Training in progress, step 400, checkpoint

checkpoint-400/adapter_config.json

@@ -23,12 +23,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
     "k_proj",
-    "down_proj",
+    "up_proj",
     "v_proj",
+    "o_proj",
     "q_proj",
+    "down_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

checkpoint-400/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ad57c2d9c520a1ca889d61873609d9fa94e59e1fb7a1320d7c59b0dc1125e9
+oid sha256:d4b89471d426195ef6b5e002d67fdd2c438e95cc7750b8a3181e95781dd29de6
 size 45118424

checkpoint-400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c17b08ad4d0b430f3228a21ceb18bad7954f0f983e5f13340523b91d13d295
+oid sha256:ef04aedfe7c98347d43fa29f4e7b39b2a687ae7ce2e366a0ce4dceaffa6dda58
 size 23159546

checkpoint-400/trainer_state.json

@@ -10,140 +10,140 @@
   "log_history": [
     {
       "epoch": 0.021333333333333333,
-      "grad_norm": 0.47001057863235474,
+      "grad_norm": 0.4694526791572571,
       "learning_rate": 0.00019678111587982831,
-      "loss": 1.2773,
+      "loss": 1.2772,
       "step": 20
     },
     {
       "epoch": 0.042666666666666665,
-      "grad_norm": 0.3469043970108032,
+      "grad_norm": 0.34691280126571655,
       "learning_rate": 0.0001924892703862661,
       "loss": 0.8918,
       "step": 40
     },
     {
       "epoch": 0.064,
-      "grad_norm": 0.4485608637332916,
+      "grad_norm": 0.44894590973854065,
       "learning_rate": 0.00018819742489270387,
       "loss": 0.8588,
       "step": 60
     },
     {
       "epoch": 0.08533333333333333,
-      "grad_norm": 0.4924505054950714,
+      "grad_norm": 0.4901750981807709,
       "learning_rate": 0.00018390557939914164,
       "loss": 0.7577,
       "step": 80
     },
     {
       "epoch": 0.10666666666666667,
-      "grad_norm": 0.3011874854564667,
+      "grad_norm": 0.3013491630554199,
       "learning_rate": 0.00017961373390557942,
       "loss": 0.7796,
       "step": 100
     },
     {
       "epoch": 0.128,
-      "grad_norm": 0.35178664326667786,
+      "grad_norm": 0.35143589973449707,
       "learning_rate": 0.00017532188841201717,
       "loss": 0.7647,
       "step": 120
     },
     {
       "epoch": 0.14933333333333335,
-      "grad_norm": 0.29895663261413574,
+      "grad_norm": 0.29885634779930115,
       "learning_rate": 0.00017103004291845494,
-      "loss": 0.6741,
+      "loss": 0.674,
       "step": 140
     },
     {
       "epoch": 0.17066666666666666,
-      "grad_norm": 0.265635222196579,
+      "grad_norm": 0.26554301381111145,
       "learning_rate": 0.00016673819742489272,
       "loss": 0.7586,
       "step": 160
     },
     {
       "epoch": 0.192,
-      "grad_norm": 0.29633283615112305,
+      "grad_norm": 0.2963835895061493,
       "learning_rate": 0.0001624463519313305,
       "loss": 0.7364,
       "step": 180
     },
     {
       "epoch": 0.21333333333333335,
-      "grad_norm": 0.3618737757205963,
+      "grad_norm": 0.36166927218437195,
       "learning_rate": 0.00015815450643776824,
       "loss": 0.7943,
       "step": 200
     },
     {
       "epoch": 0.23466666666666666,
-      "grad_norm": 0.2392752766609192,
+      "grad_norm": 0.23920877277851105,
       "learning_rate": 0.000153862660944206,
-      "loss": 0.7054,
+      "loss": 0.7055,
       "step": 220
     },
     {
       "epoch": 0.256,
-      "grad_norm": 0.3207932114601135,
+      "grad_norm": 0.32076919078826904,
       "learning_rate": 0.00014957081545064377,
       "loss": 0.7495,
       "step": 240
     },
     {
       "epoch": 0.2773333333333333,
-      "grad_norm": 0.3499705493450165,
+      "grad_norm": 0.34986230731010437,
       "learning_rate": 0.00014527896995708155,
       "loss": 0.7739,
       "step": 260
     },
     {
       "epoch": 0.2986666666666667,
-      "grad_norm": 0.27541521191596985,
+      "grad_norm": 0.27509021759033203,
       "learning_rate": 0.00014098712446351932,
       "loss": 0.7125,
       "step": 280
     },
     {
       "epoch": 0.32,
-      "grad_norm": 0.27608659863471985,
+      "grad_norm": 0.2761971652507782,
       "learning_rate": 0.0001366952789699571,
-      "loss": 0.7307,
+      "loss": 0.7306,
       "step": 300
     },
     {
       "epoch": 0.3413333333333333,
-      "grad_norm": 0.27710551023483276,
+      "grad_norm": 0.27699899673461914,
       "learning_rate": 0.00013240343347639485,
       "loss": 0.6974,
       "step": 320
     },
     {
       "epoch": 0.3626666666666667,
-      "grad_norm": 0.334416002035141,
+      "grad_norm": 0.33432355523109436,
       "learning_rate": 0.00012811158798283262,
       "loss": 0.7555,
       "step": 340
     },
     {
       "epoch": 0.384,
-      "grad_norm": 0.288921594619751,
+      "grad_norm": 0.2890004515647888,
       "learning_rate": 0.0001238197424892704,
-      "loss": 0.7222,
+      "loss": 0.7221,
       "step": 360
     },
     {
       "epoch": 0.4053333333333333,
-      "grad_norm": 0.3428654074668884,
+      "grad_norm": 0.3435133397579193,
       "learning_rate": 0.00011952789699570816,
       "loss": 0.7466,
       "step": 380
     },
     {
       "epoch": 0.4266666666666667,
-      "grad_norm": 0.42291027307510376,
+      "grad_norm": 0.42325925827026367,
       "learning_rate": 0.00011523605150214594,
       "loss": 0.6999,
       "step": 400

checkpoint-400/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4651d06185709dd3d181207d567d0b3ed653efb01f01015cb44b8df4eebee657
+oid sha256:69617c1bea4a27e99b6c6729498e45489dcd01641dbfbfbf0cc0b118ad579975
 size 5560