Upload 12 files

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "up_proj",
     "k_proj",
-    "down_proj",
     "gate_proj",
-    "o_proj",
-    "v_proj"
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2bdf097d839bacb6794ab6b523a82cddd704ad62064bf65405e014e0da39a8b
+oid sha256:fbc3576307cf44ce9d7035b9a3aafb9a2b1e2b81056bc5cd464d9625dd418096
 size 100059752

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339c84f94bfa38a77929258380ba32b1339499872d528bd3d58a49a5f899b046
+oid sha256:cad169389767a1102d07c3157ee244ec7b5485cb66191bebe939d24560c538c4
 size 50545780

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c948628ba1804e0dc0e988e547ad05d27e9a4f2682e0d6f6481f21ae112fc2
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0c3e57a26cae66bf125d8bf6fa7070a034c23d0416abcf71b28aefe1bb53b6
+oid sha256:a6f4d2b44e7b6291612b138962c82e22b66be3188e99394e29c3a567af8e3db1
 size 1064

trainer_state.json

@@ -1,370 +1,90 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 50.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 50,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 2.530534029006958,
+      "grad_norm": 3.2200822830200195,
       "learning_rate": 0.0001,
-      "loss": 1.1597,
+      "loss": 1.1272,
       "step": 1
     },
     {
       "epoch": 2.0,
-      "grad_norm": 2.530534029006958,
+      "grad_norm": 3.2200822830200195,
       "learning_rate": 0.0002,
-      "loss": 1.1597,
+      "loss": 1.1272,
       "step": 2
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.3551818132400513,
-      "learning_rate": 0.00019795918367346938,
-      "loss": 0.9742,
+      "grad_norm": 1.8294692039489746,
+      "learning_rate": 0.0001995983935742972,
+      "loss": 0.8989,
       "step": 3
     },
     {
       "epoch": 4.0,
-      "grad_norm": 1.7891594171524048,
-      "learning_rate": 0.0001959183673469388,
-      "loss": 0.7509,
+      "grad_norm": 1.9677034616470337,
+      "learning_rate": 0.0001991967871485944,
+      "loss": 0.6342,
       "step": 4
     },
     {
       "epoch": 5.0,
-      "grad_norm": 1.3730740547180176,
-      "learning_rate": 0.00019387755102040816,
-      "loss": 0.5428,
+      "grad_norm": 1.3022174835205078,
+      "learning_rate": 0.00019879518072289158,
+      "loss": 0.3798,
       "step": 5
     },
     {
       "epoch": 6.0,
-      "grad_norm": 1.1008703708648682,
-      "learning_rate": 0.00019183673469387756,
-      "loss": 0.3649,
+      "grad_norm": 0.9234146475791931,
+      "learning_rate": 0.00019839357429718877,
+      "loss": 0.1889,
       "step": 6
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.8232898116111755,
-      "learning_rate": 0.00018979591836734697,
-      "loss": 0.2208,
+      "grad_norm": 0.6237850785255432,
+      "learning_rate": 0.00019799196787148596,
+      "loss": 0.1014,
       "step": 7
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.6340098977088928,
-      "learning_rate": 0.00018775510204081634,
-      "loss": 0.1423,
+      "grad_norm": 0.20204997062683105,
+      "learning_rate": 0.00019759036144578314,
+      "loss": 0.0767,
       "step": 8
     },
     {
       "epoch": 9.0,
-      "grad_norm": 0.7959883809089661,
-      "learning_rate": 0.00018571428571428572,
-      "loss": 0.1026,
+      "grad_norm": 0.2050553411245346,
+      "learning_rate": 0.00019718875502008033,
+      "loss": 0.0744,
       "step": 9
     },
     {
       "epoch": 10.0,
-      "grad_norm": 0.22785189747810364,
-      "learning_rate": 0.00018367346938775512,
-      "loss": 0.08,
+      "grad_norm": 0.16611504554748535,
+      "learning_rate": 0.00019678714859437752,
+      "loss": 0.0711,
       "step": 10
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 1.1459858417510986,
-      "learning_rate": 0.0001816326530612245,
-      "loss": 0.0856,
-      "step": 11
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 0.3908502459526062,
-      "learning_rate": 0.0001795918367346939,
-      "loss": 0.0719,
-      "step": 12
-    },
-    {
-      "epoch": 13.0,
-      "grad_norm": 9.051756858825684,
-      "learning_rate": 0.00017755102040816327,
-      "loss": 0.0923,
-      "step": 13
-    },
-    {
-      "epoch": 14.0,
-      "grad_norm": 0.6290709972381592,
-      "learning_rate": 0.00017551020408163265,
-      "loss": 0.0629,
-      "step": 14
-    },
-    {
-      "epoch": 15.0,
-      "grad_norm": 0.3718617260456085,
-      "learning_rate": 0.00017346938775510205,
-      "loss": 0.0558,
-      "step": 15
-    },
-    {
-      "epoch": 16.0,
-      "grad_norm": 2.362645387649536,
-      "learning_rate": 0.00017142857142857143,
-      "loss": 0.0484,
-      "step": 16
-    },
-    {
-      "epoch": 17.0,
-      "grad_norm": 0.40503254532814026,
-      "learning_rate": 0.00016938775510204083,
-      "loss": 0.0402,
-      "step": 17
-    },
-    {
-      "epoch": 18.0,
-      "grad_norm": 0.4263724982738495,
-      "learning_rate": 0.00016734693877551023,
-      "loss": 0.031,
-      "step": 18
-    },
-    {
-      "epoch": 19.0,
-      "grad_norm": 0.4310762882232666,
-      "learning_rate": 0.0001653061224489796,
-      "loss": 0.0203,
-      "step": 19
-    },
-    {
-      "epoch": 20.0,
-      "grad_norm": 0.30944424867630005,
-      "learning_rate": 0.00016326530612244898,
-      "loss": 0.0108,
-      "step": 20
-    },
-    {
-      "epoch": 21.0,
-      "grad_norm": 1.028169870376587,
-      "learning_rate": 0.00016122448979591838,
-      "loss": 0.0074,
-      "step": 21
-    },
-    {
-      "epoch": 22.0,
-      "grad_norm": 0.04014270380139351,
-      "learning_rate": 0.00015918367346938776,
-      "loss": 0.0049,
-      "step": 22
-    },
-    {
-      "epoch": 23.0,
-      "grad_norm": 0.05887392908334732,
-      "learning_rate": 0.00015714285714285716,
-      "loss": 0.0047,
-      "step": 23
-    },
-    {
-      "epoch": 24.0,
-      "grad_norm": 0.03721626475453377,
-      "learning_rate": 0.00015510204081632654,
-      "loss": 0.0045,
-      "step": 24
-    },
-    {
-      "epoch": 25.0,
-      "grad_norm": 0.028165677562355995,
-      "learning_rate": 0.0001530612244897959,
-      "loss": 0.0044,
-      "step": 25
-    },
-    {
-      "epoch": 26.0,
-      "grad_norm": 0.04805993288755417,
-      "learning_rate": 0.0001510204081632653,
-      "loss": 0.0044,
-      "step": 26
-    },
-    {
-      "epoch": 27.0,
-      "grad_norm": 0.01522037573158741,
-      "learning_rate": 0.00014897959183673472,
-      "loss": 0.0044,
-      "step": 27
-    },
-    {
-      "epoch": 28.0,
-      "grad_norm": 0.03575819730758667,
-      "learning_rate": 0.0001469387755102041,
-      "loss": 0.0044,
-      "step": 28
-    },
-    {
-      "epoch": 29.0,
-      "grad_norm": 0.015163887292146683,
-      "learning_rate": 0.0001448979591836735,
-      "loss": 0.0043,
-      "step": 29
-    },
-    {
-      "epoch": 30.0,
-      "grad_norm": 0.04816267639398575,
-      "learning_rate": 0.00014285714285714287,
-      "loss": 0.0044,
-      "step": 30
-    },
-    {
-      "epoch": 31.0,
-      "grad_norm": 0.013516299426555634,
-      "learning_rate": 0.00014081632653061224,
-      "loss": 0.0043,
-      "step": 31
-    },
-    {
-      "epoch": 32.0,
-      "grad_norm": 0.03639404475688934,
-      "learning_rate": 0.00013877551020408165,
-      "loss": 0.0044,
-      "step": 32
-    },
-    {
-      "epoch": 33.0,
-      "grad_norm": 0.01309999544173479,
-      "learning_rate": 0.00013673469387755102,
-      "loss": 0.0043,
-      "step": 33
-    },
-    {
-      "epoch": 34.0,
-      "grad_norm": 0.014071361161768436,
-      "learning_rate": 0.0001346938775510204,
-      "loss": 0.0043,
-      "step": 34
-    },
-    {
-      "epoch": 35.0,
-      "grad_norm": 0.017163768410682678,
-      "learning_rate": 0.0001326530612244898,
-      "loss": 0.0043,
-      "step": 35
-    },
-    {
-      "epoch": 36.0,
-      "grad_norm": 0.03140578046441078,
-      "learning_rate": 0.00013061224489795917,
-      "loss": 0.0044,
-      "step": 36
-    },
-    {
-      "epoch": 37.0,
-      "grad_norm": 0.023640567436814308,
-      "learning_rate": 0.00012857142857142858,
-      "loss": 0.0043,
-      "step": 37
-    },
-    {
-      "epoch": 38.0,
-      "grad_norm": 0.017914315685629845,
-      "learning_rate": 0.00012653061224489798,
-      "loss": 0.0043,
-      "step": 38
-    },
-    {
-      "epoch": 39.0,
-      "grad_norm": 0.025304120033979416,
-      "learning_rate": 0.00012448979591836735,
-      "loss": 0.0043,
-      "step": 39
-    },
-    {
-      "epoch": 40.0,
-      "grad_norm": 0.01872032880783081,
-      "learning_rate": 0.00012244897959183676,
-      "loss": 0.0043,
-      "step": 40
-    },
-    {
-      "epoch": 41.0,
-      "grad_norm": 0.020662743598222733,
-      "learning_rate": 0.00012040816326530613,
-      "loss": 0.0043,
-      "step": 41
-    },
-    {
-      "epoch": 42.0,
-      "grad_norm": 0.006046542432159185,
-      "learning_rate": 0.00011836734693877552,
-      "loss": 0.0043,
-      "step": 42
-    },
-    {
-      "epoch": 43.0,
-      "grad_norm": 0.04898548126220703,
-      "learning_rate": 0.0001163265306122449,
-      "loss": 0.0043,
-      "step": 43
-    },
-    {
-      "epoch": 44.0,
-      "grad_norm": 0.03499221429228783,
-      "learning_rate": 0.00011428571428571428,
-      "loss": 0.0043,
-      "step": 44
-    },
-    {
-      "epoch": 45.0,
-      "grad_norm": 0.03172151744365692,
-      "learning_rate": 0.00011224489795918367,
-      "loss": 0.0043,
-      "step": 45
-    },
-    {
-      "epoch": 46.0,
-      "grad_norm": 0.03858642280101776,
-      "learning_rate": 0.00011020408163265306,
-      "loss": 0.0044,
-      "step": 46
-    },
-    {
-      "epoch": 47.0,
-      "grad_norm": 0.05879056453704834,
-      "learning_rate": 0.00010816326530612246,
-      "loss": 0.0044,
-      "step": 47
-    },
-    {
-      "epoch": 48.0,
-      "grad_norm": 0.02806887961924076,
-      "learning_rate": 0.00010612244897959185,
-      "loss": 0.0043,
-      "step": 48
-    },
-    {
-      "epoch": 49.0,
-      "grad_norm": 0.04892841354012489,
-      "learning_rate": 0.00010408163265306123,
-      "loss": 0.0044,
-      "step": 49
-    },
-    {
-      "epoch": 50.0,
-      "grad_norm": 0.028942273929715157,
-      "learning_rate": 0.00010204081632653062,
-      "loss": 0.0043,
-      "step": 50
     }
   ],
   "logging_steps": 1,
-  "max_steps": 100,
+  "max_steps": 500,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 100,
+  "num_train_epochs": 500,
   "save_steps": 500,
-  "total_flos": 380258668032000.0,
+  "total_flos": 77451458764800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5b1969d43c316b9129c4e907c444a012ca9c9efecd26219396536a3708cb1bc
+oid sha256:f2fd876d19bbf30d7b89395ffb800c42675421fc4cbcca0c7ced1806676ee618
 size 4984