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:e6cf6d361f6bdde8eb2e4b53a1e71679cf96d0e36037dccefaa7fe774ab674c9
+oid sha256:369a9fc237a5c7f6cc1f54de33d98f41238e58f2c3eb5548a8ec14c776a841bd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce3f03d7458ba6af8200a5ce2e0b5e35088c12deb95e27e0d3a3abc0df234cde
+oid sha256:50e5a48ca90eefbb8355aa35d3835606ae62005ee672a04e3c9be2d3013ef078
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07899f311009253221ecb7c812577e712b3036bf5bf7d033d3f1db6da6056cbf
+oid sha256:e9e81497461b7eddb6cf48b4fb01e48dcac128bf74d88043318d66719e95e04e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13908205841446453,
+  "epoch": 0.2086230876216968,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 0.0,
       "step": 50
+    },
+    {
+      "epoch": 0.14186369958275383,
+      "grad_norm": 7.217805432446767e-06,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.14464534075104313,
+      "grad_norm": 4.9700533963914495e-06,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.1474269819193324,
+      "grad_norm": 2.5943822038243525e-05,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.1502086230876217,
+      "grad_norm": 1.6696252714609727e-05,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.1502086230876217,
+      "eval_loss": 0.0023401842918246984,
+      "eval_runtime": 65.5294,
+      "eval_samples_per_second": 4.624,
+      "eval_steps_per_second": 0.58,
+      "step": 54
+    },
+    {
+      "epoch": 0.15299026425591097,
+      "grad_norm": 3.8724078876839485e-06,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.15577190542420027,
+      "grad_norm": 1.2276537745492533e-05,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.15855354659248957,
+      "grad_norm": 2.5876863219309598e-05,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.16133518776077885,
+      "grad_norm": 8.749322296353057e-05,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.16411682892906815,
+      "grad_norm": 1.712118864816148e-05,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.16689847009735745,
+      "grad_norm": 2.308480179635808e-05,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.16968011126564672,
+      "grad_norm": 7.027095762168756e-06,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.17246175243393602,
+      "grad_norm": 7.382780040643411e-06,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.17524339360222532,
+      "grad_norm": 2.3965229047462344e-05,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.17524339360222532,
+      "eval_loss": 0.0028376129921525717,
+      "eval_runtime": 65.4873,
+      "eval_samples_per_second": 4.627,
+      "eval_steps_per_second": 0.58,
+      "step": 63
+    },
+    {
+      "epoch": 0.1780250347705146,
+      "grad_norm": 1.0226192898699082e-05,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.1808066759388039,
+      "grad_norm": 1.0573015060799662e-05,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.1835883171070932,
+      "grad_norm": 9.868974302662537e-06,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.18636995827538247,
+      "grad_norm": 2.5517723770462908e-05,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.18915159944367177,
+      "grad_norm": 1.1723280294972938e-05,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.19193324061196107,
+      "grad_norm": 7.75958142185118e-06,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.19471488178025034,
+      "grad_norm": 1.409273136232514e-05,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.19749652294853964,
+      "grad_norm": 1.160700685431948e-05,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.20027816411682892,
+      "grad_norm": 1.2022701412206516e-05,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.20027816411682892,
+      "eval_loss": 0.00283798947930336,
+      "eval_runtime": 65.5515,
+      "eval_samples_per_second": 4.622,
+      "eval_steps_per_second": 0.58,
+      "step": 72
+    },
+    {
+      "epoch": 0.20305980528511822,
+      "grad_norm": 8.21447520138463e-06,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.20584144645340752,
+      "grad_norm": 8.699649697518907e-06,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.2086230876216968,
+      "grad_norm": 2.3488306396757253e-05,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.196306650536346e+16,
+  "total_flos": 1.0905743068338586e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null