Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb8fe6e75c1e7ebc7abc93ede0705655150a01d32070837e95f8328ce2a3745
+oid sha256:1add8c17dea05a8daadd8b15db544a6078553d43852070b848a02932b2c0b0fb
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed869223fc14437aac55c22dd4b2376ab797e052e1e35da5df87c62ab5d572ec
+oid sha256:dc3e6c8f83617e1fe431227c2825344eeb249df7cfe00dc2233b8db45cc16461
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aacd22c043d7f6609b2b994e4e0a778f43a4761465f4b4f3dcd83d7e6cfd870
+oid sha256:9d1b7498e23cf7cd4cfe8b9d6e0b97ab34a946dd843cdcf11d48dc8e3e01b803
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013763722759298706,
+  "epoch": 0.01572996886776995,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 232.311,
       "eval_steps_per_second": 29.046,
       "step": 63
+    },
+    {
+      "epoch": 0.01441913812878912,
+      "grad_norm": 0.2436102032661438,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.266,
+      "step": 66
+    },
+    {
+      "epoch": 0.015074553498279535,
+      "grad_norm": 0.2320987582206726,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.2794,
+      "step": 69
+    },
+    {
+      "epoch": 0.01572996886776995,
+      "grad_norm": 0.21924351155757904,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.2635,
+      "step": 72
+    },
+    {
+      "epoch": 0.01572996886776995,
+      "eval_loss": 10.265777587890625,
+      "eval_runtime": 33.0027,
+      "eval_samples_per_second": 233.618,
+      "eval_steps_per_second": 29.21,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 14055383236608.0,
+  "total_flos": 16063295127552.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null