Update fine-tuned model

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d57abfb1995626406e3aeee2635cbf7ef4de508d19400e9f935699650285534
+oid sha256:6e65b62711fb40774e983ba8a155fe7b89d891c55de6cad3efb68a9dd6a37dbb
 size 159967880

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:914661d73dcb472dfac465b65b85ff1016e9cfd770b94d95e9ffab7bcfd0a48e
+oid sha256:ac7c2c248712d14a1c3022c85ad5228595efd998c1b12ab0b0f6155b591daddd
 size 852876198

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d6261dada0cbb2e61bb4c36e57a1530b123b847a587188b0b247cf1f8b69e2
+oid sha256:bafcd8d51eed71f7d6cebafbead90bc7049b2af7535b94c4ab6edd6700c7939b
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

trainer_state.json

@@ -1,718 +1,368 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.02,
-      "grad_norm": 0.3624022305011749,
-      "learning_rate": 2e-05,
-      "loss": 0.5345,
+      "grad_norm": 0.3415137231349945,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.4337,
       "step": 1
     },
     {
       "epoch": 0.04,
-      "grad_norm": 0.3736283481121063,
-      "learning_rate": 4e-05,
-      "loss": 0.5545,
+      "grad_norm": 0.33824849128723145,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.4472,
       "step": 2
     },
     {
       "epoch": 0.06,
-      "grad_norm": 0.3715187907218933,
-      "learning_rate": 6e-05,
-      "loss": 0.5167,
+      "grad_norm": 0.3517794609069824,
+      "learning_rate": 0.0002,
+      "loss": 0.4119,
       "step": 3
     },
     {
       "epoch": 0.08,
-      "grad_norm": 0.3104977607727051,
-      "learning_rate": 8e-05,
-      "loss": 0.4994,
+      "grad_norm": 0.49278953671455383,
+      "learning_rate": 0.00019977668786231534,
+      "loss": 0.4045,
       "step": 4
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.3549410104751587,
-      "learning_rate": 0.0001,
-      "loss": 0.5208,
+      "grad_norm": 0.5396780967712402,
+      "learning_rate": 0.000199107748815478,
+      "loss": 0.4354,
       "step": 5
     },
     {
       "epoch": 0.12,
-      "grad_norm": 0.41164880990982056,
-      "learning_rate": 9.997266286704631e-05,
-      "loss": 0.528,
+      "grad_norm": 0.5213820934295654,
+      "learning_rate": 0.0001979961705036587,
+      "loss": 0.4435,
       "step": 6
     },
     {
       "epoch": 0.14,
-      "grad_norm": 0.4071100354194641,
-      "learning_rate": 9.989068136093873e-05,
-      "loss": 0.5083,
+      "grad_norm": 0.42753931879997253,
+      "learning_rate": 0.00019644691750543767,
+      "loss": 0.4306,
       "step": 7
     },
     {
       "epoch": 0.16,
-      "grad_norm": 0.42801719903945923,
-      "learning_rate": 9.975414512725057e-05,
-      "loss": 0.5336,
+      "grad_norm": 0.46985888481140137,
+      "learning_rate": 0.0001944669091607919,
+      "loss": 0.4558,
       "step": 8
     },
     {
       "epoch": 0.18,
-      "grad_norm": 0.43720319867134094,
-      "learning_rate": 9.956320346634876e-05,
-      "loss": 0.5478,
+      "grad_norm": 0.44640442728996277,
+      "learning_rate": 0.00019206498866764288,
+      "loss": 0.4777,
       "step": 9
     },
     {
       "epoch": 0.2,
-      "grad_norm": 0.39605292677879333,
-      "learning_rate": 9.931806517013612e-05,
-      "loss": 0.5509,
+      "grad_norm": 0.4198346734046936,
+      "learning_rate": 0.00018925188358598813,
+      "loss": 0.4845,
       "step": 10
     },
     {
       "epoch": 0.22,
-      "grad_norm": 0.4373878240585327,
-      "learning_rate": 9.901899829374047e-05,
-      "loss": 0.4953,
+      "grad_norm": 0.43529659509658813,
+      "learning_rate": 0.00018604015792601396,
+      "loss": 0.4327,
       "step": 11
     },
     {
       "epoch": 0.24,
-      "grad_norm": 0.3865221440792084,
-      "learning_rate": 9.86663298624003e-05,
-      "loss": 0.5273,
+      "grad_norm": 0.4187154471874237,
+      "learning_rate": 0.00018244415603417603,
+      "loss": 0.4682,
       "step": 12
     },
     {
       "epoch": 0.26,
-      "grad_norm": 0.3498033881187439,
-      "learning_rate": 9.826044551386744e-05,
-      "loss": 0.5626,
+      "grad_norm": 0.4378308057785034,
+      "learning_rate": 0.0001784799385278661,
+      "loss": 0.5107,
       "step": 13
     },
     {
       "epoch": 0.28,
-      "grad_norm": 0.33049601316452026,
-      "learning_rate": 9.780178907671789e-05,
-      "loss": 0.5252,
+      "grad_norm": 0.40074899792671204,
+      "learning_rate": 0.00017416521056479577,
+      "loss": 0.4809,
       "step": 14
     },
     {
       "epoch": 0.3,
-      "grad_norm": 0.3525201082229614,
-      "learning_rate": 9.729086208503174e-05,
-      "loss": 0.5433,
+      "grad_norm": 0.4163818955421448,
+      "learning_rate": 0.00016951924276746425,
+      "loss": 0.4956,
       "step": 15
     },
     {
       "epoch": 0.32,
-      "grad_norm": 0.3323298990726471,
-      "learning_rate": 9.672822322997305e-05,
-      "loss": 0.5371,
+      "grad_norm": 0.39697593450546265,
+      "learning_rate": 0.00016456278515588024,
+      "loss": 0.4907,
       "step": 16
     },
     {
       "epoch": 0.34,
-      "grad_norm": 0.34475523233413696,
-      "learning_rate": 9.611448774886924e-05,
-      "loss": 0.5273,
+      "grad_norm": 0.4083729088306427,
+      "learning_rate": 0.00015931797447293552,
+      "loss": 0.4838,
       "step": 17
     },
     {
       "epoch": 0.36,
-      "grad_norm": 0.33978456258773804,
-      "learning_rate": 9.545032675245813e-05,
-      "loss": 0.5377,
+      "grad_norm": 0.38315674662590027,
+      "learning_rate": 0.00015380823531633729,
+      "loss": 0.4958,
       "step": 18
     },
     {
       "epoch": 0.38,
-      "grad_norm": 0.32446014881134033,
-      "learning_rate": 9.473646649103818e-05,
-      "loss": 0.5321,
+      "grad_norm": 0.37201324105262756,
+      "learning_rate": 0.00014805817551866838,
+      "loss": 0.4897,
       "step": 19
     },
     {
       "epoch": 0.4,
-      "grad_norm": 0.32642048597335815,
-      "learning_rate": 9.397368756032445e-05,
-      "loss": 0.5134,
+      "grad_norm": 0.37709081172943115,
+      "learning_rate": 0.0001420934762428335,
+      "loss": 0.4692,
       "step": 20
     },
     {
       "epoch": 0.42,
-      "grad_norm": 0.32789453864097595,
-      "learning_rate": 9.316282404787871e-05,
-      "loss": 0.5516,
+      "grad_norm": 0.37321537733078003,
+      "learning_rate": 0.00013594077728375128,
+      "loss": 0.5103,
       "step": 21
     },
     {
       "epoch": 0.44,
-      "grad_norm": 0.33384475111961365,
-      "learning_rate": 9.230476262104677e-05,
-      "loss": 0.5656,
+      "grad_norm": 0.38839632272720337,
+      "learning_rate": 0.00012962755808856342,
+      "loss": 0.5218,
       "step": 22
     },
     {
       "epoch": 0.46,
-      "grad_norm": 0.3290055990219116,
-      "learning_rate": 9.140044155740101e-05,
-      "loss": 0.5809,
+      "grad_norm": 0.37921735644340515,
+      "learning_rate": 0.00012318201502675285,
+      "loss": 0.5324,
       "step": 23
     },
     {
       "epoch": 0.48,
-      "grad_norm": 0.3402266204357147,
-      "learning_rate": 9.045084971874738e-05,
-      "loss": 0.5617,
+      "grad_norm": 0.4005667567253113,
+      "learning_rate": 0.00011663293545831302,
+      "loss": 0.5168,
       "step": 24
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.33358535170555115,
-      "learning_rate": 8.945702546981969e-05,
-      "loss": 0.5357,
+      "grad_norm": 0.37409457564353943,
+      "learning_rate": 0.00011000956916240985,
+      "loss": 0.4907,
       "step": 25
     },
     {
       "epoch": 0.52,
-      "grad_norm": 0.33832627534866333,
-      "learning_rate": 8.842005554284296e-05,
-      "loss": 0.5587,
+      "grad_norm": 0.3958514630794525,
+      "learning_rate": 0.00010334149770076747,
+      "loss": 0.5186,
       "step": 26
     },
     {
       "epoch": 0.54,
-      "grad_norm": 0.3213883638381958,
-      "learning_rate": 8.73410738492077e-05,
-      "loss": 0.5697,
+      "grad_norm": 0.38589972257614136,
+      "learning_rate": 9.665850229923258e-05,
+      "loss": 0.5282,
       "step": 27
     },
     {
       "epoch": 0.56,
-      "grad_norm": 0.34648266434669495,
-      "learning_rate": 8.622126023955446e-05,
-      "loss": 0.522,
+      "grad_norm": 0.3830341100692749,
+      "learning_rate": 8.999043083759017e-05,
+      "loss": 0.4814,
       "step": 28
     },
     {
       "epoch": 0.58,
-      "grad_norm": 0.3362743854522705,
-      "learning_rate": 8.506183921362443e-05,
-      "loss": 0.5572,
+      "grad_norm": 0.37159013748168945,
+      "learning_rate": 8.336706454168701e-05,
+      "loss": 0.5096,
       "step": 29
     },
     {
       "epoch": 0.6,
-      "grad_norm": 0.3271280825138092,
-      "learning_rate": 8.386407858128706e-05,
-      "loss": 0.514,
+      "grad_norm": 0.3702056109905243,
+      "learning_rate": 7.681798497324716e-05,
+      "loss": 0.4727,
       "step": 30
     },
     {
       "epoch": 0.62,
-      "grad_norm": 0.334176629781723,
-      "learning_rate": 8.262928807620843e-05,
-      "loss": 0.5092,
+      "grad_norm": 0.3684118688106537,
+      "learning_rate": 7.037244191143661e-05,
+      "loss": 0.4695,
       "step": 31
     },
     {
       "epoch": 0.64,
-      "grad_norm": 0.33813613653182983,
-      "learning_rate": 8.135881792367686e-05,
-      "loss": 0.57,
+      "grad_norm": 0.3787296712398529,
+      "learning_rate": 6.405922271624874e-05,
+      "loss": 0.5261,
       "step": 32
     },
     {
       "epoch": 0.66,
-      "grad_norm": 0.3526760935783386,
-      "learning_rate": 8.005405736415126e-05,
-      "loss": 0.5737,
+      "grad_norm": 0.39863407611846924,
+      "learning_rate": 5.790652375716652e-05,
+      "loss": 0.5312,
       "step": 33
     },
     {
       "epoch": 0.68,
-      "grad_norm": 0.3210213780403137,
-      "learning_rate": 7.871643313414718e-05,
-      "loss": 0.5444,
+      "grad_norm": 0.35908952355384827,
+      "learning_rate": 5.1941824481331626e-05,
+      "loss": 0.507,
       "step": 34
     },
     {
       "epoch": 0.7,
-      "grad_norm": 0.3287356197834015,
-      "learning_rate": 7.734740790612136e-05,
-      "loss": 0.5188,
+      "grad_norm": 0.37030553817749023,
+      "learning_rate": 4.6191764683662744e-05,
+      "loss": 0.4799,
       "step": 35
     },
     {
       "epoch": 0.72,
-      "grad_norm": 0.3406030535697937,
-      "learning_rate": 7.594847868906076e-05,
-      "loss": 0.5491,
+      "grad_norm": 0.3842332661151886,
+      "learning_rate": 4.0682025527064486e-05,
+      "loss": 0.5104,
       "step": 36
     },
     {
       "epoch": 0.74,
-      "grad_norm": 0.3229946792125702,
-      "learning_rate": 7.452117519152542e-05,
-      "loss": 0.5309,
+      "grad_norm": 0.3656119108200073,
+      "learning_rate": 3.543721484411976e-05,
+      "loss": 0.4926,
       "step": 37
     },
     {
       "epoch": 0.76,
-      "grad_norm": 0.31070253252983093,
-      "learning_rate": 7.30670581489344e-05,
-      "loss": 0.5348,
+      "grad_norm": 0.3526756763458252,
+      "learning_rate": 3.0480757232535772e-05,
+      "loss": 0.4962,
       "step": 38
     },
     {
       "epoch": 0.78,
-      "grad_norm": 0.31888288259506226,
-      "learning_rate": 7.158771761692464e-05,
-      "loss": 0.5598,
+      "grad_norm": 0.3747156858444214,
+      "learning_rate": 2.5834789435204243e-05,
+      "loss": 0.5222,
       "step": 39
     },
     {
       "epoch": 0.8,
-      "grad_norm": 0.3222619295120239,
-      "learning_rate": 7.008477123264848e-05,
-      "loss": 0.5674,
+      "grad_norm": 0.37097883224487305,
+      "learning_rate": 2.1520061472133902e-05,
+      "loss": 0.5288,
       "step": 40
     },
     {
       "epoch": 0.82,
-      "grad_norm": 0.3319852352142334,
-      "learning_rate": 6.855986244591104e-05,
-      "loss": 0.5371,
+      "grad_norm": 0.37520304322242737,
+      "learning_rate": 1.7555843965823992e-05,
+      "loss": 0.5005,
       "step": 41
     },
     {
       "epoch": 0.84,
-      "grad_norm": 0.30418190360069275,
-      "learning_rate": 6.701465872208216e-05,
-      "loss": 0.5104,
+      "grad_norm": 0.34392106533050537,
+      "learning_rate": 1.3959842073986085e-05,
+      "loss": 0.4774,
       "step": 42
     },
     {
       "epoch": 0.86,
-      "grad_norm": 0.3073510229587555,
-      "learning_rate": 6.545084971874738e-05,
-      "loss": 0.5359,
+      "grad_norm": 0.3575632572174072,
+      "learning_rate": 1.0748116414011888e-05,
+      "loss": 0.5033,
       "step": 43
     },
     {
       "epoch": 0.88,
-      "grad_norm": 0.3012188673019409,
-      "learning_rate": 6.387014543809223e-05,
-      "loss": 0.5341,
+      "grad_norm": 0.35089874267578125,
+      "learning_rate": 7.935011332357112e-06,
+      "loss": 0.5018,
       "step": 44
     },
     {
       "epoch": 0.9,
-      "grad_norm": 0.2977622151374817,
-      "learning_rate": 6.227427435703997e-05,
-      "loss": 0.5448,
+      "grad_norm": 0.3535928428173065,
+      "learning_rate": 5.533090839208133e-06,
+      "loss": 0.5141,
       "step": 45
     },
     {
       "epoch": 0.92,
-      "grad_norm": 0.312294065952301,
-      "learning_rate": 6.066498153718735e-05,
-      "loss": 0.5421,
+      "grad_norm": 0.37137070298194885,
+      "learning_rate": 3.5530824945623542e-06,
+      "loss": 0.5101,
       "step": 46
     },
     {
       "epoch": 0.94,
-      "grad_norm": 0.33205491304397583,
-      "learning_rate": 5.90440267166055e-05,
-      "loss": 0.5841,
+      "grad_norm": 0.38077953457832336,
+      "learning_rate": 2.003829496341325e-06,
+      "loss": 0.5513,
       "step": 47
     },
     {
       "epoch": 0.96,
-      "grad_norm": 0.31330958008766174,
-      "learning_rate": 5.74131823855921e-05,
-      "loss": 0.5344,
+      "grad_norm": 0.3571460545063019,
+      "learning_rate": 8.922511845219971e-07,
+      "loss": 0.5074,
       "step": 48
     },
     {
       "epoch": 0.98,
-      "grad_norm": 0.32422611117362976,
-      "learning_rate": 5.577423184847932e-05,
-      "loss": 0.5277,
+      "grad_norm": 0.34851184487342834,
+      "learning_rate": 2.2331213768468363e-07,
+      "loss": 0.4974,
       "step": 49
     },
     {
       "epoch": 1.0,
-      "grad_norm": 0.3156668245792389,
-      "learning_rate": 5.4128967273616625e-05,
-      "loss": 0.5454,
-      "step": 50
-    },
-    {
-      "epoch": 1.02,
-      "grad_norm": 0.3290346562862396,
-      "learning_rate": 5.247918773366112e-05,
-      "loss": 0.4873,
-      "step": 51
-    },
-    {
-      "epoch": 1.04,
-      "grad_norm": 0.3424556255340576,
-      "learning_rate": 5.0826697238317935e-05,
-      "loss": 0.4639,
-      "step": 52
-    },
-    {
-      "epoch": 1.06,
-      "grad_norm": 0.31981292366981506,
-      "learning_rate": 4.917330276168208e-05,
-      "loss": 0.459,
-      "step": 53
-    },
-    {
-      "epoch": 1.08,
-      "grad_norm": 0.3340217173099518,
-      "learning_rate": 4.7520812266338885e-05,
-      "loss": 0.4981,
-      "step": 54
-    },
-    {
-      "epoch": 1.1,
-      "grad_norm": 0.3345750868320465,
-      "learning_rate": 4.5871032726383386e-05,
-      "loss": 0.4898,
-      "step": 55
-    },
-    {
-      "epoch": 1.12,
-      "grad_norm": 0.2998408079147339,
-      "learning_rate": 4.4225768151520694e-05,
-      "loss": 0.4329,
-      "step": 56
-    },
-    {
-      "epoch": 1.1400000000000001,
-      "grad_norm": 0.33386602997779846,
-      "learning_rate": 4.2586817614407895e-05,
-      "loss": 0.43,
-      "step": 57
-    },
-    {
-      "epoch": 1.16,
-      "grad_norm": 0.3249485492706299,
-      "learning_rate": 4.095597328339452e-05,
-      "loss": 0.4762,
-      "step": 58
-    },
-    {
-      "epoch": 1.18,
-      "grad_norm": 0.32801133394241333,
-      "learning_rate": 3.933501846281267e-05,
-      "loss": 0.4514,
-      "step": 59
-    },
-    {
-      "epoch": 1.2,
-      "grad_norm": 0.32089194655418396,
-      "learning_rate": 3.772572564296005e-05,
-      "loss": 0.4206,
-      "step": 60
-    },
-    {
-      "epoch": 1.22,
-      "grad_norm": 0.32813841104507446,
-      "learning_rate": 3.612985456190778e-05,
-      "loss": 0.4853,
-      "step": 61
-    },
-    {
-      "epoch": 1.24,
-      "grad_norm": 0.33598625659942627,
-      "learning_rate": 3.4549150281252636e-05,
-      "loss": 0.4334,
-      "step": 62
-    },
-    {
-      "epoch": 1.26,
-      "grad_norm": 0.3225085139274597,
-      "learning_rate": 3.298534127791785e-05,
-      "loss": 0.4479,
-      "step": 63
-    },
-    {
-      "epoch": 1.28,
-      "grad_norm": 0.3295815885066986,
-      "learning_rate": 3.144013755408895e-05,
-      "loss": 0.4739,
-      "step": 64
-    },
-    {
-      "epoch": 1.3,
-      "grad_norm": 0.3391561508178711,
-      "learning_rate": 2.991522876735154e-05,
-      "loss": 0.4211,
-      "step": 65
-    },
-    {
-      "epoch": 1.32,
-      "grad_norm": 0.3367979824542999,
-      "learning_rate": 2.8412282383075363e-05,
-      "loss": 0.4502,
-      "step": 66
-    },
-    {
-      "epoch": 1.34,
-      "grad_norm": 0.3409813344478607,
-      "learning_rate": 2.693294185106562e-05,
-      "loss": 0.4886,
-      "step": 67
-    },
-    {
-      "epoch": 1.3599999999999999,
-      "grad_norm": 0.33046984672546387,
-      "learning_rate": 2.547882480847461e-05,
-      "loss": 0.4142,
-      "step": 68
-    },
-    {
-      "epoch": 1.38,
-      "grad_norm": 0.3314824104309082,
-      "learning_rate": 2.405152131093926e-05,
-      "loss": 0.4535,
-      "step": 69
-    },
-    {
-      "epoch": 1.4,
-      "grad_norm": 0.34188470244407654,
-      "learning_rate": 2.2652592093878666e-05,
-      "loss": 0.4525,
-      "step": 70
-    },
-    {
-      "epoch": 1.42,
-      "grad_norm": 0.3405551612377167,
-      "learning_rate": 2.128356686585282e-05,
-      "loss": 0.4306,
-      "step": 71
-    },
-    {
-      "epoch": 1.44,
-      "grad_norm": 0.34439051151275635,
-      "learning_rate": 1.9945942635848748e-05,
-      "loss": 0.4849,
-      "step": 72
-    },
-    {
-      "epoch": 1.46,
-      "grad_norm": 0.33053305745124817,
-      "learning_rate": 1.8641182076323148e-05,
-      "loss": 0.4395,
-      "step": 73
-    },
-    {
-      "epoch": 1.48,
-      "grad_norm": 0.3231377601623535,
-      "learning_rate": 1.7370711923791567e-05,
-      "loss": 0.4461,
-      "step": 74
-    },
-    {
-      "epoch": 1.5,
-      "grad_norm": 0.3283744752407074,
-      "learning_rate": 1.6135921418712956e-05,
-      "loss": 0.4322,
-      "step": 75
-    },
-    {
-      "epoch": 1.52,
-      "grad_norm": 0.3327557146549225,
-      "learning_rate": 1.4938160786375572e-05,
-      "loss": 0.4796,
-      "step": 76
-    },
-    {
-      "epoch": 1.54,
-      "grad_norm": 0.3517839312553406,
-      "learning_rate": 1.3778739760445552e-05,
-      "loss": 0.4617,
-      "step": 77
-    },
-    {
-      "epoch": 1.56,
-      "grad_norm": 0.3397415578365326,
-      "learning_rate": 1.2658926150792322e-05,
-      "loss": 0.4561,
-      "step": 78
-    },
-    {
-      "epoch": 1.58,
-      "grad_norm": 0.32547858357429504,
-      "learning_rate": 1.157994445715706e-05,
-      "loss": 0.4522,
-      "step": 79
-    },
-    {
-      "epoch": 1.6,
-      "grad_norm": 0.322001576423645,
-      "learning_rate": 1.0542974530180327e-05,
-      "loss": 0.4275,
-      "step": 80
-    },
-    {
-      "epoch": 1.62,
-      "grad_norm": 0.32253459095954895,
-      "learning_rate": 9.549150281252633e-06,
-      "loss": 0.4388,
-      "step": 81
-    },
-    {
-      "epoch": 1.6400000000000001,
-      "grad_norm": 0.33204764127731323,
-      "learning_rate": 8.599558442598998e-06,
-      "loss": 0.4317,
-      "step": 82
-    },
-    {
-      "epoch": 1.6600000000000001,
-      "grad_norm": 0.32604044675827026,
-      "learning_rate": 7.695237378953223e-06,
-      "loss": 0.4357,
-      "step": 83
-    },
-    {
-      "epoch": 1.6800000000000002,
-      "grad_norm": 0.34298455715179443,
-      "learning_rate": 6.837175952121306e-06,
-      "loss": 0.442,
-      "step": 84
-    },
-    {
-      "epoch": 1.7,
-      "grad_norm": 0.3202356994152069,
-      "learning_rate": 6.026312439675552e-06,
-      "loss": 0.4342,
-      "step": 85
-    },
-    {
-      "epoch": 1.72,
-      "grad_norm": 0.3258272409439087,
-      "learning_rate": 5.263533508961827e-06,
-      "loss": 0.4348,
-      "step": 86
-    },
-    {
-      "epoch": 1.74,
-      "grad_norm": 0.3249031901359558,
-      "learning_rate": 4.549673247541875e-06,
-      "loss": 0.4093,
-      "step": 87
-    },
-    {
-      "epoch": 1.76,
-      "grad_norm": 0.32874855399131775,
-      "learning_rate": 3.885512251130763e-06,
-      "loss": 0.4076,
-      "step": 88
-    },
-    {
-      "epoch": 1.78,
-      "grad_norm": 0.33212965726852417,
-      "learning_rate": 3.271776770026963e-06,
-      "loss": 0.4426,
-      "step": 89
-    },
-    {
-      "epoch": 1.8,
-      "grad_norm": 0.32816311717033386,
-      "learning_rate": 2.7091379149682685e-06,
-      "loss": 0.4422,
-      "step": 90
-    },
-    {
-      "epoch": 1.8199999999999998,
-      "grad_norm": 0.333683580160141,
-      "learning_rate": 2.1982109232821178e-06,
-      "loss": 0.4619,
-      "step": 91
-    },
-    {
-      "epoch": 1.8399999999999999,
-      "grad_norm": 0.3273014724254608,
-      "learning_rate": 1.7395544861325718e-06,
-      "loss": 0.4662,
-      "step": 92
-    },
-    {
-      "epoch": 1.8599999999999999,
-      "grad_norm": 0.33303171396255493,
-      "learning_rate": 1.333670137599713e-06,
-      "loss": 0.4467,
-      "step": 93
-    },
-    {
-      "epoch": 1.88,
-      "grad_norm": 0.3208991587162018,
-      "learning_rate": 9.810017062595322e-07,
-      "loss": 0.4459,
-      "step": 94
-    },
-    {
-      "epoch": 1.9,
-      "grad_norm": 0.3281053304672241,
-      "learning_rate": 6.819348298638839e-07,
-      "loss": 0.4471,
-      "step": 95
-    },
-    {
-      "epoch": 1.92,
-      "grad_norm": 0.31943386793136597,
-      "learning_rate": 4.367965336512403e-07,
-      "loss": 0.4342,
-      "step": 96
-    },
-    {
-      "epoch": 1.94,
-      "grad_norm": 0.3442579507827759,
-      "learning_rate": 2.458548727494292e-07,
-      "loss": 0.454,
-      "step": 97
-    },
-    {
-      "epoch": 1.96,
-      "grad_norm": 0.3283260762691498,
-      "learning_rate": 1.0931863906127327e-07,
-      "loss": 0.4328,
-      "step": 98
-    },
-    {
-      "epoch": 1.98,
-      "grad_norm": 0.33244219422340393,
-      "learning_rate": 2.7337132953697554e-08,
-      "loss": 0.4145,
-      "step": 99
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 0.3326053321361542,
+      "grad_norm": 0.3630204200744629,
       "learning_rate": 0.0,
-      "loss": 0.4836,
-      "step": 100
+      "loss": 0.52,
+      "step": 50
     }
   ],
   "logging_steps": 1,
-  "max_steps": 100,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -726,7 +376,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.211706059414569e+17,
+  "total_flos": 6.058530297072845e+16,
   "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 sha256:3991df946dfe0faf0ca3dbffd32bec5aefcf4baf342b73addfac6fc0a9b22d2f
+oid sha256:59162a93435cfb36bf3c4a8d8a4d01733f1556bb641b2341bd8c5982db4beb61
 size 5240