Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6555cf8a29457276732fd9bc2fdc5a89fe9e051401899dfd5183783ebe3da4
+oid sha256:6686f5ae7dfc878f72936847da06eeac01008e09df88347b2f30a460459a377f
 size 1302756720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:504411e42e399d958bc8cb18afcf24a3f8a21f26cc0bd9f773974fc4513b2680
+oid sha256:7270a31c8d4fb2fc28c50c143e8f841de2f9ec598cf624cf28e9bfa5554c75b2
 size 2565803322

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1fa93da0c2875fae2b3dcbada512eeb6a982b69738b73857be3d8519295167d
+oid sha256:2897c38dac08136a5628ce08901d07d2cfb15ee9e8714b83b6c60b1d028942ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1512b05ecde3d79b8a9aab4d842fe779f22331ec3de110dfb95adf173e5e7b77
+oid sha256:33564dd5ef98daba647cdcb8031cbd9869053733e31acfe850ce8e6667769898
 size 1256

last-checkpoint/trainer_state.json

@@ -1,238 +1,125 @@
 {
-  "best_metric": 1.2389616966247559,
+  "best_metric": 1.324646234512329,
   "best_model_checkpoint": "./output/checkpoint-150",
-  "epoch": 0.018648598247031765,
+  "epoch": 0.004662294470518758,
   "eval_steps": 150,
-  "global_step": 300,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0006216199415677255,
-      "grad_norm": 17.246639251708984,
+      "epoch": 0.0003108196313679172,
+      "grad_norm": 16.272132873535156,
       "learning_rate": 1.0000000000000004e-05,
-      "loss": 0.97,
+      "loss": 1.0644,
       "step": 10
     },
     {
-      "epoch": 0.001243239883135451,
-      "grad_norm": 17.03240203857422,
+      "epoch": 0.0006216392627358344,
+      "grad_norm": 25.7003116607666,
       "learning_rate": 2.000000000000001e-05,
-      "loss": 1.0066,
+      "loss": 1.2499,
       "step": 20
     },
     {
-      "epoch": 0.0018648598247031764,
-      "grad_norm": 20.47074317932129,
+      "epoch": 0.0009324588941037516,
+      "grad_norm": 31.47926902770996,
       "learning_rate": 3.0000000000000008e-05,
-      "loss": 0.8208,
+      "loss": 1.2088,
       "step": 30
     },
     {
-      "epoch": 0.002486479766270902,
-      "grad_norm": 15.462767601013184,
+      "epoch": 0.0012432785254716688,
+      "grad_norm": 16.037790298461914,
       "learning_rate": 4.000000000000002e-05,
-      "loss": 0.9462,
+      "loss": 0.8968,
       "step": 40
     },
     {
-      "epoch": 0.0031080997078386276,
-      "grad_norm": 13.560821533203125,
+      "epoch": 0.001554098156839586,
+      "grad_norm": 21.551687240600586,
       "learning_rate": 5.0000000000000016e-05,
-      "loss": 1.0112,
+      "loss": 1.1641,
       "step": 50
     },
     {
-      "epoch": 0.0037297196494063527,
-      "grad_norm": 15.589034080505371,
+      "epoch": 0.0018649177882075032,
+      "grad_norm": 12.384719848632812,
       "learning_rate": 6.0000000000000015e-05,
-      "loss": 1.2022,
+      "loss": 1.1243,
       "step": 60
     },
     {
-      "epoch": 0.004351339590974079,
-      "grad_norm": 12.097992897033691,
+      "epoch": 0.0021757374195754205,
+      "grad_norm": 19.645782470703125,
       "learning_rate": 7.000000000000002e-05,
-      "loss": 0.8705,
+      "loss": 0.9319,
       "step": 70
     },
     {
-      "epoch": 0.004972959532541804,
-      "grad_norm": 11.035839080810547,
+      "epoch": 0.0024865570509433376,
+      "grad_norm": 27.288326263427734,
       "learning_rate": 8.000000000000003e-05,
-      "loss": 1.0257,
+      "loss": 1.3724,
       "step": 80
     },
     {
-      "epoch": 0.005594579474109529,
-      "grad_norm": 21.564220428466797,
+      "epoch": 0.0027973766823112547,
+      "grad_norm": 24.819137573242188,
       "learning_rate": 9.000000000000003e-05,
-      "loss": 1.1064,
+      "loss": 1.1858,
       "step": 90
     },
     {
-      "epoch": 0.006216199415677255,
-      "grad_norm": 16.1055908203125,
+      "epoch": 0.003108196313679172,
+      "grad_norm": 20.58218765258789,
       "learning_rate": 0.00010000000000000003,
-      "loss": 1.0177,
+      "loss": 1.5071,
       "step": 100
     },
     {
-      "epoch": 0.00683781935724498,
-      "grad_norm": 20.55684471130371,
+      "epoch": 0.0034190159450470893,
+      "grad_norm": 21.837909698486328,
       "learning_rate": 9.999897234791833e-05,
-      "loss": 1.0674,
+      "loss": 0.8717,
       "step": 110
     },
     {
-      "epoch": 0.0074594392988127055,
-      "grad_norm": 11.746541023254395,
+      "epoch": 0.0037298355764150064,
+      "grad_norm": 24.357887268066406,
       "learning_rate": 9.9995889433916e-05,
-      "loss": 1.0558,
+      "loss": 1.1974,
       "step": 120
     },
     {
-      "epoch": 0.00808105924038043,
-      "grad_norm": 12.144071578979492,
+      "epoch": 0.0040406552077829234,
+      "grad_norm": 31.516538619995117,
       "learning_rate": 9.999075138471954e-05,
-      "loss": 1.0471,
+      "loss": 1.2452,
       "step": 130
     },
     {
-      "epoch": 0.008702679181948158,
-      "grad_norm": 10.344304084777832,
+      "epoch": 0.004351474839150841,
+      "grad_norm": 18.15753173828125,
       "learning_rate": 9.998355841153402e-05,
-      "loss": 0.9588,
+      "loss": 1.2285,
       "step": 140
     },
     {
-      "epoch": 0.009324299123515883,
-      "grad_norm": 13.215913772583008,
+      "epoch": 0.004662294470518758,
+      "grad_norm": 5.471529483795166,
       "learning_rate": 9.997431081003442e-05,
-      "loss": 0.8682,
+      "loss": 1.0377,
       "step": 150
     },
     {
-      "epoch": 0.009324299123515883,
-      "eval_loss": 1.2389616966247559,
-      "eval_runtime": 41.9043,
-      "eval_samples_per_second": 11.932,
-      "eval_steps_per_second": 11.932,
+      "epoch": 0.004662294470518758,
+      "eval_loss": 1.324646234512329,
+      "eval_runtime": 42.8229,
+      "eval_samples_per_second": 11.676,
+      "eval_steps_per_second": 11.676,
       "step": 150
-    },
-    {
-      "epoch": 0.009945919065083608,
-      "grad_norm": 14.931775093078613,
-      "learning_rate": 9.996300896035342e-05,
-      "loss": 1.0222,
-      "step": 160
-    },
-    {
-      "epoch": 0.010567539006651333,
-      "grad_norm": 11.902103424072266,
-      "learning_rate": 9.994965332706576e-05,
-      "loss": 1.3001,
-      "step": 170
-    },
-    {
-      "epoch": 0.011189158948219058,
-      "grad_norm": 22.0516300201416,
-      "learning_rate": 9.993424445916925e-05,
-      "loss": 1.3244,
-      "step": 180
-    },
-    {
-      "epoch": 0.011810778889786785,
-      "grad_norm": 9.399397850036621,
-      "learning_rate": 9.991678299006208e-05,
-      "loss": 1.1218,
-      "step": 190
-    },
-    {
-      "epoch": 0.01243239883135451,
-      "grad_norm": 11.20373821258545,
-      "learning_rate": 9.989726963751685e-05,
-      "loss": 1.0998,
-      "step": 200
-    },
-    {
-      "epoch": 0.013054018772922235,
-      "grad_norm": 12.058830261230469,
-      "learning_rate": 9.987570520365106e-05,
-      "loss": 0.8901,
-      "step": 210
-    },
-    {
-      "epoch": 0.01367563871448996,
-      "grad_norm": 18.857656478881836,
-      "learning_rate": 9.985209057489412e-05,
-      "loss": 1.16,
-      "step": 220
-    },
-    {
-      "epoch": 0.014297258656057686,
-      "grad_norm": 17.041954040527344,
-      "learning_rate": 9.982642672195095e-05,
-      "loss": 1.1254,
-      "step": 230
-    },
-    {
-      "epoch": 0.014918878597625411,
-      "grad_norm": 21.957040786743164,
-      "learning_rate": 9.979871469976199e-05,
-      "loss": 1.0891,
-      "step": 240
-    },
-    {
-      "epoch": 0.015540498539193138,
-      "grad_norm": 17.357450485229492,
-      "learning_rate": 9.976895564745994e-05,
-      "loss": 1.4696,
-      "step": 250
-    },
-    {
-      "epoch": 0.01616211848076086,
-      "grad_norm": 20.507247924804688,
-      "learning_rate": 9.97371507883229e-05,
-      "loss": 1.1785,
-      "step": 260
-    },
-    {
-      "epoch": 0.016783738422328588,
-      "grad_norm": 13.351741790771484,
-      "learning_rate": 9.970330142972404e-05,
-      "loss": 1.1672,
-      "step": 270
-    },
-    {
-      "epoch": 0.017405358363896315,
-      "grad_norm": 12.915800094604492,
-      "learning_rate": 9.966740896307794e-05,
-      "loss": 0.9764,
-      "step": 280
-    },
-    {
-      "epoch": 0.01802697830546404,
-      "grad_norm": 17.168745040893555,
-      "learning_rate": 9.962947486378328e-05,
-      "loss": 1.32,
-      "step": 290
-    },
-    {
-      "epoch": 0.018648598247031765,
-      "grad_norm": 21.55893325805664,
-      "learning_rate": 9.958950069116233e-05,
-      "loss": 1.0517,
-      "step": 300
-    },
-    {
-      "epoch": 0.018648598247031765,
-      "eval_loss": 1.2531065940856934,
-      "eval_runtime": 43.4681,
-      "eval_samples_per_second": 11.503,
-      "eval_steps_per_second": 11.503,
-      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -252,8 +139,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.40239103461294e+16,
-  "train_batch_size": 8,
+  "total_flos": 1.370537077794816e+16,
+  "train_batch_size": 4,
   "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:ed1fc0280ad76bf7eefe5890f6b7719cb4a29865b4802a8fa0cc911a4794b1f3
+oid sha256:39a0b375dd911e66cfcb8681bea9d7ab3fa3c0a9af046afc9badec1306fe469f
 size 5496