Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23ee6f81dd496aa2a837a563f66f71607eec837c9c178d4351919ddf89c7c59
+oid sha256:d49def9cc32d2020c862170ab6e071e45970f68bf0828a71a1e5bfe1e68158b5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b983c4dc1d54aeb8fa04b4467ff343795c06f02e2408d7abb5bedd3c7ea4498
+oid sha256:5ab8aa4f77d37479f722eeefec8be90ba2b06d4e3eaec252dd13d5116df31863
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1301d8ff77a21126a7a758614a70c01a552c16ba64fe53295c29cdd7bbf62b76
+oid sha256:a94f17b84a2a153300a730dbbb93a1452695fbc57cc338b21412c031fc784729
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
+oid sha256:b8eccac390378b22aeb148c260b00bec01d948946d8363d5282899af673e0e86
 size 1064

last-checkpoint/trainer_state.json

@@ -2,7 +2,7 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 0.4678362573099415,
-  "eval_steps": 13,
+  "eval_steps": 25,
   "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.00935672514619883,
-      "grad_norm": 4.390414714813232,
+      "grad_norm": 4.463105201721191,
       "learning_rate": 2e-05,
       "loss": 3.2142,
       "step": 1
@@ -18,384 +18,376 @@
     {
       "epoch": 0.00935672514619883,
       "eval_loss": 3.3358547687530518,
-      "eval_runtime": 13.9154,
-      "eval_samples_per_second": 6.468,
-      "eval_steps_per_second": 6.468,
+      "eval_runtime": 13.9023,
+      "eval_samples_per_second": 6.474,
+      "eval_steps_per_second": 6.474,
       "step": 1
     },
     {
       "epoch": 0.01871345029239766,
-      "grad_norm": 4.702328205108643,
+      "grad_norm": 4.7624897956848145,
       "learning_rate": 4e-05,
       "loss": 3.3766,
       "step": 2
     },
     {
       "epoch": 0.028070175438596492,
-      "grad_norm": 3.9439697265625,
+      "grad_norm": 3.991523265838623,
       "learning_rate": 6e-05,
-      "loss": 3.3938,
+      "loss": 3.3922,
       "step": 3
     },
     {
       "epoch": 0.03742690058479532,
-      "grad_norm": 3.85864520072937,
+      "grad_norm": 3.8783044815063477,
       "learning_rate": 8e-05,
-      "loss": 3.0785,
+      "loss": 3.0767,
       "step": 4
     },
     {
       "epoch": 0.04678362573099415,
-      "grad_norm": 4.246149063110352,
+      "grad_norm": 4.1902995109558105,
       "learning_rate": 0.0001,
-      "loss": 3.3005,
+      "loss": 3.2965,
       "step": 5
     },
     {
       "epoch": 0.056140350877192984,
-      "grad_norm": 3.976107597351074,
+      "grad_norm": 4.054313659667969,
       "learning_rate": 0.00012,
-      "loss": 3.0138,
+      "loss": 3.0089,
       "step": 6
     },
     {
       "epoch": 0.06549707602339182,
-      "grad_norm": 4.311132907867432,
+      "grad_norm": 4.280858993530273,
       "learning_rate": 0.00014,
-      "loss": 3.0914,
+      "loss": 3.0863,
       "step": 7
     },
     {
       "epoch": 0.07485380116959064,
-      "grad_norm": 3.888803482055664,
+      "grad_norm": 3.999479293823242,
       "learning_rate": 0.00016,
-      "loss": 2.9978,
+      "loss": 2.9925,
       "step": 8
     },
     {
       "epoch": 0.08421052631578947,
-      "grad_norm": 3.422027826309204,
+      "grad_norm": 3.4866421222686768,
       "learning_rate": 0.00018,
-      "loss": 2.9429,
+      "loss": 2.941,
       "step": 9
     },
     {
       "epoch": 0.0935672514619883,
-      "grad_norm": 3.8653438091278076,
+      "grad_norm": 3.900364398956299,
       "learning_rate": 0.0002,
-      "loss": 2.7896,
+      "loss": 2.7885,
       "step": 10
     },
     {
       "epoch": 0.10292397660818714,
-      "grad_norm": 3.4567666053771973,
-      "learning_rate": 0.0001996917333733128,
-      "loss": 2.8054,
+      "grad_norm": 3.4323623180389404,
+      "learning_rate": 0.0001999390827019096,
+      "loss": 2.8013,
       "step": 11
     },
     {
       "epoch": 0.11228070175438597,
-      "grad_norm": 3.503476619720459,
-      "learning_rate": 0.00019876883405951377,
-      "loss": 2.6823,
+      "grad_norm": 3.4795432090759277,
+      "learning_rate": 0.00019975640502598244,
+      "loss": 2.6806,
       "step": 12
     },
     {
       "epoch": 0.1216374269005848,
-      "grad_norm": 3.275860548019409,
-      "learning_rate": 0.00019723699203976766,
-      "loss": 2.6355,
-      "step": 13
-    },
-    {
-      "epoch": 0.1216374269005848,
-      "eval_loss": 2.705251932144165,
-      "eval_runtime": 14.0018,
-      "eval_samples_per_second": 6.428,
-      "eval_steps_per_second": 6.428,
+      "grad_norm": 3.2568836212158203,
+      "learning_rate": 0.00019945218953682734,
+      "loss": 2.6366,
       "step": 13
     },
     {
       "epoch": 0.13099415204678364,
-      "grad_norm": 3.013310432434082,
-      "learning_rate": 0.00019510565162951537,
-      "loss": 2.7933,
+      "grad_norm": 2.9930436611175537,
+      "learning_rate": 0.00019902680687415705,
+      "loss": 2.7908,
       "step": 14
     },
     {
       "epoch": 0.14035087719298245,
-      "grad_norm": 2.840459108352661,
-      "learning_rate": 0.0001923879532511287,
-      "loss": 2.5431,
+      "grad_norm": 2.845224380493164,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 2.5384,
       "step": 15
     },
     {
       "epoch": 0.1497076023391813,
-      "grad_norm": 2.7099273204803467,
-      "learning_rate": 0.0001891006524188368,
-      "loss": 2.7605,
+      "grad_norm": 2.690312385559082,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.7595,
       "step": 16
     },
     {
       "epoch": 0.15906432748538013,
-      "grad_norm": 3.015941858291626,
-      "learning_rate": 0.00018526401643540922,
-      "loss": 2.7942,
+      "grad_norm": 3.0404510498046875,
+      "learning_rate": 0.00019702957262759965,
+      "loss": 2.7844,
       "step": 17
     },
     {
       "epoch": 0.16842105263157894,
-      "grad_norm": 2.8122756481170654,
-      "learning_rate": 0.00018090169943749476,
-      "loss": 2.4924,
+      "grad_norm": 2.836411952972412,
+      "learning_rate": 0.0001961261695938319,
+      "loss": 2.4923,
       "step": 18
     },
     {
       "epoch": 0.17777777777777778,
-      "grad_norm": 3.007946729660034,
-      "learning_rate": 0.0001760405965600031,
-      "loss": 2.603,
+      "grad_norm": 3.020054578781128,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.6076,
       "step": 19
     },
     {
       "epoch": 0.1871345029239766,
-      "grad_norm": 2.713869571685791,
-      "learning_rate": 0.00017071067811865476,
-      "loss": 2.6412,
+      "grad_norm": 2.719973087310791,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 2.6418,
       "step": 20
     },
     {
       "epoch": 0.19649122807017544,
-      "grad_norm": 3.0754899978637695,
-      "learning_rate": 0.00016494480483301836,
-      "loss": 2.7249,
+      "grad_norm": 3.120027780532837,
+      "learning_rate": 0.00019271838545667876,
+      "loss": 2.7253,
       "step": 21
     },
     {
       "epoch": 0.20584795321637428,
-      "grad_norm": 2.7693493366241455,
-      "learning_rate": 0.00015877852522924732,
-      "loss": 2.4397,
+      "grad_norm": 2.7467753887176514,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.4353,
       "step": 22
     },
     {
       "epoch": 0.2152046783625731,
-      "grad_norm": 3.2417685985565186,
-      "learning_rate": 0.0001522498564715949,
-      "loss": 2.6893,
+      "grad_norm": 3.3954317569732666,
+      "learning_rate": 0.0001898794046299167,
+      "loss": 2.6932,
       "step": 23
     },
     {
       "epoch": 0.22456140350877193,
-      "grad_norm": 2.7010700702667236,
-      "learning_rate": 0.00014539904997395468,
-      "loss": 2.5236,
+      "grad_norm": 2.6571295261383057,
+      "learning_rate": 0.00018829475928589271,
+      "loss": 2.5214,
       "step": 24
     },
     {
       "epoch": 0.23391812865497075,
-      "grad_norm": 2.3874123096466064,
-      "learning_rate": 0.000138268343236509,
-      "loss": 2.6103,
+      "grad_norm": 2.4160666465759277,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 2.6052,
       "step": 25
     },
     {
-      "epoch": 0.2432748538011696,
-      "grad_norm": 2.6382222175598145,
-      "learning_rate": 0.00013090169943749476,
-      "loss": 2.5479,
-      "step": 26
+      "epoch": 0.23391812865497075,
+      "eval_loss": 2.5258662700653076,
+      "eval_runtime": 13.9413,
+      "eval_samples_per_second": 6.456,
+      "eval_steps_per_second": 6.456,
+      "step": 25
     },
     {
       "epoch": 0.2432748538011696,
-      "eval_loss": 2.524278163909912,
-      "eval_runtime": 14.0548,
-      "eval_samples_per_second": 6.404,
-      "eval_steps_per_second": 6.404,
+      "grad_norm": 2.6495888233184814,
+      "learning_rate": 0.0001848048096156426,
+      "loss": 2.5469,
       "step": 26
     },
     {
       "epoch": 0.25263157894736843,
-      "grad_norm": 2.8567240238189697,
-      "learning_rate": 0.00012334453638559057,
-      "loss": 2.5996,
+      "grad_norm": 2.838324785232544,
+      "learning_rate": 0.00018290375725550417,
+      "loss": 2.5969,
       "step": 27
     },
     {
       "epoch": 0.26198830409356727,
-      "grad_norm": 2.801514148712158,
-      "learning_rate": 0.0001156434465040231,
-      "loss": 2.418,
+      "grad_norm": 2.747297525405884,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.4122,
       "step": 28
     },
     {
       "epoch": 0.27134502923976606,
-      "grad_norm": 2.5751523971557617,
-      "learning_rate": 0.0001078459095727845,
-      "loss": 2.3009,
+      "grad_norm": 2.5374674797058105,
+      "learning_rate": 0.00017880107536067218,
+      "loss": 2.2964,
       "step": 29
     },
     {
       "epoch": 0.2807017543859649,
-      "grad_norm": 2.7880630493164062,
-      "learning_rate": 0.0001,
-      "loss": 2.6674,
+      "grad_norm": 2.8469207286834717,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 2.6656,
       "step": 30
     },
     {
       "epoch": 0.29005847953216374,
-      "grad_norm": 2.797865152359009,
-      "learning_rate": 9.215409042721552e-05,
-      "loss": 2.2681,
+      "grad_norm": 2.8864634037017822,
+      "learning_rate": 0.00017431448254773944,
+      "loss": 2.2717,
       "step": 31
     },
     {
       "epoch": 0.2994152046783626,
-      "grad_norm": 2.4833743572235107,
-      "learning_rate": 8.435655349597689e-05,
-      "loss": 2.3812,
+      "grad_norm": 2.550114393234253,
+      "learning_rate": 0.0001719339800338651,
+      "loss": 2.3912,
       "step": 32
     },
     {
       "epoch": 0.3087719298245614,
-      "grad_norm": 2.8263983726501465,
-      "learning_rate": 7.66554636144095e-05,
-      "loss": 2.3514,
+      "grad_norm": 2.7608063220977783,
+      "learning_rate": 0.00016946583704589973,
+      "loss": 2.3453,
       "step": 33
     },
     {
       "epoch": 0.31812865497076026,
-      "grad_norm": 2.8448684215545654,
-      "learning_rate": 6.909830056250527e-05,
-      "loss": 2.4968,
+      "grad_norm": 2.7784292697906494,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.495,
       "step": 34
     },
     {
       "epoch": 0.32748538011695905,
-      "grad_norm": 2.7989699840545654,
-      "learning_rate": 6.173165676349103e-05,
-      "loss": 2.3572,
+      "grad_norm": 2.7670254707336426,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 2.3523,
       "step": 35
     },
     {
       "epoch": 0.3368421052631579,
-      "grad_norm": 2.8134164810180664,
-      "learning_rate": 5.4600950026045326e-05,
-      "loss": 2.4871,
+      "grad_norm": 2.92022442817688,
+      "learning_rate": 0.0001615661475325658,
+      "loss": 2.5027,
       "step": 36
     },
     {
       "epoch": 0.34619883040935673,
-      "grad_norm": 2.7917492389678955,
-      "learning_rate": 4.7750143528405126e-05,
-      "loss": 2.5673,
+      "grad_norm": 2.6825602054595947,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 2.5576,
       "step": 37
     },
     {
       "epoch": 0.35555555555555557,
-      "grad_norm": 2.7606780529022217,
-      "learning_rate": 4.12214747707527e-05,
-      "loss": 2.4209,
+      "grad_norm": 2.5809407234191895,
+      "learning_rate": 0.0001559192903470747,
+      "loss": 2.4248,
       "step": 38
     },
     {
       "epoch": 0.3649122807017544,
-      "grad_norm": 2.731044054031372,
-      "learning_rate": 3.5055195166981645e-05,
-      "loss": 2.3921,
-      "step": 39
-    },
-    {
-      "epoch": 0.3649122807017544,
-      "eval_loss": 2.4570887088775635,
-      "eval_runtime": 13.8846,
-      "eval_samples_per_second": 6.482,
-      "eval_steps_per_second": 6.482,
+      "grad_norm": 2.5570051670074463,
+      "learning_rate": 0.0001529919264233205,
+      "loss": 2.3693,
       "step": 39
     },
     {
       "epoch": 0.3742690058479532,
-      "grad_norm": 2.5024521350860596,
-      "learning_rate": 2.9289321881345254e-05,
-      "loss": 2.4786,
+      "grad_norm": 2.4310109615325928,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.4687,
       "step": 40
     },
     {
       "epoch": 0.38362573099415204,
-      "grad_norm": 2.737299919128418,
-      "learning_rate": 2.3959403439996907e-05,
-      "loss": 2.5444,
+      "grad_norm": 2.647545099258423,
+      "learning_rate": 0.00014694715627858908,
+      "loss": 2.5393,
       "step": 41
     },
     {
       "epoch": 0.3929824561403509,
-      "grad_norm": 2.6610891819000244,
-      "learning_rate": 1.9098300562505266e-05,
-      "loss": 2.3979,
+      "grad_norm": 2.5504465103149414,
+      "learning_rate": 0.00014383711467890774,
+      "loss": 2.3839,
       "step": 42
     },
     {
       "epoch": 0.4023391812865497,
-      "grad_norm": 2.5578110218048096,
-      "learning_rate": 1.4735983564590783e-05,
-      "loss": 2.5223,
+      "grad_norm": 2.3321890830993652,
+      "learning_rate": 0.00014067366430758004,
+      "loss": 2.5113,
       "step": 43
     },
     {
       "epoch": 0.41169590643274856,
-      "grad_norm": 2.6688404083251953,
-      "learning_rate": 1.0899347581163221e-05,
-      "loss": 2.3434,
+      "grad_norm": 2.408841371536255,
+      "learning_rate": 0.00013746065934159123,
+      "loss": 2.3157,
       "step": 44
     },
     {
       "epoch": 0.42105263157894735,
-      "grad_norm": 2.8133082389831543,
-      "learning_rate": 7.612046748871327e-06,
-      "loss": 2.6974,
+      "grad_norm": 2.5375423431396484,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 2.676,
       "step": 45
     },
     {
       "epoch": 0.4304093567251462,
-      "grad_norm": 3.1550958156585693,
-      "learning_rate": 4.8943483704846475e-06,
-      "loss": 2.8442,
+      "grad_norm": 2.8962650299072266,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.8322,
       "step": 46
     },
     {
       "epoch": 0.439766081871345,
-      "grad_norm": 2.393209218978882,
-      "learning_rate": 2.7630079602323442e-06,
-      "loss": 2.3097,
+      "grad_norm": 2.144554615020752,
+      "learning_rate": 0.0001275637355816999,
+      "loss": 2.2713,
       "step": 47
     },
     {
       "epoch": 0.44912280701754387,
-      "grad_norm": 2.543856382369995,
-      "learning_rate": 1.231165940486234e-06,
-      "loss": 2.3707,
+      "grad_norm": 2.3191635608673096,
+      "learning_rate": 0.00012419218955996676,
+      "loss": 2.3502,
       "step": 48
     },
     {
       "epoch": 0.4584795321637427,
-      "grad_norm": 2.64045786857605,
-      "learning_rate": 3.0826662668720364e-07,
-      "loss": 2.6261,
+      "grad_norm": 2.344190835952759,
+      "learning_rate": 0.00012079116908177593,
+      "loss": 2.5839,
       "step": 49
     },
     {
       "epoch": 0.4678362573099415,
-      "grad_norm": 2.683619976043701,
-      "learning_rate": 0.0,
-      "loss": 2.5441,
+      "grad_norm": 2.446531295776367,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 2.5168,
+      "step": 50
+    },
+    {
+      "epoch": 0.4678362573099415,
+      "eval_loss": 2.3896028995513916,
+      "eval_runtime": 13.9611,
+      "eval_samples_per_second": 6.446,
+      "eval_steps_per_second": 6.446,
       "step": 50
     }
   ],
   "logging_steps": 1,
-  "max_steps": 50,
+  "max_steps": 100,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -403,7 +395,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcda8f02659f8934defef4e265587a384ef2bea0c9e7337b7be092c1ae1125f1
+oid sha256:36e637851f50326b005ac061988bdd65d45a6f285acb2c7b112447253753de7f
 size 6776