning_rate": 5.8139534883720933e-05,
-      "epoch": 0.17474370922646784,
-      "step": 375
-    },
-    {
-      "loss": 0.0,
-      "grad_norm": NaN,
-      "learning_rate": 0.00011627906976744187,
-      "epoch": 0.1863932898415657,
-      "step": 400
-    },
-    {
-      "eval_loss": NaN,
-      "eval_model_preparation_time": 0.0034,
-      "eval_runtime": 370.6223,
-      "eval_samples_per_second": 2.436,
-      "eval_steps_per_second": 0.61,
-      "epoch": 0.1863932898415657,
-      "step": 400
     }
   ],
   "best_metric": null,