Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
     "q_proj",
-    "gate_proj",
     "v_proj",
-    "k_proj",
-    "o_proj"
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "k_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 sha256:9a323fc60e398f07df76076effccdfc93386e7f2c06a4d210f5fe11ef1e793cb
+oid sha256:1cac2011fb82e5057de30ac0f4ffa50549541a1374f6529f80528efcca6fa182
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782565b9486e1f287d668be0d2421dc3074e2b1b1e242aff627dee195273fa4c
+oid sha256:9b41a67e3cf04aab2b4ab76df5e332334d0306c62a9b9e823e5c35bdcca406ab
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc4595eb36291107783340eb4d984b80178a3bbeee1592461d47747aabcdadd
+oid sha256:6df819ca8e305cb78b68e11c597c4be358949e29b2d90d1c61804b773554cf08
 size 14244

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007842983470912335,
+  "epoch": 0.007763824459928961,
   "eval_steps": 500,
   "global_step": 100,
   "is_hyper_param_search": false,
@@ -9,703 +9,703 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 7.842983470912334e-05,
-      "grad_norm": 8.825519561767578,
+      "epoch": 7.763824459928961e-05,
+      "grad_norm": 15.173023223876953,
       "learning_rate": 1e-05,
-      "loss": 2.8016,
+      "loss": 3.6366,
       "step": 1
     },
     {
-      "epoch": 0.0001568596694182467,
-      "grad_norm": 12.083088874816895,
+      "epoch": 0.00015527648919857922,
+      "grad_norm": 18.251972198486328,
       "learning_rate": 2e-05,
-      "loss": 3.6411,
+      "loss": 5.1138,
       "step": 2
     },
     {
-      "epoch": 0.00023528950412737005,
-      "grad_norm": 15.9275541305542,
+      "epoch": 0.00023291473379786882,
+      "grad_norm": 18.701696395874023,
       "learning_rate": 3e-05,
-      "loss": 4.9024,
+      "loss": 4.9591,
       "step": 3
     },
     {
-      "epoch": 0.0003137193388364934,
-      "grad_norm": 21.615602493286133,
+      "epoch": 0.00031055297839715845,
+      "grad_norm": 19.8187198638916,
       "learning_rate": 4e-05,
-      "loss": 6.0083,
+      "loss": 4.3723,
       "step": 4
     },
     {
-      "epoch": 0.00039214917354561674,
-      "grad_norm": 22.12832260131836,
+      "epoch": 0.00038819122299644805,
+      "grad_norm": 18.29945945739746,
       "learning_rate": 5e-05,
-      "loss": 5.5202,
+      "loss": 5.9455,
       "step": 5
     },
     {
-      "epoch": 0.0004705790082547401,
-      "grad_norm": 9.948811531066895,
+      "epoch": 0.00046582946759573764,
+      "grad_norm": 32.43329620361328,
       "learning_rate": 6e-05,
-      "loss": 2.9518,
+      "loss": 8.4791,
       "step": 6
     },
     {
-      "epoch": 0.0005490088429638635,
-      "grad_norm": 15.534398078918457,
+      "epoch": 0.0005434677121950273,
+      "grad_norm": 20.790515899658203,
       "learning_rate": 7e-05,
-      "loss": 4.1157,
+      "loss": 5.3114,
       "step": 7
     },
     {
-      "epoch": 0.0006274386776729868,
-      "grad_norm": 16.559049606323242,
+      "epoch": 0.0006211059567943169,
+      "grad_norm": 17.102371215820312,
       "learning_rate": 8e-05,
-      "loss": 5.0582,
+      "loss": 4.3752,
       "step": 8
     },
     {
-      "epoch": 0.0007058685123821102,
-      "grad_norm": 42.421512603759766,
+      "epoch": 0.0006987442013936065,
+      "grad_norm": 16.773916244506836,
       "learning_rate": 9e-05,
-      "loss": 6.5426,
+      "loss": 4.1246,
       "step": 9
     },
     {
-      "epoch": 0.0007842983470912335,
-      "grad_norm": 20.62925148010254,
+      "epoch": 0.0007763824459928961,
+      "grad_norm": 12.671195030212402,
       "learning_rate": 0.0001,
-      "loss": 4.6693,
+      "loss": 2.7808,
       "step": 10
     },
     {
-      "epoch": 0.0008627281818003569,
-      "grad_norm": 15.661595344543457,
+      "epoch": 0.0008540206905921857,
+      "grad_norm": 18.52830696105957,
       "learning_rate": 9.99695413509548e-05,
-      "loss": 3.6362,
+      "loss": 3.1277,
       "step": 11
     },
     {
-      "epoch": 0.0009411580165094802,
-      "grad_norm": 14.2806978225708,
+      "epoch": 0.0009316589351914753,
+      "grad_norm": 18.569049835205078,
       "learning_rate": 9.987820251299122e-05,
-      "loss": 2.3931,
+      "loss": 3.1262,
       "step": 12
     },
     {
-      "epoch": 0.0010195878512186036,
-      "grad_norm": 28.024402618408203,
+      "epoch": 0.0010092971797907649,
+      "grad_norm": 19.517616271972656,
       "learning_rate": 9.972609476841367e-05,
-      "loss": 3.4275,
+      "loss": 2.7361,
       "step": 13
     },
     {
-      "epoch": 0.001098017685927727,
-      "grad_norm": 16.453929901123047,
+      "epoch": 0.0010869354243900546,
+      "grad_norm": 22.662939071655273,
       "learning_rate": 9.951340343707852e-05,
-      "loss": 2.1056,
+      "loss": 2.5586,
       "step": 14
     },
     {
-      "epoch": 0.0011764475206368502,
-      "grad_norm": 22.603105545043945,
+      "epoch": 0.001164573668989344,
+      "grad_norm": 35.87885665893555,
       "learning_rate": 9.924038765061042e-05,
-      "loss": 2.0804,
+      "loss": 2.4555,
       "step": 15
     },
     {
-      "epoch": 0.0012548773553459735,
-      "grad_norm": 25.013137817382812,
+      "epoch": 0.0012422119135886338,
+      "grad_norm": 18.5505428314209,
       "learning_rate": 9.890738003669029e-05,
-      "loss": 2.4932,
+      "loss": 1.974,
       "step": 16
     },
     {
-      "epoch": 0.001333307190055097,
-      "grad_norm": 22.514392852783203,
+      "epoch": 0.0013198501581879233,
+      "grad_norm": 13.761811256408691,
       "learning_rate": 9.851478631379982e-05,
-      "loss": 2.5763,
+      "loss": 1.4696,
       "step": 17
     },
     {
-      "epoch": 0.0014117370247642203,
-      "grad_norm": 29.10135841369629,
+      "epoch": 0.001397488402787213,
+      "grad_norm": 14.877791404724121,
       "learning_rate": 9.806308479691595e-05,
-      "loss": 1.8406,
+      "loss": 1.7532,
       "step": 18
     },
     {
-      "epoch": 0.0014901668594733436,
-      "grad_norm": 12.27782917022705,
+      "epoch": 0.0014751266473865027,
+      "grad_norm": 17.029918670654297,
       "learning_rate": 9.755282581475769e-05,
-      "loss": 1.4448,
+      "loss": 1.7558,
       "step": 19
     },
     {
-      "epoch": 0.001568596694182467,
-      "grad_norm": 36.448997497558594,
+      "epoch": 0.0015527648919857922,
+      "grad_norm": 17.873872756958008,
       "learning_rate": 9.698463103929542e-05,
-      "loss": 2.9484,
+      "loss": 1.7163,
       "step": 20
     },
     {
-      "epoch": 0.0016470265288915905,
-      "grad_norm": 11.227051734924316,
+      "epoch": 0.0016304031365850819,
+      "grad_norm": 10.733744621276855,
       "learning_rate": 9.635919272833938e-05,
-      "loss": 1.8091,
+      "loss": 1.2642,
       "step": 21
     },
     {
-      "epoch": 0.0017254563636007138,
-      "grad_norm": 14.083976745605469,
+      "epoch": 0.0017080413811843714,
+      "grad_norm": 16.097576141357422,
       "learning_rate": 9.567727288213005e-05,
-      "loss": 1.3116,
+      "loss": 1.9344,
       "step": 22
     },
     {
-      "epoch": 0.001803886198309837,
-      "grad_norm": 14.545560836791992,
+      "epoch": 0.001785679625783661,
+      "grad_norm": 14.290857315063477,
       "learning_rate": 9.493970231495835e-05,
-      "loss": 1.6795,
+      "loss": 1.3434,
       "step": 23
     },
     {
-      "epoch": 0.0018823160330189604,
-      "grad_norm": 15.083060264587402,
+      "epoch": 0.0018633178703829506,
+      "grad_norm": 12.831293106079102,
       "learning_rate": 9.414737964294636e-05,
-      "loss": 1.7426,
+      "loss": 1.7986,
       "step": 24
     },
     {
-      "epoch": 0.0019607458677280837,
-      "grad_norm": 14.212522506713867,
+      "epoch": 0.0019409561149822403,
+      "grad_norm": 25.20969581604004,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.732,
+      "loss": 2.0613,
       "step": 25
     },
     {
-      "epoch": 0.002039175702437207,
-      "grad_norm": 11.611138343811035,
+      "epoch": 0.0020185943595815298,
+      "grad_norm": 11.39193344116211,
       "learning_rate": 9.24024048078213e-05,
-      "loss": 1.2554,
+      "loss": 1.3613,
       "step": 26
     },
     {
-      "epoch": 0.0021176055371463303,
-      "grad_norm": 10.914994239807129,
+      "epoch": 0.0020962326041808195,
+      "grad_norm": 20.78348731994629,
       "learning_rate": 9.145187862775209e-05,
-      "loss": 1.394,
+      "loss": 2.0145,
       "step": 27
     },
     {
-      "epoch": 0.002196035371855454,
-      "grad_norm": 20.15048599243164,
+      "epoch": 0.002173870848780109,
+      "grad_norm": 13.54377555847168,
       "learning_rate": 9.045084971874738e-05,
-      "loss": 2.1326,
+      "loss": 1.6814,
       "step": 28
     },
     {
-      "epoch": 0.0022744652065645773,
-      "grad_norm": 14.226958274841309,
+      "epoch": 0.002251509093379399,
+      "grad_norm": 9.71171760559082,
       "learning_rate": 8.940053768033609e-05,
-      "loss": 1.411,
+      "loss": 1.2467,
       "step": 29
     },
     {
-      "epoch": 0.0023528950412737004,
-      "grad_norm": 15.308096885681152,
+      "epoch": 0.002329147337978688,
+      "grad_norm": 10.445706367492676,
       "learning_rate": 8.83022221559489e-05,
-      "loss": 2.2317,
+      "loss": 1.6891,
       "step": 30
     },
     {
-      "epoch": 0.002431324875982824,
-      "grad_norm": 37.11000442504883,
+      "epoch": 0.002406785582577978,
+      "grad_norm": 16.003211975097656,
       "learning_rate": 8.715724127386972e-05,
-      "loss": 3.0994,
+      "loss": 2.4213,
       "step": 31
     },
     {
-      "epoch": 0.002509754710691947,
-      "grad_norm": 13.671127319335938,
+      "epoch": 0.0024844238271772676,
+      "grad_norm": 12.86924934387207,
       "learning_rate": 8.596699001693255e-05,
-      "loss": 2.3658,
+      "loss": 1.8616,
       "step": 32
     },
     {
-      "epoch": 0.0025881845454010705,
-      "grad_norm": 11.981795310974121,
+      "epoch": 0.0025620620717765573,
+      "grad_norm": 8.061415672302246,
       "learning_rate": 8.473291852294987e-05,
-      "loss": 1.7347,
+      "loss": 1.5254,
       "step": 33
     },
     {
-      "epoch": 0.002666614380110194,
-      "grad_norm": 17.430723190307617,
+      "epoch": 0.0026397003163758466,
+      "grad_norm": 21.588794708251953,
       "learning_rate": 8.345653031794292e-05,
-      "loss": 2.2345,
+      "loss": 2.4648,
       "step": 34
     },
     {
-      "epoch": 0.002745044214819317,
-      "grad_norm": 14.712089538574219,
+      "epoch": 0.0027173385609751363,
+      "grad_norm": 7.5725603103637695,
       "learning_rate": 8.213938048432697e-05,
-      "loss": 2.2161,
+      "loss": 1.3198,
       "step": 35
     },
     {
-      "epoch": 0.0028234740495284407,
-      "grad_norm": 12.411870956420898,
+      "epoch": 0.002794976805574426,
+      "grad_norm": 11.222454071044922,
       "learning_rate": 8.07830737662829e-05,
-      "loss": 1.6571,
+      "loss": 1.7226,
       "step": 36
     },
     {
-      "epoch": 0.0029019038842375638,
-      "grad_norm": 11.750947952270508,
+      "epoch": 0.0028726150501737157,
+      "grad_norm": 12.333401679992676,
       "learning_rate": 7.938926261462366e-05,
-      "loss": 1.3471,
+      "loss": 1.492,
       "step": 37
     },
     {
-      "epoch": 0.0029803337189466873,
-      "grad_norm": 18.219520568847656,
+      "epoch": 0.0029502532947730054,
+      "grad_norm": 14.928689002990723,
       "learning_rate": 7.795964517353735e-05,
-      "loss": 2.2844,
+      "loss": 2.1283,
       "step": 38
     },
     {
-      "epoch": 0.003058763553655811,
-      "grad_norm": 8.215274810791016,
+      "epoch": 0.0030278915393722947,
+      "grad_norm": 11.8944091796875,
       "learning_rate": 7.649596321166024e-05,
-      "loss": 1.379,
+      "loss": 1.4857,
       "step": 39
     },
     {
-      "epoch": 0.003137193388364934,
-      "grad_norm": 10.532532691955566,
+      "epoch": 0.0031055297839715844,
+      "grad_norm": 9.366742134094238,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 1.8841,
+      "loss": 1.5347,
       "step": 40
     },
     {
-      "epoch": 0.0032156232230740574,
-      "grad_norm": 12.455815315246582,
+      "epoch": 0.003183168028570874,
+      "grad_norm": 9.03040599822998,
       "learning_rate": 7.347357813929454e-05,
-      "loss": 1.7141,
+      "loss": 0.9668,
       "step": 41
     },
     {
-      "epoch": 0.003294053057783181,
-      "grad_norm": 10.054532051086426,
+      "epoch": 0.0032608062731701638,
+      "grad_norm": 12.494256973266602,
       "learning_rate": 7.191855733945387e-05,
-      "loss": 1.6398,
+      "loss": 1.4275,
       "step": 42
     },
     {
-      "epoch": 0.003372482892492304,
-      "grad_norm": 10.613759994506836,
+      "epoch": 0.003338444517769453,
+      "grad_norm": 14.382235527038574,
       "learning_rate": 7.033683215379002e-05,
-      "loss": 1.7214,
+      "loss": 1.625,
       "step": 43
     },
     {
-      "epoch": 0.0034509127272014275,
-      "grad_norm": 10.810108184814453,
+      "epoch": 0.0034160827623687428,
+      "grad_norm": 9.916275024414062,
       "learning_rate": 6.873032967079561e-05,
-      "loss": 2.3159,
+      "loss": 1.4007,
       "step": 44
     },
     {
-      "epoch": 0.0035293425619105506,
-      "grad_norm": 11.261944770812988,
+      "epoch": 0.0034937210069680325,
+      "grad_norm": 7.911404132843018,
       "learning_rate": 6.710100716628344e-05,
-      "loss": 1.463,
+      "loss": 1.344,
       "step": 45
     },
     {
-      "epoch": 0.003607772396619674,
-      "grad_norm": 11.900640487670898,
+      "epoch": 0.003571359251567322,
+      "grad_norm": 20.48213768005371,
       "learning_rate": 6.545084971874738e-05,
-      "loss": 1.5287,
+      "loss": 1.4345,
       "step": 46
     },
     {
-      "epoch": 0.0036862022313287977,
-      "grad_norm": 14.910116195678711,
+      "epoch": 0.003648997496166612,
+      "grad_norm": 17.24418830871582,
       "learning_rate": 6.378186779084995e-05,
-      "loss": 2.1966,
+      "loss": 2.0092,
       "step": 47
     },
     {
-      "epoch": 0.0037646320660379208,
-      "grad_norm": 11.18796157836914,
+      "epoch": 0.003726635740765901,
+      "grad_norm": 18.877300262451172,
       "learning_rate": 6.209609477998338e-05,
-      "loss": 1.7811,
+      "loss": 1.8605,
       "step": 48
     },
     {
-      "epoch": 0.0038430619007470443,
-      "grad_norm": 15.256511688232422,
+      "epoch": 0.003804273985365191,
+      "grad_norm": 15.295802116394043,
       "learning_rate": 6.0395584540887963e-05,
-      "loss": 1.3157,
+      "loss": 1.7475,
       "step": 49
     },
     {
-      "epoch": 0.003921491735456167,
-      "grad_norm": 10.210933685302734,
+      "epoch": 0.0038819122299644806,
+      "grad_norm": 9.2744779586792,
       "learning_rate": 5.868240888334653e-05,
-      "loss": 1.5167,
+      "loss": 1.5498,
       "step": 50
     },
     {
-      "epoch": 0.003999921570165291,
-      "grad_norm": 14.052650451660156,
+      "epoch": 0.00395955047456377,
+      "grad_norm": 12.479969024658203,
       "learning_rate": 5.695865504800327e-05,
-      "loss": 1.7569,
+      "loss": 1.6775,
       "step": 51
     },
     {
-      "epoch": 0.004078351404874414,
-      "grad_norm": 14.927163124084473,
+      "epoch": 0.0040371887191630595,
+      "grad_norm": 19.23907470703125,
       "learning_rate": 5.522642316338268e-05,
-      "loss": 1.4792,
+      "loss": 1.7539,
       "step": 52
     },
     {
-      "epoch": 0.004156781239583538,
-      "grad_norm": 18.198444366455078,
+      "epoch": 0.00411482696376235,
+      "grad_norm": 12.233394622802734,
       "learning_rate": 5.348782368720626e-05,
-      "loss": 3.5506,
+      "loss": 1.6477,
       "step": 53
     },
     {
-      "epoch": 0.004235211074292661,
-      "grad_norm": 13.294053077697754,
+      "epoch": 0.004192465208361639,
+      "grad_norm": 7.942619800567627,
       "learning_rate": 5.174497483512506e-05,
-      "loss": 1.4432,
+      "loss": 1.3514,
       "step": 54
     },
     {
-      "epoch": 0.004313640909001784,
-      "grad_norm": 11.814456939697266,
+      "epoch": 0.004270103452960928,
+      "grad_norm": 7.320205211639404,
       "learning_rate": 5e-05,
-      "loss": 1.4172,
+      "loss": 1.0451,
       "step": 55
     },
     {
-      "epoch": 0.004392070743710908,
-      "grad_norm": 8.617324829101562,
+      "epoch": 0.004347741697560218,
+      "grad_norm": 18.8829288482666,
       "learning_rate": 4.825502516487497e-05,
-      "loss": 1.3786,
+      "loss": 2.23,
       "step": 56
     },
     {
-      "epoch": 0.004470500578420031,
-      "grad_norm": 14.102591514587402,
+      "epoch": 0.004425379942159508,
+      "grad_norm": 11.247135162353516,
       "learning_rate": 4.6512176312793736e-05,
-      "loss": 1.9422,
+      "loss": 1.361,
       "step": 57
     },
     {
-      "epoch": 0.004548930413129155,
-      "grad_norm": 10.432605743408203,
+      "epoch": 0.004503018186758798,
+      "grad_norm": 17.50565528869629,
       "learning_rate": 4.477357683661734e-05,
-      "loss": 1.3672,
+      "loss": 1.7137,
       "step": 58
     },
     {
-      "epoch": 0.004627360247838277,
-      "grad_norm": 11.157849311828613,
+      "epoch": 0.004580656431358087,
+      "grad_norm": 15.826338768005371,
       "learning_rate": 4.3041344951996746e-05,
-      "loss": 1.5081,
+      "loss": 2.1369,
       "step": 59
     },
     {
-      "epoch": 0.004705790082547401,
-      "grad_norm": 10.752006530761719,
+      "epoch": 0.004658294675957376,
+      "grad_norm": 12.451811790466309,
       "learning_rate": 4.131759111665349e-05,
-      "loss": 1.763,
+      "loss": 1.827,
       "step": 60
     },
     {
-      "epoch": 0.004784219917256524,
-      "grad_norm": 7.7650017738342285,
+      "epoch": 0.0047359329205566665,
+      "grad_norm": 7.233865737915039,
       "learning_rate": 3.960441545911204e-05,
-      "loss": 1.338,
+      "loss": 1.2302,
       "step": 61
     },
     {
-      "epoch": 0.004862649751965648,
-      "grad_norm": 9.609498977661133,
+      "epoch": 0.004813571165155956,
+      "grad_norm": 15.002647399902344,
       "learning_rate": 3.790390522001662e-05,
-      "loss": 1.5723,
+      "loss": 1.7143,
       "step": 62
     },
     {
-      "epoch": 0.004941079586674771,
-      "grad_norm": 10.62063980102539,
+      "epoch": 0.004891209409755245,
+      "grad_norm": 12.043486595153809,
       "learning_rate": 3.6218132209150045e-05,
-      "loss": 1.6656,
+      "loss": 1.6653,
       "step": 63
     },
     {
-      "epoch": 0.005019509421383894,
-      "grad_norm": 8.951350212097168,
+      "epoch": 0.004968847654354535,
+      "grad_norm": 11.110363960266113,
       "learning_rate": 3.4549150281252636e-05,
-      "loss": 1.2429,
+      "loss": 1.5404,
       "step": 64
     },
     {
-      "epoch": 0.005097939256093018,
-      "grad_norm": 18.992971420288086,
+      "epoch": 0.0050464858989538244,
+      "grad_norm": 9.822565078735352,
       "learning_rate": 3.289899283371657e-05,
-      "loss": 3.1177,
+      "loss": 1.4809,
       "step": 65
     },
     {
-      "epoch": 0.005176369090802141,
-      "grad_norm": 13.394461631774902,
+      "epoch": 0.005124124143553115,
+      "grad_norm": 11.402060508728027,
       "learning_rate": 3.12696703292044e-05,
-      "loss": 1.8502,
+      "loss": 1.6257,
       "step": 66
     },
     {
-      "epoch": 0.005254798925511265,
-      "grad_norm": 12.403133392333984,
+      "epoch": 0.005201762388152404,
+      "grad_norm": 9.092423439025879,
       "learning_rate": 2.9663167846209998e-05,
-      "loss": 1.1488,
+      "loss": 1.1908,
       "step": 67
     },
     {
-      "epoch": 0.005333228760220388,
-      "grad_norm": 7.903024673461914,
+      "epoch": 0.005279400632751693,
+      "grad_norm": 16.00357437133789,
       "learning_rate": 2.8081442660546125e-05,
-      "loss": 1.2091,
+      "loss": 2.0899,
       "step": 68
     },
     {
-      "epoch": 0.005411658594929511,
-      "grad_norm": 11.113040924072266,
+      "epoch": 0.005357038877350983,
+      "grad_norm": 11.897706031799316,
       "learning_rate": 2.6526421860705473e-05,
-      "loss": 1.6937,
+      "loss": 1.606,
       "step": 69
     },
     {
-      "epoch": 0.005490088429638634,
-      "grad_norm": 15.218375205993652,
+      "epoch": 0.0054346771219502725,
+      "grad_norm": 12.209402084350586,
       "learning_rate": 2.500000000000001e-05,
-      "loss": 1.9523,
+      "loss": 1.6851,
       "step": 70
     },
     {
-      "epoch": 0.005568518264347758,
-      "grad_norm": 10.67128849029541,
+      "epoch": 0.005512315366549563,
+      "grad_norm": 10.662795066833496,
       "learning_rate": 2.350403678833976e-05,
-      "loss": 1.3664,
+      "loss": 1.7668,
       "step": 71
     },
     {
-      "epoch": 0.005646948099056881,
-      "grad_norm": 9.806090354919434,
+      "epoch": 0.005589953611148852,
+      "grad_norm": 8.787954330444336,
       "learning_rate": 2.2040354826462668e-05,
-      "loss": 1.4883,
+      "loss": 1.4363,
       "step": 72
     },
     {
-      "epoch": 0.005725377933766005,
-      "grad_norm": 11.227718353271484,
+      "epoch": 0.005667591855748141,
+      "grad_norm": 7.407290935516357,
       "learning_rate": 2.061073738537635e-05,
-      "loss": 1.1364,
+      "loss": 1.4621,
       "step": 73
     },
     {
-      "epoch": 0.0058038077684751275,
-      "grad_norm": 17.53663444519043,
+      "epoch": 0.005745230100347431,
+      "grad_norm": 12.64970588684082,
       "learning_rate": 1.9216926233717085e-05,
-      "loss": 1.8685,
+      "loss": 1.5502,
       "step": 74
     },
     {
-      "epoch": 0.005882237603184251,
-      "grad_norm": 6.851722240447998,
+      "epoch": 0.005822868344946721,
+      "grad_norm": 15.698612213134766,
       "learning_rate": 1.7860619515673033e-05,
-      "loss": 1.0575,
+      "loss": 1.7476,
       "step": 75
     },
     {
-      "epoch": 0.0059606674378933746,
-      "grad_norm": 9.295647621154785,
+      "epoch": 0.005900506589546011,
+      "grad_norm": 9.95603084564209,
       "learning_rate": 1.6543469682057106e-05,
-      "loss": 1.0835,
+      "loss": 1.2277,
       "step": 76
     },
     {
-      "epoch": 0.006039097272602498,
-      "grad_norm": 9.07209300994873,
+      "epoch": 0.0059781448341453,
+      "grad_norm": 21.470365524291992,
       "learning_rate": 1.526708147705013e-05,
-      "loss": 1.1428,
+      "loss": 2.0358,
       "step": 77
     },
     {
-      "epoch": 0.006117527107311622,
-      "grad_norm": 8.919276237487793,
+      "epoch": 0.006055783078744589,
+      "grad_norm": 8.216337203979492,
       "learning_rate": 1.4033009983067452e-05,
-      "loss": 1.6744,
+      "loss": 0.8807,
       "step": 78
     },
     {
-      "epoch": 0.006195956942020745,
-      "grad_norm": 14.970587730407715,
+      "epoch": 0.0061334213233438795,
+      "grad_norm": 8.098356246948242,
       "learning_rate": 1.2842758726130283e-05,
-      "loss": 1.7913,
+      "loss": 1.2345,
       "step": 79
     },
     {
-      "epoch": 0.006274386776729868,
-      "grad_norm": 7.171314239501953,
+      "epoch": 0.006211059567943169,
+      "grad_norm": 9.083595275878906,
       "learning_rate": 1.1697777844051105e-05,
-      "loss": 1.5177,
+      "loss": 1.5091,
       "step": 80
     },
     {
-      "epoch": 0.006352816611438991,
-      "grad_norm": 7.902921676635742,
+      "epoch": 0.006288697812542458,
+      "grad_norm": 16.64013671875,
       "learning_rate": 1.0599462319663905e-05,
-      "loss": 1.3037,
+      "loss": 2.3048,
       "step": 81
     },
     {
-      "epoch": 0.006431246446148115,
-      "grad_norm": 6.716002941131592,
+      "epoch": 0.006366336057141748,
+      "grad_norm": 8.369383811950684,
       "learning_rate": 9.549150281252633e-06,
-      "loss": 0.962,
+      "loss": 1.0547,
       "step": 82
     },
     {
-      "epoch": 0.006509676280857238,
-      "grad_norm": 10.144266128540039,
+      "epoch": 0.006443974301741037,
+      "grad_norm": 7.26373291015625,
       "learning_rate": 8.548121372247918e-06,
-      "loss": 1.4771,
+      "loss": 1.1388,
       "step": 83
     },
     {
-      "epoch": 0.006588106115566362,
-      "grad_norm": 8.199270248413086,
+      "epoch": 0.0065216125463403276,
+      "grad_norm": 13.645014762878418,
       "learning_rate": 7.597595192178702e-06,
-      "loss": 1.2546,
+      "loss": 1.0994,
       "step": 84
     },
     {
-      "epoch": 0.0066665359502754845,
-      "grad_norm": 11.108482360839844,
+      "epoch": 0.006599250790939617,
+      "grad_norm": 12.321860313415527,
       "learning_rate": 6.698729810778065e-06,
-      "loss": 1.3973,
+      "loss": 1.5612,
       "step": 85
     },
     {
-      "epoch": 0.006744965784984608,
-      "grad_norm": 8.652900695800781,
+      "epoch": 0.006676889035538906,
+      "grad_norm": 13.168002128601074,
       "learning_rate": 5.852620357053651e-06,
-      "loss": 1.3762,
+      "loss": 1.3202,
       "step": 86
     },
     {
-      "epoch": 0.0068233956196937316,
-      "grad_norm": 14.958466529846191,
+      "epoch": 0.006754527280138196,
+      "grad_norm": 7.88428258895874,
       "learning_rate": 5.060297685041659e-06,
-      "loss": 1.7316,
+      "loss": 1.0294,
       "step": 87
     },
     {
-      "epoch": 0.006901825454402855,
-      "grad_norm": 6.1512227058410645,
+      "epoch": 0.0068321655247374855,
+      "grad_norm": 10.311480522155762,
       "learning_rate": 4.322727117869951e-06,
-      "loss": 1.1393,
+      "loss": 1.3795,
       "step": 88
     },
     {
-      "epoch": 0.006980255289111979,
-      "grad_norm": 9.555928230285645,
+      "epoch": 0.006909803769336776,
+      "grad_norm": 10.419498443603516,
       "learning_rate": 3.6408072716606346e-06,
-      "loss": 1.3302,
+      "loss": 1.1515,
       "step": 89
     },
     {
-      "epoch": 0.007058685123821101,
-      "grad_norm": 9.107611656188965,
+      "epoch": 0.006987442013936065,
+      "grad_norm": 7.458017349243164,
       "learning_rate": 3.0153689607045845e-06,
-      "loss": 1.2227,
+      "loss": 1.0061,
       "step": 90
     },
     {
-      "epoch": 0.007137114958530225,
-      "grad_norm": 5.744083881378174,
+      "epoch": 0.007065080258535354,
+      "grad_norm": 14.859030723571777,
       "learning_rate": 2.4471741852423237e-06,
-      "loss": 1.0086,
+      "loss": 2.0989,
       "step": 91
     },
     {
-      "epoch": 0.007215544793239348,
-      "grad_norm": 13.552300453186035,
+      "epoch": 0.007142718503134644,
+      "grad_norm": 10.113492012023926,
       "learning_rate": 1.9369152030840556e-06,
-      "loss": 1.7774,
+      "loss": 1.0713,
       "step": 92
     },
     {
-      "epoch": 0.007293974627948472,
-      "grad_norm": 16.62940788269043,
+      "epoch": 0.007220356747733934,
+      "grad_norm": 12.123403549194336,
       "learning_rate": 1.4852136862001764e-06,
-      "loss": 1.7008,
+      "loss": 1.1804,
       "step": 93
     },
     {
-      "epoch": 0.007372404462657595,
-      "grad_norm": 12.544093132019043,
+      "epoch": 0.007297994992333224,
+      "grad_norm": 8.072012901306152,
       "learning_rate": 1.0926199633097157e-06,
-      "loss": 1.6784,
+      "loss": 1.4086,
       "step": 94
     },
     {
-      "epoch": 0.007450834297366718,
-      "grad_norm": 10.599544525146484,
+      "epoch": 0.007375633236932513,
+      "grad_norm": 13.728706359863281,
       "learning_rate": 7.596123493895991e-07,
-      "loss": 1.5247,
+      "loss": 1.728,
       "step": 95
     },
     {
-      "epoch": 0.0075292641320758415,
-      "grad_norm": 11.64220142364502,
+      "epoch": 0.007453271481531802,
+      "grad_norm": 14.608238220214844,
       "learning_rate": 4.865965629214819e-07,
-      "loss": 1.5947,
+      "loss": 1.2751,
       "step": 96
     },
     {
-      "epoch": 0.007607693966784965,
-      "grad_norm": 7.192104339599609,
+      "epoch": 0.0075309097261310924,
+      "grad_norm": 10.540985107421875,
       "learning_rate": 2.7390523158633554e-07,
-      "loss": 1.3408,
+      "loss": 1.1588,
       "step": 97
     },
     {
-      "epoch": 0.0076861238014940885,
-      "grad_norm": 12.79780101776123,
+      "epoch": 0.007608547970730382,
+      "grad_norm": 8.851415634155273,
       "learning_rate": 1.2179748700879012e-07,
-      "loss": 2.0013,
+      "loss": 1.4473,
       "step": 98
     },
     {
-      "epoch": 0.007764553636203212,
-      "grad_norm": 8.97789478302002,
+      "epoch": 0.007686186215329671,
+      "grad_norm": 9.513968467712402,
       "learning_rate": 3.04586490452119e-08,
-      "loss": 1.5413,
+      "loss": 1.1629,
       "step": 99
     },
     {
-      "epoch": 0.007842983470912335,
-      "grad_norm": 13.65710735321045,
+      "epoch": 0.007763824459928961,
+      "grad_norm": 14.992069244384766,
       "learning_rate": 0.0,
-      "loss": 2.3571,
+      "loss": 1.3815,
       "step": 100
     }
   ],
@@ -726,7 +726,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9442519318265856.0,
+  "total_flos": 9376794125795328.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe8eb4a561fe614bf9dfc40cf2e5c3a17aeb1eabb7efb2bc9d4d362489af9314
+oid sha256:f23284b418e64ba8eb6a0fb5f9fbe8b5e6a20ebb48a7ddd92ce031e4b2486d95
 size 6776