Training in progress, step 91, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0696594f83839f848a9fb64316cd8f0fa1678b6a6ebd76756d0417be0a738d2d
+oid sha256:b22bbe910e4273c4f0031a05c86bbfc9f89b9d85c82a175790bf8e3596b6a0e9
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f433fdbdda0f9a302c42618afafd1488d146199d9b0e84b79c28cab70c4b869a
+oid sha256:eb75f06266fa6dd150fef8eceb2d15d978d4247b44bf87bfe9a05f7684ff37b1
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0bfe203dcc9b3b030e44f5295d53d381de790a5365f0913e245991089bf10fb
+oid sha256:de8201a81a96f55bea468ad3adab41e3c839bfceb39d93b4679063b40be0de53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d6e5f76805b36e4d76ee2a3b48ba3bedb1c2bda79be4f5c70f809dd0d57438
+oid sha256:e37872b45362e9c63412b1b167580155e0789faf44bbc81b017091d0c0912d87
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02160066463583495,
+  "epoch": 0.025200775408474107,
   "eval_steps": 13,
-  "global_step": 78,
+  "global_step": 91,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,42 @@
       "eval_samples_per_second": 13.188,
       "eval_steps_per_second": 1.65,
       "step": 78
+    },
+    {
+      "epoch": 0.02243145942952091,
+      "grad_norm": 2.3494913578033447,
+      "learning_rate": 4.887809678520976e-05,
+      "loss": 1.4743,
+      "step": 81
+    },
+    {
+      "epoch": 0.02326225422320687,
+      "grad_norm": 1.7049707174301147,
+      "learning_rate": 4.551803455482833e-05,
+      "loss": 1.3911,
+      "step": 84
+    },
+    {
+      "epoch": 0.024093049016892826,
+      "grad_norm": 2.5893452167510986,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.3843,
+      "step": 87
+    },
+    {
+      "epoch": 0.024923843810578786,
+      "grad_norm": 2.1799535751342773,
+      "learning_rate": 3.887395330218429e-05,
+      "loss": 1.4394,
+      "step": 90
+    },
+    {
+      "epoch": 0.025200775408474107,
+      "eval_loss": 0.3514753580093384,
+      "eval_runtime": 460.8437,
+      "eval_samples_per_second": 13.198,
+      "eval_steps_per_second": 1.651,
+      "step": 91
     }
   ],
   "logging_steps": 3,
@@ -264,7 +300,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2672972249838387e+17,
+  "total_flos": 1.4868290277369446e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null