Upload PEFT adapter weights, config, and tokenizer

adapter_config.json

@@ -24,10 +24,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
     "k_proj",
-    "v_proj"
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8bc51d26497e12f4bdd25dd590841510125e3b4db8407ccf81f34895f317e87
+oid sha256:5e93d8597cf8c79dc60dacc4acbef28dcc865a254964d0879019de4d480bec1d
 size 54560368

checkpoint-940/adapter_config.json

@@ -24,10 +24,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
     "k_proj",
-    "v_proj"
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

checkpoint-940/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8bc51d26497e12f4bdd25dd590841510125e3b4db8407ccf81f34895f317e87
+oid sha256:5e93d8597cf8c79dc60dacc4acbef28dcc865a254964d0879019de4d480bec1d
 size 54560368

checkpoint-940/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dce3b71facee56f654868b9d617e4359226e63e11eeba5d2abcfbd44bc858fb
+oid sha256:2fccb64d232e00129210a6953502cfe65577b303fd1ba19c7039f55b2092941f
 size 109267450

checkpoint-940/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d80412845fe1ffa6f6f69ab3a110851da87cd9fe84aa8a86c1245c8dd400695
+oid sha256:4a1f2ef68c40a31e2f08666d94c38cb172a4fa6fcb3871763493e1e43b83b24e
 size 14244

checkpoint-940/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbd55b657d538b783432d985a0a85c8a96173f327724f2ed74e8966d4a82c7d
-size 17208851
+oid sha256:0968dcc0ee8e56c7dccd34a7f51f8065ea0cb9e2cc529e3243d1e5c0a4bdaa0c
+size 17208754

checkpoint-940/trainer_state.json

@@ -11,660 +11,660 @@
   "log_history": [
     {
       "epoch": 0.01063264221158958,
-      "grad_norm": 5.609270095825195,
+      "grad_norm": 0.9233230352401733,
       "learning_rate": 0.00019808510638297873,
-      "loss": 2.4434,
+      "loss": 1.7298,
       "step": 10
     },
     {
       "epoch": 0.02126528442317916,
-      "grad_norm": 4.589075088500977,
+      "grad_norm": 0.9088625311851501,
       "learning_rate": 0.00019595744680851065,
-      "loss": 1.6902,
+      "loss": 1.2536,
       "step": 20
     },
     {
       "epoch": 0.03189792663476874,
-      "grad_norm": 3.7465291023254395,
+      "grad_norm": 0.9639036655426025,
       "learning_rate": 0.00019382978723404257,
-      "loss": 1.3148,
+      "loss": 1.1759,
       "step": 30
     },
     {
       "epoch": 0.04253056884635832,
-      "grad_norm": 3.543064594268799,
+      "grad_norm": 0.9426536560058594,
       "learning_rate": 0.00019170212765957448,
-      "loss": 1.4302,
+      "loss": 1.0703,
       "step": 40
     },
     {
       "epoch": 0.0531632110579479,
-      "grad_norm": 2.68544340133667,
+      "grad_norm": 0.9788757562637329,
       "learning_rate": 0.0001895744680851064,
-      "loss": 1.3222,
+      "loss": 1.0505,
       "step": 50
     },
     {
       "epoch": 0.06379585326953748,
-      "grad_norm": 2.752901792526245,
+      "grad_norm": 1.2088581323623657,
       "learning_rate": 0.00018744680851063832,
-      "loss": 1.2792,
+      "loss": 1.0358,
       "step": 60
     },
     {
       "epoch": 0.07442849548112707,
-      "grad_norm": 2.7944841384887695,
+      "grad_norm": 0.9232538342475891,
       "learning_rate": 0.0001853191489361702,
-      "loss": 1.3764,
+      "loss": 0.9859,
       "step": 70
     },
     {
       "epoch": 0.08506113769271664,
-      "grad_norm": 3.0340654850006104,
+      "grad_norm": 1.2805695533752441,
       "learning_rate": 0.00018319148936170215,
-      "loss": 1.2255,
+      "loss": 0.9763,
       "step": 80
     },
     {
       "epoch": 0.09569377990430622,
-      "grad_norm": 2.5017054080963135,
+      "grad_norm": 1.067161202430725,
       "learning_rate": 0.00018106382978723404,
-      "loss": 1.1689,
+      "loss": 1.0738,
       "step": 90
     },
     {
       "epoch": 0.1063264221158958,
-      "grad_norm": 4.572251319885254,
+      "grad_norm": 1.2387498617172241,
       "learning_rate": 0.00017893617021276596,
-      "loss": 1.1418,
+      "loss": 0.9779,
       "step": 100
     },
     {
       "epoch": 0.11695906432748537,
-      "grad_norm": 3.354853630065918,
+      "grad_norm": 1.0024847984313965,
       "learning_rate": 0.00017680851063829787,
-      "loss": 1.3103,
+      "loss": 0.9815,
       "step": 110
     },
     {
       "epoch": 0.12759170653907495,
-      "grad_norm": 2.387272834777832,
+      "grad_norm": 1.9225773811340332,
       "learning_rate": 0.0001746808510638298,
-      "loss": 1.2848,
+      "loss": 0.9203,
       "step": 120
     },
     {
       "epoch": 0.13822434875066453,
-      "grad_norm": 2.579465627670288,
+      "grad_norm": 1.3451205492019653,
       "learning_rate": 0.0001725531914893617,
-      "loss": 1.2395,
+      "loss": 0.9678,
       "step": 130
     },
     {
       "epoch": 0.14885699096225413,
-      "grad_norm": 2.9512267112731934,
+      "grad_norm": 1.4681438207626343,
       "learning_rate": 0.00017042553191489362,
-      "loss": 1.3716,
+      "loss": 0.813,
       "step": 140
     },
     {
       "epoch": 0.1594896331738437,
-      "grad_norm": 2.6200809478759766,
+      "grad_norm": 1.244214415550232,
       "learning_rate": 0.00016829787234042554,
-      "loss": 1.2647,
+      "loss": 0.7149,
       "step": 150
     },
     {
       "epoch": 0.17012227538543329,
-      "grad_norm": 2.7764666080474854,
+      "grad_norm": 1.4099949598312378,
       "learning_rate": 0.00016617021276595746,
-      "loss": 1.0862,
+      "loss": 0.8472,
       "step": 160
     },
     {
       "epoch": 0.18075491759702286,
-      "grad_norm": 2.454061269760132,
+      "grad_norm": 1.4794244766235352,
       "learning_rate": 0.00016404255319148937,
-      "loss": 1.2213,
+      "loss": 0.6425,
       "step": 170
     },
     {
       "epoch": 0.19138755980861244,
-      "grad_norm": 2.483651876449585,
+      "grad_norm": 1.574625849723816,
       "learning_rate": 0.0001619148936170213,
-      "loss": 1.1895,
+      "loss": 0.7604,
       "step": 180
     },
     {
       "epoch": 0.20202020202020202,
-      "grad_norm": 3.5856575965881348,
+      "grad_norm": 1.8564409017562866,
       "learning_rate": 0.0001597872340425532,
-      "loss": 1.2322,
+      "loss": 0.6777,
       "step": 190
     },
     {
       "epoch": 0.2126528442317916,
-      "grad_norm": 2.1436448097229004,
+      "grad_norm": 1.1089837551116943,
       "learning_rate": 0.00015765957446808512,
-      "loss": 1.2782,
+      "loss": 0.6804,
       "step": 200
     },
     {
       "epoch": 0.22328548644338117,
-      "grad_norm": 2.569831609725952,
+      "grad_norm": 1.5858855247497559,
       "learning_rate": 0.00015553191489361701,
-      "loss": 1.171,
+      "loss": 0.6962,
       "step": 210
     },
     {
       "epoch": 0.23391812865497075,
-      "grad_norm": 2.5455546379089355,
+      "grad_norm": 1.0457383394241333,
       "learning_rate": 0.00015340425531914896,
-      "loss": 1.3055,
+      "loss": 0.6975,
       "step": 220
     },
     {
       "epoch": 0.24455077086656035,
-      "grad_norm": 1.7153586149215698,
+      "grad_norm": 1.007315993309021,
       "learning_rate": 0.00015127659574468085,
-      "loss": 1.0822,
+      "loss": 0.6911,
       "step": 230
     },
     {
       "epoch": 0.2551834130781499,
-      "grad_norm": 2.549631357192993,
+      "grad_norm": 1.4641199111938477,
       "learning_rate": 0.00014914893617021276,
-      "loss": 1.3206,
+      "loss": 0.6968,
       "step": 240
     },
     {
       "epoch": 0.2658160552897395,
-      "grad_norm": 2.53717041015625,
+      "grad_norm": 1.127540111541748,
       "learning_rate": 0.00014702127659574468,
-      "loss": 1.1995,
+      "loss": 0.6226,
       "step": 250
     },
     {
       "epoch": 0.27644869750132905,
-      "grad_norm": 2.331685781478882,
+      "grad_norm": 1.841412901878357,
       "learning_rate": 0.0001448936170212766,
-      "loss": 1.2426,
+      "loss": 0.5781,
       "step": 260
     },
     {
       "epoch": 0.28708133971291866,
-      "grad_norm": 2.6866092681884766,
+      "grad_norm": 1.6684510707855225,
       "learning_rate": 0.00014276595744680851,
-      "loss": 1.1314,
+      "loss": 0.6214,
       "step": 270
     },
     {
       "epoch": 0.29771398192450826,
-      "grad_norm": 2.107909679412842,
+      "grad_norm": 1.7632583379745483,
       "learning_rate": 0.00014063829787234043,
-      "loss": 1.1542,
+      "loss": 0.5107,
       "step": 280
     },
     {
       "epoch": 0.3083466241360978,
-      "grad_norm": 1.8758138418197632,
+      "grad_norm": 1.3282111883163452,
       "learning_rate": 0.00013851063829787235,
-      "loss": 1.1377,
+      "loss": 0.6491,
       "step": 290
     },
     {
       "epoch": 0.3189792663476874,
-      "grad_norm": 1.647929072380066,
+      "grad_norm": 1.7586910724639893,
       "learning_rate": 0.00013638297872340427,
-      "loss": 1.0096,
+      "loss": 0.7237,
       "step": 300
     },
     {
       "epoch": 0.32961190855927697,
-      "grad_norm": 2.186124563217163,
+      "grad_norm": 1.5256597995758057,
       "learning_rate": 0.00013425531914893618,
-      "loss": 1.1746,
+      "loss": 0.6446,
       "step": 310
     },
     {
       "epoch": 0.34024455077086657,
-      "grad_norm": 2.4536380767822266,
+      "grad_norm": 1.4499211311340332,
       "learning_rate": 0.0001321276595744681,
-      "loss": 1.1833,
+      "loss": 0.557,
       "step": 320
     },
     {
       "epoch": 0.3508771929824561,
-      "grad_norm": 1.8024215698242188,
+      "grad_norm": 1.7797976732254028,
       "learning_rate": 0.00013000000000000002,
-      "loss": 0.9309,
+      "loss": 0.6162,
       "step": 330
     },
     {
       "epoch": 0.3615098351940457,
-      "grad_norm": 3.0355000495910645,
+      "grad_norm": 1.2894353866577148,
       "learning_rate": 0.0001278723404255319,
-      "loss": 1.0863,
+      "loss": 0.4761,
       "step": 340
     },
     {
       "epoch": 0.3721424774056353,
-      "grad_norm": 1.9415550231933594,
+      "grad_norm": 1.3315067291259766,
       "learning_rate": 0.00012574468085106382,
-      "loss": 1.0507,
+      "loss": 0.5865,
       "step": 350
     },
     {
       "epoch": 0.3827751196172249,
-      "grad_norm": 2.327995538711548,
+      "grad_norm": 1.4586937427520752,
       "learning_rate": 0.00012361702127659577,
-      "loss": 1.2524,
+      "loss": 0.5099,
       "step": 360
     },
     {
       "epoch": 0.3934077618288145,
-      "grad_norm": 2.001037120819092,
+      "grad_norm": 1.2912027835845947,
       "learning_rate": 0.00012148936170212766,
-      "loss": 1.0437,
+      "loss": 0.5801,
       "step": 370
     },
     {
       "epoch": 0.40404040404040403,
-      "grad_norm": 2.1419551372528076,
+      "grad_norm": 1.2132781744003296,
       "learning_rate": 0.00011936170212765959,
-      "loss": 1.0968,
+      "loss": 0.3565,
       "step": 380
     },
     {
       "epoch": 0.41467304625199364,
-      "grad_norm": 2.3085482120513916,
+      "grad_norm": 1.2837001085281372,
       "learning_rate": 0.0001172340425531915,
-      "loss": 1.1706,
+      "loss": 0.3634,
       "step": 390
     },
     {
       "epoch": 0.4253056884635832,
-      "grad_norm": 4.618401050567627,
+      "grad_norm": 1.6399765014648438,
       "learning_rate": 0.0001151063829787234,
-      "loss": 1.0685,
+      "loss": 0.5858,
       "step": 400
     },
     {
       "epoch": 0.4359383306751728,
-      "grad_norm": 2.421363115310669,
+      "grad_norm": 1.2120444774627686,
       "learning_rate": 0.00011297872340425532,
-      "loss": 1.0373,
+      "loss": 0.5533,
       "step": 410
     },
     {
       "epoch": 0.44657097288676234,
-      "grad_norm": 1.6373859643936157,
+      "grad_norm": 2.2904655933380127,
       "learning_rate": 0.00011085106382978725,
-      "loss": 1.0669,
+      "loss": 0.5185,
       "step": 420
     },
     {
       "epoch": 0.45720361509835195,
-      "grad_norm": 2.3031554222106934,
+      "grad_norm": 0.9909681081771851,
       "learning_rate": 0.00010872340425531916,
-      "loss": 1.1394,
+      "loss": 0.4418,
       "step": 430
     },
     {
       "epoch": 0.4678362573099415,
-      "grad_norm": 1.9488067626953125,
+      "grad_norm": 1.9283276796340942,
       "learning_rate": 0.00010659574468085107,
-      "loss": 1.0347,
+      "loss": 0.458,
       "step": 440
     },
     {
       "epoch": 0.4784688995215311,
-      "grad_norm": 1.8650946617126465,
+      "grad_norm": 1.5563241243362427,
       "learning_rate": 0.00010446808510638298,
-      "loss": 1.1159,
+      "loss": 0.3739,
       "step": 450
     },
     {
       "epoch": 0.4891015417331207,
-      "grad_norm": 1.8462837934494019,
+      "grad_norm": 0.8688263893127441,
       "learning_rate": 0.0001023404255319149,
-      "loss": 1.0389,
+      "loss": 0.3839,
       "step": 460
     },
     {
       "epoch": 0.49973418394471025,
-      "grad_norm": 2.5941386222839355,
+      "grad_norm": 1.012356162071228,
       "learning_rate": 0.00010021276595744682,
-      "loss": 1.1587,
+      "loss": 0.3637,
       "step": 470
     },
     {
       "epoch": 0.5103668261562998,
-      "grad_norm": 1.34873366355896,
+      "grad_norm": 1.2394040822982788,
       "learning_rate": 9.808510638297873e-05,
-      "loss": 1.1095,
+      "loss": 0.4456,
       "step": 480
     },
     {
       "epoch": 0.5209994683678895,
-      "grad_norm": 2.2580478191375732,
+      "grad_norm": 2.0661351680755615,
       "learning_rate": 9.595744680851064e-05,
-      "loss": 1.1268,
+      "loss": 0.3375,
       "step": 490
     },
     {
       "epoch": 0.531632110579479,
-      "grad_norm": 2.389127731323242,
+      "grad_norm": 0.8300966024398804,
       "learning_rate": 9.382978723404256e-05,
-      "loss": 1.2718,
+      "loss": 0.2703,
       "step": 500
     },
     {
       "epoch": 0.5422647527910686,
-      "grad_norm": 2.1379384994506836,
+      "grad_norm": 2.6386091709136963,
       "learning_rate": 9.170212765957448e-05,
-      "loss": 1.0394,
+      "loss": 0.3582,
       "step": 510
     },
     {
       "epoch": 0.5528973950026581,
-      "grad_norm": 2.5996925830841064,
+      "grad_norm": 1.5658433437347412,
       "learning_rate": 8.95744680851064e-05,
-      "loss": 1.0508,
+      "loss": 0.5284,
       "step": 520
     },
     {
       "epoch": 0.5635300372142478,
-      "grad_norm": 2.143913984298706,
+      "grad_norm": 1.4143650531768799,
       "learning_rate": 8.74468085106383e-05,
-      "loss": 1.0038,
+      "loss": 0.3619,
       "step": 530
     },
     {
       "epoch": 0.5741626794258373,
-      "grad_norm": 2.285888910293579,
+      "grad_norm": 1.0321277379989624,
       "learning_rate": 8.531914893617021e-05,
-      "loss": 1.2064,
+      "loss": 0.449,
       "step": 540
     },
     {
       "epoch": 0.5847953216374269,
-      "grad_norm": 2.3260293006896973,
+      "grad_norm": 1.4047714471817017,
       "learning_rate": 8.319148936170213e-05,
-      "loss": 1.0499,
+      "loss": 0.3873,
       "step": 550
     },
     {
       "epoch": 0.5954279638490165,
-      "grad_norm": 2.3417248725891113,
+      "grad_norm": 1.176665186882019,
       "learning_rate": 8.106382978723405e-05,
-      "loss": 1.1371,
+      "loss": 0.3208,
       "step": 560
     },
     {
       "epoch": 0.6060606060606061,
-      "grad_norm": 2.194345474243164,
+      "grad_norm": 1.349563479423523,
       "learning_rate": 7.893617021276596e-05,
-      "loss": 1.0571,
+      "loss": 0.3534,
       "step": 570
     },
     {
       "epoch": 0.6166932482721956,
-      "grad_norm": 2.3759639263153076,
+      "grad_norm": 1.899173617362976,
       "learning_rate": 7.680851063829788e-05,
-      "loss": 0.9709,
+      "loss": 0.4149,
       "step": 580
     },
     {
       "epoch": 0.6273258904837852,
-      "grad_norm": 1.7851307392120361,
+      "grad_norm": 1.041756272315979,
       "learning_rate": 7.46808510638298e-05,
-      "loss": 1.0751,
+      "loss": 0.2761,
       "step": 590
     },
     {
       "epoch": 0.6379585326953748,
-      "grad_norm": 2.1073718070983887,
+      "grad_norm": 1.1541553735733032,
       "learning_rate": 7.25531914893617e-05,
-      "loss": 1.0453,
+      "loss": 0.3183,
       "step": 600
     },
     {
       "epoch": 0.6485911749069644,
-      "grad_norm": 3.0715222358703613,
+      "grad_norm": 1.7732151746749878,
       "learning_rate": 7.042553191489362e-05,
-      "loss": 1.019,
+      "loss": 0.4356,
       "step": 610
     },
     {
       "epoch": 0.6592238171185539,
-      "grad_norm": 2.7208268642425537,
+      "grad_norm": 2.6027865409851074,
       "learning_rate": 6.829787234042554e-05,
-      "loss": 0.919,
+      "loss": 0.5153,
       "step": 620
     },
     {
       "epoch": 0.6698564593301436,
-      "grad_norm": 1.7897045612335205,
+      "grad_norm": 1.1163185834884644,
       "learning_rate": 6.617021276595745e-05,
-      "loss": 0.9964,
+      "loss": 0.3758,
       "step": 630
     },
     {
       "epoch": 0.6804891015417331,
-      "grad_norm": 2.317929744720459,
+      "grad_norm": 0.8950490355491638,
       "learning_rate": 6.404255319148937e-05,
-      "loss": 1.1598,
+      "loss": 0.3092,
       "step": 640
     },
     {
       "epoch": 0.6911217437533227,
-      "grad_norm": 1.826894760131836,
+      "grad_norm": 0.8353213667869568,
       "learning_rate": 6.191489361702127e-05,
-      "loss": 1.117,
+      "loss": 0.2713,
       "step": 650
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 2.0165112018585205,
+      "grad_norm": 0.9185741543769836,
       "learning_rate": 5.9787234042553196e-05,
-      "loss": 1.0511,
+      "loss": 0.2692,
       "step": 660
     },
     {
       "epoch": 0.7123870281765019,
-      "grad_norm": 1.6636179685592651,
+      "grad_norm": 1.5412646532058716,
       "learning_rate": 5.7659574468085106e-05,
-      "loss": 1.0488,
+      "loss": 0.252,
       "step": 670
     },
     {
       "epoch": 0.7230196703880915,
-      "grad_norm": 2.3491950035095215,
+      "grad_norm": 1.210580825805664,
       "learning_rate": 5.553191489361702e-05,
-      "loss": 1.2297,
+      "loss": 0.2394,
       "step": 680
     },
     {
       "epoch": 0.733652312599681,
-      "grad_norm": 2.28796124458313,
+      "grad_norm": 2.3778483867645264,
       "learning_rate": 5.3404255319148946e-05,
-      "loss": 1.1457,
+      "loss": 0.2672,
       "step": 690
     },
     {
       "epoch": 0.7442849548112705,
-      "grad_norm": 2.550320863723755,
+      "grad_norm": 2.204791784286499,
       "learning_rate": 5.1276595744680856e-05,
-      "loss": 1.069,
+      "loss": 0.3295,
       "step": 700
     },
     {
       "epoch": 0.7549175970228602,
-      "grad_norm": 1.5172102451324463,
+      "grad_norm": 1.610378623008728,
       "learning_rate": 4.9148936170212766e-05,
-      "loss": 0.849,
+      "loss": 0.3868,
       "step": 710
     },
     {
       "epoch": 0.7655502392344498,
-      "grad_norm": 1.7714675664901733,
+      "grad_norm": 1.7490154504776,
       "learning_rate": 4.702127659574468e-05,
-      "loss": 1.1457,
+      "loss": 0.302,
       "step": 720
     },
     {
       "epoch": 0.7761828814460393,
-      "grad_norm": 1.587169885635376,
+      "grad_norm": 1.022546410560608,
       "learning_rate": 4.489361702127659e-05,
-      "loss": 0.9438,
+      "loss": 0.2969,
       "step": 730
     },
     {
       "epoch": 0.786815523657629,
-      "grad_norm": 2.464047908782959,
+      "grad_norm": 1.0458086729049683,
       "learning_rate": 4.276595744680851e-05,
-      "loss": 1.0606,
+      "loss": 0.3652,
       "step": 740
     },
     {
       "epoch": 0.7974481658692185,
-      "grad_norm": 1.6491392850875854,
+      "grad_norm": 1.330607295036316,
       "learning_rate": 4.063829787234043e-05,
-      "loss": 1.0333,
+      "loss": 0.2184,
       "step": 750
     },
     {
       "epoch": 0.8080808080808081,
-      "grad_norm": 2.159282684326172,
+      "grad_norm": 1.8219746351242065,
       "learning_rate": 3.8510638297872344e-05,
-      "loss": 0.9192,
+      "loss": 0.2359,
       "step": 760
     },
     {
       "epoch": 0.8187134502923976,
-      "grad_norm": 1.6473966836929321,
+      "grad_norm": 3.080618143081665,
       "learning_rate": 3.638297872340426e-05,
-      "loss": 1.0218,
+      "loss": 0.3008,
       "step": 770
     },
     {
       "epoch": 0.8293460925039873,
-      "grad_norm": 2.5140249729156494,
+      "grad_norm": 2.212218999862671,
       "learning_rate": 3.425531914893617e-05,
-      "loss": 1.1425,
+      "loss": 0.2675,
       "step": 780
     },
     {
       "epoch": 0.8399787347155768,
-      "grad_norm": 1.8191956281661987,
+      "grad_norm": 1.714879035949707,
       "learning_rate": 3.212765957446809e-05,
-      "loss": 1.0179,
+      "loss": 0.2914,
       "step": 790
     },
     {
       "epoch": 0.8506113769271664,
-      "grad_norm": 1.570918083190918,
+      "grad_norm": 2.811004161834717,
       "learning_rate": 3e-05,
-      "loss": 1.0624,
+      "loss": 0.2235,
       "step": 800
     },
     {
       "epoch": 0.861244019138756,
-      "grad_norm": 2.4648308753967285,
+      "grad_norm": 2.3071866035461426,
       "learning_rate": 2.7872340425531918e-05,
-      "loss": 1.0768,
+      "loss": 0.2387,
       "step": 810
     },
     {
       "epoch": 0.8718766613503456,
-      "grad_norm": 2.4284791946411133,
+      "grad_norm": 2.134385108947754,
       "learning_rate": 2.574468085106383e-05,
-      "loss": 1.0748,
+      "loss": 0.2365,
       "step": 820
     },
     {
       "epoch": 0.8825093035619351,
-      "grad_norm": 2.543541193008423,
+      "grad_norm": 1.6607768535614014,
       "learning_rate": 2.3617021276595748e-05,
-      "loss": 1.051,
+      "loss": 0.3073,
       "step": 830
     },
     {
       "epoch": 0.8931419457735247,
-      "grad_norm": 2.0287232398986816,
+      "grad_norm": 2.4962167739868164,
       "learning_rate": 2.148936170212766e-05,
-      "loss": 0.9987,
+      "loss": 0.2799,
       "step": 840
     },
     {
       "epoch": 0.9037745879851143,
-      "grad_norm": 2.2504048347473145,
+      "grad_norm": 3.272426128387451,
       "learning_rate": 1.9361702127659575e-05,
-      "loss": 0.9468,
+      "loss": 0.2627,
       "step": 850
     },
     {
       "epoch": 0.9144072301967039,
-      "grad_norm": 1.889223337173462,
+      "grad_norm": 0.6173011064529419,
       "learning_rate": 1.723404255319149e-05,
-      "loss": 1.1471,
+      "loss": 0.2336,
       "step": 860
     },
     {
       "epoch": 0.9250398724082934,
-      "grad_norm": 2.414099931716919,
+      "grad_norm": 1.584494948387146,
       "learning_rate": 1.5106382978723405e-05,
-      "loss": 1.0941,
+      "loss": 0.2081,
       "step": 870
     },
     {
       "epoch": 0.935672514619883,
-      "grad_norm": 1.7655644416809082,
+      "grad_norm": 0.16361036896705627,
       "learning_rate": 1.2978723404255318e-05,
-      "loss": 1.0504,
+      "loss": 0.3102,
       "step": 880
     },
     {
       "epoch": 0.9463051568314726,
-      "grad_norm": 1.6641113758087158,
+      "grad_norm": 1.1021312475204468,
       "learning_rate": 1.0851063829787235e-05,
-      "loss": 1.1144,
+      "loss": 0.2414,
       "step": 890
     },
     {
       "epoch": 0.9569377990430622,
-      "grad_norm": 2.2806735038757324,
+      "grad_norm": 1.4342254400253296,
       "learning_rate": 8.72340425531915e-06,
-      "loss": 1.0884,
+      "loss": 0.2268,
       "step": 900
     },
     {
       "epoch": 0.9675704412546517,
-      "grad_norm": 2.1201162338256836,
+      "grad_norm": 3.8059401512145996,
       "learning_rate": 6.595744680851064e-06,
-      "loss": 1.0405,
+      "loss": 0.192,
       "step": 910
     },
     {
       "epoch": 0.9782030834662414,
-      "grad_norm": 1.651154637336731,
+      "grad_norm": 3.46911883354187,
       "learning_rate": 4.468085106382979e-06,
-      "loss": 0.9533,
+      "loss": 0.2758,
       "step": 920
     },
     {
       "epoch": 0.988835725677831,
-      "grad_norm": 2.6276893615722656,
+      "grad_norm": 1.878474235534668,
       "learning_rate": 2.3404255319148935e-06,
-      "loss": 1.0675,
+      "loss": 0.2006,
       "step": 930
     },
     {
       "epoch": 0.9994683678894205,
-      "grad_norm": 1.7685601711273193,
+      "grad_norm": 4.247520923614502,
       "learning_rate": 2.1276595744680852e-07,
-      "loss": 0.8962,
+      "loss": 0.2977,
       "step": 940
     }
   ],
@@ -685,7 +685,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2872735048949760.0,
+  "total_flos": 5.314124516155392e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

checkpoint-940/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8da861a048e54d4badc72113caff5faf9a0f0d6fdc304e556f2195e8ed22968a
+oid sha256:547c8e7ff6d0180957de69fa91373006aca497154b790be7261ec4a80d705d40
 size 5304

runs/May04_20-23-18_165-1-77-80/events.out.tfevents.1746390198.165-1-77-80.15451.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09fe710f9e4dc912c0a0bfeca74e1a1c07e6594950fd12250612246404efdb03
+size 25190

runs/May04_21-11-15_165-1-77-80/events.out.tfevents.1746393075.165-1-77-80.19842.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f443d17772c29fcf88525f499d5e14e3ea42364448211ee79556023e5c004f00
+size 25190

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbd55b657d538b783432d985a0a85c8a96173f327724f2ed74e8966d4a82c7d
-size 17208851
+oid sha256:0968dcc0ee8e56c7dccd34a7f51f8065ea0cb9e2cc529e3243d1e5c0a4bdaa0c
+size 17208754