Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c7a23d41d76dd3c71ac58f09cc2da9d8f36efb2ffecf12c1318ab51f307df1
+oid sha256:3fab0666d425f2b1a8d264cbddaa5c05c26073a25d3cd66089ef79095b5f43ac
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a40b5f89a1f23f6a0ae60b3ad69602b5b719032bf028990bd7bf0267ffafd9a
+oid sha256:465e632fca81892554919115658a88b89d8094cf9c23b354320c6e259797791f
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b52d2891588f3bc22db833fbe6cf2657d7384a09063c47d00a63155fa7f7707
+oid sha256:67a8180afa19bb4034c7a74f5ec57ad823d7eea821b9aad8d766a2070fd77c8e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85eac2daddfe8e3f78a5d6ef1e9ba13c04651694635a9ed76369a20726389db
+oid sha256:8d43bd90ad476e419738deb9472ad85fd5991005a147e1627aa99867bdfc5655
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.051068264721209,
+  "epoch": 1.201146430432517,
   "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": 119.753,
       "eval_steps_per_second": 60.171,
       "step": 63
+    },
+    {
+      "epoch": 1.1010943199583116,
+      "grad_norm": 0.08838286995887756,
+      "learning_rate": 5.7491597710807114e-05,
+      "loss": 11.7056,
+      "step": 66
+    },
+    {
+      "epoch": 1.1511203751954142,
+      "grad_norm": 0.08494899421930313,
+      "learning_rate": 4.904122071918801e-05,
+      "loss": 11.7037,
+      "step": 69
+    },
+    {
+      "epoch": 1.201146430432517,
+      "grad_norm": 0.07477749139070511,
+      "learning_rate": 4.095071251953399e-05,
+      "loss": 11.7745,
+      "step": 72
+    },
+    {
+      "epoch": 1.201146430432517,
+      "eval_loss": 11.73630428314209,
+      "eval_runtime": 1.6967,
+      "eval_samples_per_second": 119.645,
+      "eval_steps_per_second": 60.117,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 117793161216000.0,
+  "total_flos": 134591490293760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null