Upload folder using huggingface_hub

checkpoint-30/adapter_config.json

@@ -34,13 +34,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
     "v_proj",
-    "k_proj",
-    "up_proj",
     "o_proj",
-    "q_proj",
-    "down_proj",
-    "gate_proj"
+    "up_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

checkpoint-30/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32cd276cc4085f634fdf4c79ed262b19f8f2a9b6eacb30a7c10341e5e71dca9e
+oid sha256:fde086140e7963aedad838f8435896127787d98f02ecad970bc4ec15042a858a
 size 59933632

checkpoint-30/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ca7d76fb26b098a3e4f13e4a6690ebcfbfc36e63d805626b907788afb77000
+oid sha256:7471b9291a078960c699328acf57efb81bc2eb2c5edecb4a448e58f710f9343f
 size 120166091

checkpoint-30/trainer_state.json

@@ -67,156 +67,156 @@
     },
     {
       "epoch": 0.05934065934065934,
-      "grad_norm": 0.8124693632125854,
+      "grad_norm": 0.812495768070221,
       "learning_rate": 0.00019866962305986697,
       "loss": 1.3178,
       "step": 9
     },
     {
       "epoch": 0.06593406593406594,
-      "grad_norm": 1.4746452569961548,
+      "grad_norm": 1.4647173881530762,
       "learning_rate": 0.00019822616407982261,
-      "loss": 1.3747,
+      "loss": 1.3721,
       "step": 10
     },
     {
       "epoch": 0.07252747252747253,
-      "grad_norm": 1.0956214666366577,
+      "grad_norm": 1.0903385877609253,
       "learning_rate": 0.00019778270509977829,
-      "loss": 1.2291,
+      "loss": 1.2288,
       "step": 11
     },
     {
       "epoch": 0.07912087912087912,
-      "grad_norm": 0.5584886074066162,
+      "grad_norm": 0.5566668510437012,
       "learning_rate": 0.00019733924611973393,
-      "loss": 1.2929,
+      "loss": 1.2958,
       "step": 12
     },
     {
       "epoch": 0.08571428571428572,
-      "grad_norm": 0.8778825402259827,
+      "grad_norm": 0.9000307321548462,
       "learning_rate": 0.0001968957871396896,
-      "loss": 1.0355,
+      "loss": 1.0353,
       "step": 13
     },
     {
       "epoch": 0.09230769230769231,
-      "grad_norm": 0.5020594596862793,
+      "grad_norm": 0.5002865791320801,
       "learning_rate": 0.00019645232815964525,
-      "loss": 1.1668,
+      "loss": 1.1657,
       "step": 14
     },
     {
       "epoch": 0.0989010989010989,
-      "grad_norm": 0.4985601305961609,
+      "grad_norm": 0.4956091344356537,
       "learning_rate": 0.00019600886917960092,
-      "loss": 1.1048,
+      "loss": 1.1026,
       "step": 15
     },
     {
       "epoch": 0.1054945054945055,
-      "grad_norm": 0.4597553312778473,
+      "grad_norm": 0.46295931935310364,
       "learning_rate": 0.00019556541019955653,
-      "loss": 1.0144,
+      "loss": 1.0131,
       "step": 16
     },
     {
       "epoch": 0.11208791208791209,
-      "grad_norm": 0.44980549812316895,
+      "grad_norm": 0.44878455996513367,
       "learning_rate": 0.0001951219512195122,
-      "loss": 1.128,
+      "loss": 1.1302,
       "step": 17
     },
     {
       "epoch": 0.11868131868131868,
-      "grad_norm": 0.33276212215423584,
+      "grad_norm": 0.3325801193714142,
       "learning_rate": 0.00019467849223946785,
-      "loss": 0.9434,
+      "loss": 0.9445,
       "step": 18
     },
     {
       "epoch": 0.12527472527472527,
-      "grad_norm": 0.46772485971450806,
+      "grad_norm": 0.46596264839172363,
       "learning_rate": 0.00019423503325942352,
-      "loss": 1.2302,
+      "loss": 1.2325,
       "step": 19
     },
     {
       "epoch": 0.13186813186813187,
-      "grad_norm": 0.3876091241836548,
+      "grad_norm": 0.38645994663238525,
       "learning_rate": 0.00019379157427937917,
-      "loss": 1.0448,
+      "loss": 1.0453,
       "step": 20
     },
     {
       "epoch": 0.13846153846153847,
-      "grad_norm": 0.3786633610725403,
+      "grad_norm": 0.3800373375415802,
       "learning_rate": 0.00019334811529933484,
-      "loss": 1.0449,
+      "loss": 1.045,
       "step": 21
     },
     {
       "epoch": 0.14505494505494507,
-      "grad_norm": 0.4180683195590973,
+      "grad_norm": 0.4129738211631775,
       "learning_rate": 0.00019290465631929045,
-      "loss": 1.1112,
+      "loss": 1.1104,
       "step": 22
     },
     {
       "epoch": 0.15164835164835164,
-      "grad_norm": 0.4051693081855774,
+      "grad_norm": 0.40392687916755676,
       "learning_rate": 0.00019246119733924613,
-      "loss": 1.0586,
+      "loss": 1.0589,
       "step": 23
     },
     {
       "epoch": 0.15824175824175823,
-      "grad_norm": 0.30783703923225403,
+      "grad_norm": 0.3075926899909973,
       "learning_rate": 0.00019201773835920177,
-      "loss": 0.9412,
+      "loss": 0.9411,
       "step": 24
     },
     {
       "epoch": 0.16483516483516483,
-      "grad_norm": 0.3420283794403076,
+      "grad_norm": 0.3475458323955536,
       "learning_rate": 0.00019157427937915744,
-      "loss": 0.9213,
+      "loss": 0.9233,
       "step": 25
     },
     {
       "epoch": 0.17142857142857143,
-      "grad_norm": 0.47376200556755066,
+      "grad_norm": 0.49025434255599976,
       "learning_rate": 0.00019113082039911309,
-      "loss": 0.9635,
+      "loss": 0.9665,
       "step": 26
     },
     {
       "epoch": 0.17802197802197803,
-      "grad_norm": 0.3626822233200073,
+      "grad_norm": 0.3652801215648651,
       "learning_rate": 0.00019068736141906876,
-      "loss": 0.7696,
+      "loss": 0.7703,
       "step": 27
     },
     {
       "epoch": 0.18461538461538463,
-      "grad_norm": 0.46646377444267273,
+      "grad_norm": 0.45883381366729736,
       "learning_rate": 0.0001902439024390244,
-      "loss": 1.098,
+      "loss": 1.0975,
       "step": 28
     },
     {
       "epoch": 0.1912087912087912,
-      "grad_norm": 0.38763922452926636,
+      "grad_norm": 0.3874357044696808,
       "learning_rate": 0.00018980044345898005,
-      "loss": 1.1587,
+      "loss": 1.1598,
       "step": 29
     },
     {
       "epoch": 0.1978021978021978,
-      "grad_norm": 0.3439793288707733,
+      "grad_norm": 0.34444889426231384,
       "learning_rate": 0.00018935698447893572,
-      "loss": 1.1153,
+      "loss": 1.115,
       "step": 30
     }
   ],

checkpoint-30/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e6107b40730f00b0ecebeb53261d03c090314acc28d156f0c2a1f966f3cdca
+oid sha256:0f4aaa76910e776691a8e236eac6a84769f2e9172a54a9d30fe100706079516a
 size 6417