Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:299e14e199d99f2186b7062868e1a5691909e05241c4f4d12f8927273aa7c7f4
+oid sha256:01a9e050224b3c272740989cfabb3544f86aec34edd482e680e15071867ef3e2
 size 1540577008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca229c2cf19b6a65b0f9ec8abfcb44b522c1caa75d6d8332038337af7197f5a8
+oid sha256:37076c30930c41ccdea85aa6688eae613d6e940ec3d34809031f0718a1a6f7ee
 size 1695317131

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b6bed560ba82ad938724499dcd6b1144659f41214cf5bc1f5da6347e162b25
+oid sha256:9079206c3c25e14fa2f8a19a24a32c2e5380266de4ccca26cb728acd92fae5e8
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2b96950726cb5d1ecc220f8fe4a4ed97580d0d059753b7132b783c68be6714
+oid sha256:928cbfa65b99703b5bf1d60c465c9c16cef0c309f2e79c7b70d53048326d3c49
 size 1465

last-checkpoint/trainer_state.json

@@ -2,888 +2,450 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12,
+  "epoch": 0.06,
   "eval_steps": 150,
-  "global_step": 600,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.001,
-      "grad_norm": 0.5131137371063232,
-      "learning_rate": 6.4e-08,
-      "loss": 10.957261657714843,
+      "grad_norm": 0.541594386100769,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 10.997595977783202,
       "step": 5
     },
     {
       "epoch": 0.002,
-      "grad_norm": 0.5448781251907349,
-      "learning_rate": 1.44e-07,
-      "loss": 10.8884033203125,
+      "grad_norm": 0.550841212272644,
+      "learning_rate": 1.44e-05,
+      "loss": 10.93243865966797,
       "step": 10
     },
     {
       "epoch": 0.003,
-      "grad_norm": 0.5491417646408081,
-      "learning_rate": 2.24e-07,
-      "loss": 10.823747253417968,
+      "grad_norm": 0.5471506714820862,
+      "learning_rate": 2.2400000000000002e-05,
+      "loss": 10.8595703125,
       "step": 15
     },
     {
       "epoch": 0.004,
-      "grad_norm": 0.556300163269043,
-      "learning_rate": 3.0399999999999997e-07,
-      "loss": 10.758411407470703,
+      "grad_norm": 0.5520158410072327,
+      "learning_rate": 3.04e-05,
+      "loss": 10.787896728515625,
       "step": 20
     },
     {
       "epoch": 0.005,
-      "grad_norm": 0.6397489309310913,
-      "learning_rate": 3.84e-07,
-      "loss": 10.67077407836914,
+      "grad_norm": 0.6384730339050293,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 10.68493423461914,
       "step": 25
     },
     {
       "epoch": 0.006,
-      "grad_norm": 0.6714406609535217,
-      "learning_rate": 4.64e-07,
-      "loss": 10.603721618652344,
+      "grad_norm": 0.6661590337753296,
+      "learning_rate": 4.64e-05,
+      "loss": 10.593788146972656,
       "step": 30
     },
     {
       "epoch": 0.007,
-      "grad_norm": 0.7375972270965576,
-      "learning_rate": 5.44e-07,
-      "loss": 10.503799438476562,
+      "grad_norm": 0.7120365500450134,
+      "learning_rate": 5.440000000000001e-05,
+      "loss": 10.463143157958985,
       "step": 35
     },
     {
       "epoch": 0.008,
-      "grad_norm": 0.6434732675552368,
-      "learning_rate": 6.24e-07,
-      "loss": 10.438059997558593,
+      "grad_norm": 0.6313916444778442,
+      "learning_rate": 6.24e-05,
+      "loss": 10.36687774658203,
       "step": 40
     },
     {
       "epoch": 0.009,
-      "grad_norm": 0.7892774939537048,
-      "learning_rate": 7.04e-07,
-      "loss": 10.297109222412109,
+      "grad_norm": 0.6490567922592163,
+      "learning_rate": 7.04e-05,
+      "loss": 10.178239440917968,
       "step": 45
     },
     {
       "epoch": 0.01,
-      "grad_norm": 0.6715490221977234,
-      "learning_rate": 7.84e-07,
-      "loss": 10.194837188720703,
+      "grad_norm": 0.6117688417434692,
+      "learning_rate": 7.840000000000001e-05,
+      "loss": 10.030424499511719,
       "step": 50
     },
     {
       "epoch": 0.011,
-      "grad_norm": 0.644976794719696,
-      "learning_rate": 8.639999999999999e-07,
-      "loss": 10.094287109375,
+      "grad_norm": 0.6446435451507568,
+      "learning_rate": 8.64e-05,
+      "loss": 9.86950225830078,
       "step": 55
     },
     {
       "epoch": 0.012,
-      "grad_norm": 0.643751859664917,
-      "learning_rate": 9.439999999999999e-07,
-      "loss": 9.97855453491211,
+      "grad_norm": 0.5392746329307556,
+      "learning_rate": 9.44e-05,
+      "loss": 9.688623046875,
       "step": 60
     },
     {
       "epoch": 0.013,
-      "grad_norm": 0.640312910079956,
-      "learning_rate": 1.024e-06,
-      "loss": 9.856808471679688,
+      "grad_norm": 0.5041754841804504,
+      "learning_rate": 0.00010240000000000001,
+      "loss": 9.514056396484374,
       "step": 65
     },
     {
       "epoch": 0.014,
-      "grad_norm": 0.6511930823326111,
-      "learning_rate": 1.1040000000000001e-06,
-      "loss": 9.75417251586914,
+      "grad_norm": 0.4725438058376312,
+      "learning_rate": 0.00011040000000000001,
+      "loss": 9.406781005859376,
       "step": 70
     },
     {
       "epoch": 0.015,
-      "grad_norm": 0.6131484508514404,
-      "learning_rate": 1.1839999999999998e-06,
-      "loss": 9.632675170898438,
+      "grad_norm": 0.42810311913490295,
+      "learning_rate": 0.0001184,
+      "loss": 9.310884857177735,
       "step": 75
     },
     {
       "epoch": 0.016,
-      "grad_norm": 0.605525553226471,
-      "learning_rate": 1.2639999999999999e-06,
-      "loss": 9.530663299560548,
+      "grad_norm": 0.41262492537498474,
+      "learning_rate": 0.0001264,
+      "loss": 9.21496810913086,
       "step": 80
     },
     {
       "epoch": 0.017,
-      "grad_norm": 0.5865434408187866,
-      "learning_rate": 1.344e-06,
-      "loss": 9.533056640625,
+      "grad_norm": 0.424248069524765,
+      "learning_rate": 0.00013440000000000001,
+      "loss": 9.244066619873047,
       "step": 85
     },
     {
       "epoch": 0.018,
-      "grad_norm": 0.6370518207550049,
-      "learning_rate": 1.4239999999999998e-06,
-      "loss": 9.445852661132813,
+      "grad_norm": 0.4215868413448334,
+      "learning_rate": 0.0001424,
+      "loss": 9.153144073486327,
       "step": 90
     },
     {
       "epoch": 0.019,
-      "grad_norm": 0.517352283000946,
-      "learning_rate": 1.504e-06,
-      "loss": 9.347330474853516,
+      "grad_norm": 0.4235755503177643,
+      "learning_rate": 0.0001504,
+      "loss": 9.029894256591797,
       "step": 95
     },
     {
       "epoch": 0.02,
-      "grad_norm": 0.6384696960449219,
-      "learning_rate": 1.584e-06,
-      "loss": 9.231375122070313,
+      "grad_norm": 0.47701263427734375,
+      "learning_rate": 0.00015840000000000003,
+      "loss": 8.909495544433593,
       "step": 100
     },
     {
       "epoch": 0.021,
-      "grad_norm": 0.5805168151855469,
-      "learning_rate": 1.6639999999999999e-06,
-      "loss": 9.230397796630859,
+      "grad_norm": 0.5133949518203735,
+      "learning_rate": 0.0001664,
+      "loss": 8.913885498046875,
       "step": 105
     },
     {
       "epoch": 0.022,
-      "grad_norm": 0.5052227973937988,
-      "learning_rate": 1.744e-06,
-      "loss": 9.230642700195313,
+      "grad_norm": 0.43619266152381897,
+      "learning_rate": 0.0001744,
+      "loss": 8.908492279052734,
       "step": 110
     },
     {
       "epoch": 0.023,
-      "grad_norm": 0.5524439811706543,
-      "learning_rate": 1.824e-06,
-      "loss": 9.179952239990234,
+      "grad_norm": 0.46515771746635437,
+      "learning_rate": 0.00018240000000000002,
+      "loss": 8.857489013671875,
       "step": 115
     },
     {
       "epoch": 0.024,
-      "grad_norm": 0.5470523238182068,
-      "learning_rate": 1.904e-06,
-      "loss": 9.130237579345703,
+      "grad_norm": 0.441704660654068,
+      "learning_rate": 0.0001904,
+      "loss": 8.795072174072265,
       "step": 120
     },
     {
       "epoch": 0.025,
-      "grad_norm": 0.5232647657394409,
-      "learning_rate": 1.984e-06,
-      "loss": 9.082659912109374,
+      "grad_norm": 0.4623314142227173,
+      "learning_rate": 0.0001984,
+      "loss": 8.735992431640625,
       "step": 125
     },
     {
       "epoch": 0.026,
-      "grad_norm": 0.47292640805244446,
-      "learning_rate": 2.064e-06,
-      "loss": 9.097735595703124,
+      "grad_norm": 0.3829725980758667,
+      "learning_rate": 0.0002064,
+      "loss": 8.752758026123047,
       "step": 130
     },
     {
       "epoch": 0.027,
-      "grad_norm": 0.4722849726676941,
-      "learning_rate": 2.144e-06,
-      "loss": 9.046373748779297,
+      "grad_norm": 0.34829118847846985,
+      "learning_rate": 0.00021440000000000003,
+      "loss": 8.698936462402344,
       "step": 135
     },
     {
       "epoch": 0.028,
-      "grad_norm": 0.4748806655406952,
-      "learning_rate": 2.2240000000000002e-06,
-      "loss": 9.014337921142578,
+      "grad_norm": 0.4280807375907898,
+      "learning_rate": 0.00022240000000000004,
+      "loss": 8.654257202148438,
       "step": 140
     },
     {
       "epoch": 0.029,
-      "grad_norm": 0.4592997133731842,
-      "learning_rate": 2.304e-06,
-      "loss": 8.961915588378906,
+      "grad_norm": 0.3860580325126648,
+      "learning_rate": 0.0002304,
+      "loss": 8.588265991210937,
       "step": 145
     },
     {
       "epoch": 0.03,
-      "grad_norm": 0.43399059772491455,
-      "learning_rate": 2.384e-06,
-      "loss": 8.965023040771484,
+      "grad_norm": 0.3843490481376648,
+      "learning_rate": 0.0002384,
+      "loss": 8.613517761230469,
       "step": 150
     },
     {
       "epoch": 0.03,
-      "eval_accuracy": 0.10875213675213675,
-      "eval_loss": 8.931988716125488,
-      "eval_runtime": 10.0631,
-      "eval_samples_per_second": 9.937,
-      "eval_steps_per_second": 1.689,
+      "eval_accuracy": 0.1278876678876679,
+      "eval_loss": 8.568678855895996,
+      "eval_runtime": 10.0729,
+      "eval_samples_per_second": 9.928,
+      "eval_steps_per_second": 1.688,
       "step": 150
     },
     {
       "epoch": 0.031,
-      "grad_norm": 0.39372554421424866,
-      "learning_rate": 2.464e-06,
-      "loss": 8.943362426757812,
+      "grad_norm": 0.3538966774940491,
+      "learning_rate": 0.0002464,
+      "loss": 8.57271957397461,
       "step": 155
     },
     {
       "epoch": 0.032,
-      "grad_norm": 0.4504595100879669,
-      "learning_rate": 2.544e-06,
-      "loss": 8.912525177001953,
+      "grad_norm": 0.4051172435283661,
+      "learning_rate": 0.0002544,
+      "loss": 8.543965911865234,
       "step": 160
     },
     {
       "epoch": 0.033,
-      "grad_norm": 0.4033423960208893,
-      "learning_rate": 2.624e-06,
-      "loss": 8.891281127929688,
+      "grad_norm": 0.35977786779403687,
+      "learning_rate": 0.00026240000000000004,
+      "loss": 8.521247863769531,
       "step": 165
     },
     {
       "epoch": 0.034,
-      "grad_norm": 0.4079058766365051,
-      "learning_rate": 2.704e-06,
-      "loss": 8.832948303222656,
+      "grad_norm": 0.3093051314353943,
+      "learning_rate": 0.0002704,
+      "loss": 8.447119903564452,
       "step": 170
     },
     {
       "epoch": 0.035,
-      "grad_norm": 0.4341174066066742,
-      "learning_rate": 2.7839999999999995e-06,
-      "loss": 8.736992645263673,
+      "grad_norm": 0.3675788342952728,
+      "learning_rate": 0.0002784,
+      "loss": 8.352106475830078,
       "step": 175
     },
     {
       "epoch": 0.036,
-      "grad_norm": 0.4039728045463562,
-      "learning_rate": 2.8639999999999996e-06,
-      "loss": 8.764207458496093,
+      "grad_norm": 0.3488416373729706,
+      "learning_rate": 0.0002864,
+      "loss": 8.375956726074218,
       "step": 180
     },
     {
       "epoch": 0.037,
-      "grad_norm": 0.48787590861320496,
-      "learning_rate": 2.9439999999999997e-06,
-      "loss": 8.90152587890625,
+      "grad_norm": 0.4550418555736542,
+      "learning_rate": 0.0002944,
+      "loss": 8.539746856689453,
       "step": 185
     },
     {
       "epoch": 0.038,
-      "grad_norm": 0.4344586730003357,
-      "learning_rate": 3.0239999999999998e-06,
-      "loss": 8.79043197631836,
+      "grad_norm": 0.4015609323978424,
+      "learning_rate": 0.00030240000000000003,
+      "loss": 8.388836669921876,
       "step": 190
     },
     {
       "epoch": 0.039,
-      "grad_norm": 0.3761419653892517,
-      "learning_rate": 3.104e-06,
-      "loss": 8.768655395507812,
+      "grad_norm": 0.3297787308692932,
+      "learning_rate": 0.0003104,
+      "loss": 8.376402282714844,
       "step": 195
     },
     {
       "epoch": 0.04,
-      "grad_norm": 0.40232253074645996,
-      "learning_rate": 3.184e-06,
-      "loss": 8.727652740478515,
+      "grad_norm": 0.3928952217102051,
+      "learning_rate": 0.00031840000000000004,
+      "loss": 8.331494140625,
       "step": 200
     },
     {
       "epoch": 0.041,
-      "grad_norm": 0.4565980136394501,
-      "learning_rate": 3.2639999999999996e-06,
-      "loss": 8.654769134521484,
+      "grad_norm": 0.3978789746761322,
+      "learning_rate": 0.0003264,
+      "loss": 8.267201995849609,
       "step": 205
     },
     {
       "epoch": 0.042,
-      "grad_norm": 0.3786274492740631,
-      "learning_rate": 3.3439999999999997e-06,
-      "loss": 8.736286926269532,
+      "grad_norm": 0.35222581028938293,
+      "learning_rate": 0.0003344,
+      "loss": 8.33883285522461,
       "step": 210
     },
     {
       "epoch": 0.043,
-      "grad_norm": 0.3933294415473938,
-      "learning_rate": 3.4239999999999997e-06,
-      "loss": 8.671070861816407,
+      "grad_norm": 0.34856143593788147,
+      "learning_rate": 0.00034240000000000003,
+      "loss": 8.259492492675781,
       "step": 215
     },
     {
       "epoch": 0.044,
-      "grad_norm": 0.4195927083492279,
-      "learning_rate": 3.504e-06,
-      "loss": 8.66961898803711,
+      "grad_norm": 0.38233524560928345,
+      "learning_rate": 0.0003504,
+      "loss": 8.267060852050781,
       "step": 220
     },
     {
       "epoch": 0.045,
-      "grad_norm": 0.3836154043674469,
-      "learning_rate": 3.584e-06,
-      "loss": 8.615521240234376,
+      "grad_norm": 0.3278593420982361,
+      "learning_rate": 0.00035840000000000004,
+      "loss": 8.20487289428711,
       "step": 225
     },
     {
       "epoch": 0.046,
-      "grad_norm": 0.41303297877311707,
-      "learning_rate": 3.664e-06,
-      "loss": 8.627992248535156,
+      "grad_norm": 0.37537282705307007,
+      "learning_rate": 0.0003664,
+      "loss": 8.216254425048827,
       "step": 230
     },
     {
       "epoch": 0.047,
-      "grad_norm": 0.4286525547504425,
-      "learning_rate": 3.744e-06,
-      "loss": 8.595711517333985,
+      "grad_norm": 0.41651761531829834,
+      "learning_rate": 0.00037440000000000005,
+      "loss": 8.180746459960938,
       "step": 235
     },
     {
       "epoch": 0.048,
-      "grad_norm": 0.3865108788013458,
-      "learning_rate": 3.823999999999999e-06,
-      "loss": 8.616091918945312,
+      "grad_norm": 0.3697809875011444,
+      "learning_rate": 0.0003824,
+      "loss": 8.194245910644531,
       "step": 240
     },
     {
       "epoch": 0.049,
-      "grad_norm": 0.4198671281337738,
-      "learning_rate": 3.903999999999999e-06,
-      "loss": 8.540158081054688,
+      "grad_norm": 0.3911236822605133,
+      "learning_rate": 0.0003904,
+      "loss": 8.119849395751952,
       "step": 245
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.5092390179634094,
-      "learning_rate": 3.9839999999999995e-06,
-      "loss": 8.554955291748048,
+      "grad_norm": 0.4369955360889435,
+      "learning_rate": 0.00039840000000000003,
+      "loss": 8.130778503417968,
       "step": 250
     },
     {
       "epoch": 0.051,
-      "grad_norm": 0.39753150939941406,
-      "learning_rate": 3.99999300106024e-06,
-      "loss": 8.531331634521484,
+      "grad_norm": 0.34227898716926575,
+      "learning_rate": 0.0003999993001060241,
+      "loss": 8.120016479492188,
       "step": 255
     },
     {
       "epoch": 0.052,
-      "grad_norm": 0.382576584815979,
-      "learning_rate": 3.9999645679514235e-06,
-      "loss": 8.556974792480469,
+      "grad_norm": 0.33067235350608826,
+      "learning_rate": 0.00039999645679514236,
+      "loss": 8.143791198730469,
       "step": 260
     },
     {
       "epoch": 0.053,
-      "grad_norm": 0.3579820394515991,
-      "learning_rate": 3.999914263550513e-06,
-      "loss": 8.572657012939453,
+      "grad_norm": 0.3268544375896454,
+      "learning_rate": 0.00039999142635505135,
+      "loss": 8.166898345947265,
       "step": 265
     },
     {
       "epoch": 0.054,
-      "grad_norm": 0.6057927012443542,
-      "learning_rate": 3.9998420884076325e-06,
-      "loss": 8.486345672607422,
+      "grad_norm": 0.5480589866638184,
+      "learning_rate": 0.00039998420884076324,
+      "loss": 8.070804595947266,
       "step": 270
     },
     {
       "epoch": 0.055,
-      "grad_norm": 0.3516131639480591,
-      "learning_rate": 3.999748043312075e-06,
-      "loss": 8.500395202636719,
+      "grad_norm": 0.3590603172779083,
+      "learning_rate": 0.00039997480433120753,
+      "loss": 8.069869995117188,
       "step": 275
     },
     {
       "epoch": 0.056,
-      "grad_norm": 0.39441752433776855,
-      "learning_rate": 3.999632129292304e-06,
-      "loss": 8.484166717529297,
+      "grad_norm": 0.35152456164360046,
+      "learning_rate": 0.00039996321292923043,
+      "loss": 8.04738540649414,
       "step": 280
     },
     {
       "epoch": 0.057,
-      "grad_norm": 0.42147520184516907,
-      "learning_rate": 3.9994943476159364e-06,
-      "loss": 8.458255004882812,
+      "grad_norm": 0.3499545156955719,
+      "learning_rate": 0.00039994943476159367,
+      "loss": 8.03879623413086,
       "step": 285
     },
     {
       "epoch": 0.058,
-      "grad_norm": 0.3418014347553253,
-      "learning_rate": 3.999334699789731e-06,
-      "loss": 8.439933013916015,
+      "grad_norm": 0.29000213742256165,
+      "learning_rate": 0.00039993346997897316,
+      "loss": 8.007131958007813,
       "step": 290
     },
     {
       "epoch": 0.059,
-      "grad_norm": 0.392968088388443,
-      "learning_rate": 3.99915318755957e-06,
-      "loss": 8.47509536743164,
+      "grad_norm": 0.3708847761154175,
+      "learning_rate": 0.00039991531875595705,
+      "loss": 8.036698913574218,
       "step": 295
     },
     {
       "epoch": 0.06,
-      "grad_norm": 0.35503852367401123,
-      "learning_rate": 3.9989498129104425e-06,
-      "loss": 8.460848236083985,
+      "grad_norm": 0.3241623640060425,
+      "learning_rate": 0.0003998949812910443,
+      "loss": 8.021849822998046,
       "step": 300
     },
     {
       "epoch": 0.06,
-      "eval_accuracy": 0.11944810744810745,
-      "eval_loss": 8.447799682617188,
-      "eval_runtime": 9.9265,
-      "eval_samples_per_second": 10.074,
+      "eval_accuracy": 0.1364126984126984,
+      "eval_loss": 8.011240005493164,
+      "eval_runtime": 9.9246,
+      "eval_samples_per_second": 10.076,
       "eval_steps_per_second": 1.713,
       "step": 300
-    },
-    {
-      "epoch": 0.061,
-      "grad_norm": 0.39879587292671204,
-      "learning_rate": 3.998724578066421e-06,
-      "loss": 8.460777282714844,
-      "step": 305
-    },
-    {
-      "epoch": 0.062,
-      "grad_norm": 0.39906880259513855,
-      "learning_rate": 3.998477485490638e-06,
-      "loss": 8.430789184570312,
-      "step": 310
-    },
-    {
-      "epoch": 0.063,
-      "grad_norm": 0.35292986035346985,
-      "learning_rate": 3.998208537885259e-06,
-      "loss": 8.430660247802734,
-      "step": 315
-    },
-    {
-      "epoch": 0.064,
-      "grad_norm": 0.346780002117157,
-      "learning_rate": 3.997917738191449e-06,
-      "loss": 8.45125732421875,
-      "step": 320
-    },
-    {
-      "epoch": 0.065,
-      "grad_norm": 0.5084764361381531,
-      "learning_rate": 3.99760508958935e-06,
-      "loss": 8.386634826660156,
-      "step": 325
-    },
-    {
-      "epoch": 0.066,
-      "grad_norm": 0.40600430965423584,
-      "learning_rate": 3.997270595498036e-06,
-      "loss": 8.341055297851563,
-      "step": 330
-    },
-    {
-      "epoch": 0.067,
-      "grad_norm": 0.34203389286994934,
-      "learning_rate": 3.99691425957548e-06,
-      "loss": 8.48632354736328,
-      "step": 335
-    },
-    {
-      "epoch": 0.068,
-      "grad_norm": 0.3634227514266968,
-      "learning_rate": 3.996536085718516e-06,
-      "loss": 8.400882720947266,
-      "step": 340
-    },
-    {
-      "epoch": 0.069,
-      "grad_norm": 0.33795344829559326,
-      "learning_rate": 3.996136078062792e-06,
-      "loss": 8.43860092163086,
-      "step": 345
-    },
-    {
-      "epoch": 0.07,
-      "grad_norm": 0.36207878589630127,
-      "learning_rate": 3.995714240982727e-06,
-      "loss": 8.418954467773437,
-      "step": 350
-    },
-    {
-      "epoch": 0.071,
-      "grad_norm": 0.380937397480011,
-      "learning_rate": 3.995270579091465e-06,
-      "loss": 8.300949096679688,
-      "step": 355
-    },
-    {
-      "epoch": 0.072,
-      "grad_norm": 0.3572588860988617,
-      "learning_rate": 3.99480509724082e-06,
-      "loss": 8.41064453125,
-      "step": 360
-    },
-    {
-      "epoch": 0.073,
-      "grad_norm": 0.4473942220211029,
-      "learning_rate": 3.994317800521228e-06,
-      "loss": 8.382225036621094,
-      "step": 365
-    },
-    {
-      "epoch": 0.074,
-      "grad_norm": 0.40747135877609253,
-      "learning_rate": 3.993808694261687e-06,
-      "loss": 8.360281372070313,
-      "step": 370
-    },
-    {
-      "epoch": 0.075,
-      "grad_norm": 0.42307648062705994,
-      "learning_rate": 3.993277784029702e-06,
-      "loss": 8.374369812011718,
-      "step": 375
-    },
-    {
-      "epoch": 0.076,
-      "grad_norm": 0.38264399766921997,
-      "learning_rate": 3.992725075631223e-06,
-      "loss": 8.344956207275391,
-      "step": 380
-    },
-    {
-      "epoch": 0.077,
-      "grad_norm": 0.34773537516593933,
-      "learning_rate": 3.992150575110579e-06,
-      "loss": 8.235700988769532,
-      "step": 385
-    },
-    {
-      "epoch": 0.078,
-      "grad_norm": 0.37760239839553833,
-      "learning_rate": 3.991554288750416e-06,
-      "loss": 8.38818130493164,
-      "step": 390
-    },
-    {
-      "epoch": 0.079,
-      "grad_norm": 0.4430180490016937,
-      "learning_rate": 3.990936223071627e-06,
-      "loss": 8.25281982421875,
-      "step": 395
-    },
-    {
-      "epoch": 0.08,
-      "grad_norm": 0.37283849716186523,
-      "learning_rate": 3.990296384833279e-06,
-      "loss": 8.315816497802734,
-      "step": 400
-    },
-    {
-      "epoch": 0.081,
-      "grad_norm": 0.40707769989967346,
-      "learning_rate": 3.989634781032539e-06,
-      "loss": 8.215055084228515,
-      "step": 405
-    },
-    {
-      "epoch": 0.082,
-      "grad_norm": 0.38030412793159485,
-      "learning_rate": 3.9889514189046015e-06,
-      "loss": 8.311016845703126,
-      "step": 410
-    },
-    {
-      "epoch": 0.083,
-      "grad_norm": 0.37480244040489197,
-      "learning_rate": 3.988246305922606e-06,
-      "loss": 8.189589691162109,
-      "step": 415
-    },
-    {
-      "epoch": 0.084,
-      "grad_norm": 0.3482901453971863,
-      "learning_rate": 3.987519449797554e-06,
-      "loss": 8.21697540283203,
-      "step": 420
-    },
-    {
-      "epoch": 0.085,
-      "grad_norm": 0.34717708826065063,
-      "learning_rate": 3.986770858478227e-06,
-      "loss": 8.241048431396484,
-      "step": 425
-    },
-    {
-      "epoch": 0.086,
-      "grad_norm": 0.36790233850479126,
-      "learning_rate": 3.986000540151101e-06,
-      "loss": 8.249729919433594,
-      "step": 430
-    },
-    {
-      "epoch": 0.087,
-      "grad_norm": 0.3420678973197937,
-      "learning_rate": 3.985208503240253e-06,
-      "loss": 8.281121063232423,
-      "step": 435
-    },
-    {
-      "epoch": 0.088,
-      "grad_norm": 0.34600451588630676,
-      "learning_rate": 3.9843947564072725e-06,
-      "loss": 8.357573699951171,
-      "step": 440
-    },
-    {
-      "epoch": 0.089,
-      "grad_norm": 0.35705456137657166,
-      "learning_rate": 3.983559308551164e-06,
-      "loss": 8.280086517333984,
-      "step": 445
-    },
-    {
-      "epoch": 0.09,
-      "grad_norm": 0.3669961392879486,
-      "learning_rate": 3.982702168808252e-06,
-      "loss": 8.206847381591796,
-      "step": 450
-    },
-    {
-      "epoch": 0.09,
-      "eval_accuracy": 0.12533089133089134,
-      "eval_loss": 8.183599472045898,
-      "eval_runtime": 9.8934,
-      "eval_samples_per_second": 10.108,
-      "eval_steps_per_second": 1.718,
-      "step": 450
-    },
-    {
-      "epoch": 0.091,
-      "grad_norm": 0.37337207794189453,
-      "learning_rate": 3.981823346552078e-06,
-      "loss": 8.199935913085938,
-      "step": 455
-    },
-    {
-      "epoch": 0.092,
-      "grad_norm": 0.44037237763404846,
-      "learning_rate": 3.980922851393302e-06,
-      "loss": 8.162527465820313,
-      "step": 460
-    },
-    {
-      "epoch": 0.093,
-      "grad_norm": 0.3508804142475128,
-      "learning_rate": 3.9800006931795954e-06,
-      "loss": 8.137972259521485,
-      "step": 465
-    },
-    {
-      "epoch": 0.094,
-      "grad_norm": 0.3387139141559601,
-      "learning_rate": 3.979056881995533e-06,
-      "loss": 8.121975708007813,
-      "step": 470
-    },
-    {
-      "epoch": 0.095,
-      "grad_norm": 0.341962069272995,
-      "learning_rate": 3.978091428162482e-06,
-      "loss": 8.128800964355468,
-      "step": 475
-    },
-    {
-      "epoch": 0.096,
-      "grad_norm": 0.3712274730205536,
-      "learning_rate": 3.97710434223849e-06,
-      "loss": 8.214947509765626,
-      "step": 480
-    },
-    {
-      "epoch": 0.097,
-      "grad_norm": 0.4289889335632324,
-      "learning_rate": 3.976095635018172e-06,
-      "loss": 8.149790954589843,
-      "step": 485
-    },
-    {
-      "epoch": 0.098,
-      "grad_norm": 0.33974844217300415,
-      "learning_rate": 3.975065317532588e-06,
-      "loss": 8.15101318359375,
-      "step": 490
-    },
-    {
-      "epoch": 0.099,
-      "grad_norm": 0.3340671956539154,
-      "learning_rate": 3.974013401049125e-06,
-      "loss": 8.08057861328125,
-      "step": 495
-    },
-    {
-      "epoch": 0.1,
-      "grad_norm": 0.3514098525047302,
-      "learning_rate": 3.972939897071373e-06,
-      "loss": 8.09535903930664,
-      "step": 500
-    },
-    {
-      "epoch": 0.101,
-      "grad_norm": 0.34814581274986267,
-      "learning_rate": 3.971844817338999e-06,
-      "loss": 8.083773803710937,
-      "step": 505
-    },
-    {
-      "epoch": 0.102,
-      "grad_norm": 0.34985920786857605,
-      "learning_rate": 3.97072817382762e-06,
-      "loss": 8.11724853515625,
-      "step": 510
-    },
-    {
-      "epoch": 0.103,
-      "grad_norm": 0.3791492283344269,
-      "learning_rate": 3.969589978748671e-06,
-      "loss": 8.136322021484375,
-      "step": 515
-    },
-    {
-      "epoch": 0.104,
-      "grad_norm": 0.32822874188423157,
-      "learning_rate": 3.968430244549271e-06,
-      "loss": 8.104237365722657,
-      "step": 520
-    },
-    {
-      "epoch": 0.105,
-      "grad_norm": 0.3564032018184662,
-      "learning_rate": 3.967248983912086e-06,
-      "loss": 8.096965026855468,
-      "step": 525
-    },
-    {
-      "epoch": 0.106,
-      "grad_norm": 0.376220703125,
-      "learning_rate": 3.966046209755195e-06,
-      "loss": 8.00832748413086,
-      "step": 530
-    },
-    {
-      "epoch": 0.107,
-      "grad_norm": 0.36956483125686646,
-      "learning_rate": 3.964821935231942e-06,
-      "loss": 8.112174224853515,
-      "step": 535
-    },
-    {
-      "epoch": 0.108,
-      "grad_norm": 0.34770211577415466,
-      "learning_rate": 3.963576173730798e-06,
-      "loss": 8.067781066894531,
-      "step": 540
-    },
-    {
-      "epoch": 0.109,
-      "grad_norm": 0.3450458347797394,
-      "learning_rate": 3.9623089388752105e-06,
-      "loss": 8.181710815429687,
-      "step": 545
-    },
-    {
-      "epoch": 0.11,
-      "grad_norm": 0.35391199588775635,
-      "learning_rate": 3.961020244523458e-06,
-      "loss": 8.074383544921876,
-      "step": 550
-    },
-    {
-      "epoch": 0.111,
-      "grad_norm": 0.35581737756729126,
-      "learning_rate": 3.959710104768493e-06,
-      "loss": 8.113288879394531,
-      "step": 555
-    },
-    {
-      "epoch": 0.112,
-      "grad_norm": 0.3356166481971741,
-      "learning_rate": 3.958378533937797e-06,
-      "loss": 8.000715637207032,
-      "step": 560
-    },
-    {
-      "epoch": 0.113,
-      "grad_norm": 0.4040232300758362,
-      "learning_rate": 3.957025546593213e-06,
-      "loss": 8.02787094116211,
-      "step": 565
-    },
-    {
-      "epoch": 0.114,
-      "grad_norm": 0.3501885235309601,
-      "learning_rate": 3.9556511575307956e-06,
-      "loss": 8.096998596191407,
-      "step": 570
-    },
-    {
-      "epoch": 0.115,
-      "grad_norm": 0.4042588472366333,
-      "learning_rate": 3.954255381780641e-06,
-      "loss": 7.963522338867188,
-      "step": 575
-    },
-    {
-      "epoch": 0.116,
-      "grad_norm": 0.35777050256729126,
-      "learning_rate": 3.952838234606732e-06,
-      "loss": 8.016288757324219,
-      "step": 580
-    },
-    {
-      "epoch": 0.117,
-      "grad_norm": 0.35311609506607056,
-      "learning_rate": 3.951399731506761e-06,
-      "loss": 8.053848266601562,
-      "step": 585
-    },
-    {
-      "epoch": 0.118,
-      "grad_norm": 0.41893506050109863,
-      "learning_rate": 3.949939888211968e-06,
-      "loss": 8.02327651977539,
-      "step": 590
-    },
-    {
-      "epoch": 0.119,
-      "grad_norm": 0.44586342573165894,
-      "learning_rate": 3.948458720686966e-06,
-      "loss": 7.9286552429199215,
-      "step": 595
-    },
-    {
-      "epoch": 0.12,
-      "grad_norm": 0.34198442101478577,
-      "learning_rate": 3.946956245129566e-06,
-      "loss": 7.989341735839844,
-      "step": 600
-    },
-    {
-      "epoch": 0.12,
-      "eval_accuracy": 0.12831746031746033,
-      "eval_loss": 8.00243091583252,
-      "eval_runtime": 9.9685,
-      "eval_samples_per_second": 10.032,
-      "eval_steps_per_second": 1.705,
-      "step": 600
     }
   ],
   "logging_steps": 5,

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542c39b999873d04e8ee4a3271b21d58fcf1252ca48f9f04659e9b82e85ebaaa
+oid sha256:8105dc9cc5632cea019c1d838b89a15e2936bc190d52fb089119a523f083e859
 size 5265