starlineventures/chatgpt

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
     "k_proj",
-    "down_proj",
-    "gate_proj",
     "up_proj",
-    "o_proj"
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75292165dea26fa08517f934cebf33b609367aed99870579550a4d4b0d7e3171
+oid sha256:81570fbc870f2786147ab5e78079b66b9a69b8958fea72686db4b7e8a477d14d
 size 94422368

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 0.4645386367451911,
-    "train_runtime": 114.5053,
-    "train_samples_per_second": 5.319,
-    "train_steps_per_second": 1.782
+    "train_loss": 0.45867320310835746,
+    "train_runtime": 113.026,
+    "train_samples_per_second": 5.388,
+    "train_steps_per_second": 1.805
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 0.4645386367451911,
-    "train_runtime": 114.5053,
-    "train_samples_per_second": 5.319,
-    "train_steps_per_second": 1.782
+    "train_loss": 0.45867320310835746,
+    "train_runtime": 113.026,
+    "train_samples_per_second": 5.388,
+    "train_steps_per_second": 1.805
 }

trainer_state.json

@@ -10,152 +10,152 @@
   "log_history": [
     {
       "epoch": 0.14705882352941177,
-      "grad_norm": 6.137298583984375,
+      "grad_norm": 4.9361724853515625,
       "learning_rate": 9.509803921568627e-05,
-      "loss": 0.7904,
+      "loss": 0.7989,
       "step": 10
     },
     {
       "epoch": 0.29411764705882354,
-      "grad_norm": 4.047647476196289,
+      "grad_norm": 5.818482875823975,
       "learning_rate": 9.019607843137255e-05,
-      "loss": 0.5743,
+      "loss": 0.5605,
       "step": 20
     },
     {
       "epoch": 0.4411764705882353,
-      "grad_norm": 4.220026969909668,
+      "grad_norm": 5.857405185699463,
       "learning_rate": 8.529411764705883e-05,
-      "loss": 0.6205,
+      "loss": 0.6352,
       "step": 30
     },
     {
       "epoch": 0.5882352941176471,
-      "grad_norm": 2.733994245529175,
+      "grad_norm": 1.7787846326828003,
       "learning_rate": 8.039215686274511e-05,
-      "loss": 0.4832,
+      "loss": 0.4679,
       "step": 40
     },
     {
       "epoch": 0.7352941176470589,
-      "grad_norm": 4.188838958740234,
+      "grad_norm": 1.7786710262298584,
       "learning_rate": 7.549019607843137e-05,
-      "loss": 0.4551,
+      "loss": 0.4386,
       "step": 50
     },
     {
       "epoch": 0.8823529411764706,
-      "grad_norm": 1.6839237213134766,
+      "grad_norm": 2.569049119949341,
       "learning_rate": 7.058823529411765e-05,
-      "loss": 0.5278,
+      "loss": 0.5042,
       "step": 60
     },
     {
       "epoch": 1.0294117647058822,
-      "grad_norm": 1.9638292789459229,
+      "grad_norm": 1.8246957063674927,
       "learning_rate": 6.568627450980392e-05,
-      "loss": 0.553,
+      "loss": 0.5466,
       "step": 70
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 2.633883476257324,
+      "grad_norm": 2.425893783569336,
       "learning_rate": 6.078431372549019e-05,
-      "loss": 0.4395,
+      "loss": 0.413,
       "step": 80
     },
     {
       "epoch": 1.3235294117647058,
-      "grad_norm": 1.7703025341033936,
+      "grad_norm": 1.5483649969100952,
       "learning_rate": 5.588235294117647e-05,
-      "loss": 0.4684,
+      "loss": 0.4693,
       "step": 90
     },
     {
       "epoch": 1.4705882352941178,
-      "grad_norm": 2.4201583862304688,
+      "grad_norm": 1.3050321340560913,
       "learning_rate": 5.0980392156862745e-05,
-      "loss": 0.4265,
+      "loss": 0.4126,
       "step": 100
     },
     {
       "epoch": 1.6176470588235294,
-      "grad_norm": 1.9578927755355835,
+      "grad_norm": 1.3402087688446045,
       "learning_rate": 4.607843137254902e-05,
-      "loss": 0.4062,
+      "loss": 0.3931,
       "step": 110
     },
     {
       "epoch": 1.7647058823529411,
-      "grad_norm": 1.2929710149765015,
+      "grad_norm": 1.9078748226165771,
       "learning_rate": 4.11764705882353e-05,
-      "loss": 0.4958,
+      "loss": 0.4831,
       "step": 120
     },
     {
       "epoch": 1.9117647058823528,
-      "grad_norm": 1.7142033576965332,
+      "grad_norm": 2.0981125831604004,
       "learning_rate": 3.627450980392157e-05,
-      "loss": 0.4277,
+      "loss": 0.4249,
       "step": 130
     },
     {
       "epoch": 2.0588235294117645,
-      "grad_norm": 1.1636111736297607,
+      "grad_norm": 2.552691698074341,
       "learning_rate": 3.137254901960784e-05,
-      "loss": 0.3949,
+      "loss": 0.3972,
       "step": 140
     },
     {
       "epoch": 2.2058823529411766,
-      "grad_norm": 1.2120593786239624,
+      "grad_norm": 1.179951548576355,
       "learning_rate": 2.647058823529412e-05,
-      "loss": 0.3773,
+      "loss": 0.3928,
       "step": 150
     },
     {
       "epoch": 2.3529411764705883,
-      "grad_norm": 1.0980979204177856,
+      "grad_norm": 1.4807623624801636,
       "learning_rate": 2.1568627450980395e-05,
-      "loss": 0.4216,
+      "loss": 0.4141,
       "step": 160
     },
     {
       "epoch": 2.5,
-      "grad_norm": 2.2430527210235596,
+      "grad_norm": 2.2445242404937744,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.317,
+      "loss": 0.3197,
       "step": 170
     },
     {
       "epoch": 2.6470588235294117,
-      "grad_norm": 1.2304041385650635,
+      "grad_norm": 1.3446571826934814,
       "learning_rate": 1.1764705882352942e-05,
-      "loss": 0.397,
+      "loss": 0.3921,
       "step": 180
     },
     {
       "epoch": 2.7941176470588234,
-      "grad_norm": 1.9168137311935425,
+      "grad_norm": 2.043297290802002,
       "learning_rate": 6.862745098039216e-06,
-      "loss": 0.3849,
+      "loss": 0.3877,
       "step": 190
     },
     {
       "epoch": 2.9411764705882355,
-      "grad_norm": 1.1686815023422241,
+      "grad_norm": 0.9528805613517761,
       "learning_rate": 1.96078431372549e-06,
-      "loss": 0.3651,
+      "loss": 0.3592,
       "step": 200
     },
     {
       "epoch": 3.0,
       "step": 204,
       "total_flos": 0.0,
-      "train_loss": 0.4645386367451911,
-      "train_runtime": 114.5053,
-      "train_samples_per_second": 5.319,
-      "train_steps_per_second": 1.782
+      "train_loss": 0.45867320310835746,
+      "train_runtime": 113.026,
+      "train_samples_per_second": 5.388,
+      "train_steps_per_second": 1.805
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828fe5e7be55c7b818986065fe2262ae436027c435c5188a91284d11f52bf581
+oid sha256:7a342ca2204ee91e163d377f9114d821ab032d9f89163f6ca3e4864769ccd118
 size 5432