Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48aa3685ad8b6ea63626e1b86b68d7d8c22a114d11bdf1ae962ac4d8772e4918
+oid sha256:198d342ef19c8d689e7d5807eef3d0db68d68033424117e91cd08740f64cb48e
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7931480ac71b52693036fbf4816bad532b8a6655783216f5b7f99ef27944157f
+oid sha256:56acf5affbb1287f1122bd505d97a6ef8790e1fbf13e5129a98d6ed4d987c9e0
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afbbeff9c2106aa6747a9a6b6d1f2974325978cb30b288d183425c5cf2062c3
+oid sha256:997b37e8e4d4313266e5aafe8f4d418b086633a9c94b4c13db86ae839aa09b15
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8eccac390378b22aeb148c260b00bec01d948946d8363d5282899af673e0e86
+oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04222972972972973,
+  "epoch": 0.0633445945945946,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 3.929,
       "eval_steps_per_second": 1.968,
       "step": 50
+    },
+    {
+      "epoch": 0.04307432432432432,
+      "grad_norm": 5.329013347625732,
+      "learning_rate": 0.00011391731009600654,
+      "loss": 0.2995,
+      "step": 51
+    },
+    {
+      "epoch": 0.04391891891891892,
+      "grad_norm": 2.9597175121307373,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.1657,
+      "step": 52
+    },
+    {
+      "epoch": 0.044763513513513514,
+      "grad_norm": 4.471776485443115,
+      "learning_rate": 0.00010697564737441252,
+      "loss": 0.2049,
+      "step": 53
+    },
+    {
+      "epoch": 0.04560810810810811,
+      "grad_norm": 1.612620234489441,
+      "learning_rate": 0.00010348994967025012,
+      "loss": 0.0311,
+      "step": 54
+    },
+    {
+      "epoch": 0.0464527027027027,
+      "grad_norm": 8.52501392364502,
+      "learning_rate": 0.0001,
+      "loss": 0.4772,
+      "step": 55
+    },
+    {
+      "epoch": 0.0472972972972973,
+      "grad_norm": 11.812604904174805,
+      "learning_rate": 9.651005032974994e-05,
+      "loss": 0.6968,
+      "step": 56
+    },
+    {
+      "epoch": 0.04814189189189189,
+      "grad_norm": 3.004138708114624,
+      "learning_rate": 9.302435262558747e-05,
+      "loss": 0.66,
+      "step": 57
+    },
+    {
+      "epoch": 0.048986486486486486,
+      "grad_norm": 7.490670204162598,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.5833,
+      "step": 58
+    },
+    {
+      "epoch": 0.04983108108108108,
+      "grad_norm": 3.6796233654022217,
+      "learning_rate": 8.608268990399349e-05,
+      "loss": 0.5957,
+      "step": 59
+    },
+    {
+      "epoch": 0.05067567567567568,
+      "grad_norm": 0.1634790003299713,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.0041,
+      "step": 60
+    },
+    {
+      "epoch": 0.05152027027027027,
+      "grad_norm": 6.999042510986328,
+      "learning_rate": 7.920883091822408e-05,
+      "loss": 0.4254,
+      "step": 61
+    },
+    {
+      "epoch": 0.052364864864864864,
+      "grad_norm": 1.4367730617523193,
+      "learning_rate": 7.580781044003324e-05,
+      "loss": 0.0328,
+      "step": 62
+    },
+    {
+      "epoch": 0.05320945945945946,
+      "grad_norm": 4.265451908111572,
+      "learning_rate": 7.243626441830009e-05,
+      "loss": 0.1511,
+      "step": 63
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 2.716522693634033,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.2104,
+      "step": 64
+    },
+    {
+      "epoch": 0.05489864864864865,
+      "grad_norm": 1.9555131196975708,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.1398,
+      "step": 65
+    },
+    {
+      "epoch": 0.05574324324324324,
+      "grad_norm": 2.594125509262085,
+      "learning_rate": 6.25393406584088e-05,
+      "loss": 0.2959,
+      "step": 66
+    },
+    {
+      "epoch": 0.056587837837837836,
+      "grad_norm": 4.196368217468262,
+      "learning_rate": 5.9326335692419995e-05,
+      "loss": 0.2828,
+      "step": 67
+    },
+    {
+      "epoch": 0.057432432432432436,
+      "grad_norm": 7.690390110015869,
+      "learning_rate": 5.616288532109225e-05,
+      "loss": 0.6751,
+      "step": 68
+    },
+    {
+      "epoch": 0.05827702702702703,
+      "grad_norm": 5.08601713180542,
+      "learning_rate": 5.305284372141095e-05,
+      "loss": 0.7061,
+      "step": 69
+    },
+    {
+      "epoch": 0.05912162162162162,
+      "grad_norm": 0.743725597858429,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0161,
+      "step": 70
+    },
+    {
+      "epoch": 0.059966216216216214,
+      "grad_norm": 1.1107006072998047,
+      "learning_rate": 4.700807357667952e-05,
+      "loss": 0.0289,
+      "step": 71
+    },
+    {
+      "epoch": 0.060810810810810814,
+      "grad_norm": 3.6318747997283936,
+      "learning_rate": 4.4080709652925336e-05,
+      "loss": 0.2351,
+      "step": 72
+    },
+    {
+      "epoch": 0.06165540540540541,
+      "grad_norm": 3.365870714187622,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.2887,
+      "step": 73
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 2.29145884513855,
+      "learning_rate": 3.843385246743417e-05,
+      "loss": 0.2137,
+      "step": 74
+    },
+    {
+      "epoch": 0.0633445945945946,
+      "grad_norm": 0.12063544243574142,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.0043,
+      "step": 75
+    },
+    {
+      "epoch": 0.0633445945945946,
+      "eval_loss": 0.14590471982955933,
+      "eval_runtime": 126.9422,
+      "eval_samples_per_second": 3.931,
+      "eval_steps_per_second": 1.969,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -400,7 +583,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.6109411688448e+16,
+  "total_flos": 9.9164117532672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null