Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd83e8a68ff0b516522fae1b1dfdddc57ab17f6a67f83b6713c5d3b4020df2f
+oid sha256:681141d77b2b9a13dbc9dcb10aba6f017bca801927047f9b59b9de2a2f547b0e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f995c8da7cf862606d0b3fab16e8b9d5bbe66b1aab0a12da1e7bbbbf4b6fd747
+oid sha256:c7c86949afa86d85d014b8d765f011c79adc504ae1818f566596f9c3d1ec6fb1
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
+oid sha256:eaef23ad6b9358048cfa2eb81866d8f39693a1c7df686b619cd9d9ea3051d3a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05357142857142857,
+  "epoch": 0.060267857142857144,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 13.984,
       "eval_steps_per_second": 1.748,
       "step": 72
+    },
+    {
+      "epoch": 0.05580357142857143,
+      "grad_norm": 6.060158729553223,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 3.9547,
+      "step": 75
+    },
+    {
+      "epoch": 0.05803571428571429,
+      "grad_norm": 4.884081840515137,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 3.8446,
+      "step": 78
+    },
+    {
+      "epoch": 0.060267857142857144,
+      "grad_norm": 5.20225191116333,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 3.8639,
+      "step": 81
+    },
+    {
+      "epoch": 0.060267857142857144,
+      "eval_loss": 4.055640697479248,
+      "eval_runtime": 161.812,
+      "eval_samples_per_second": 13.992,
+      "eval_steps_per_second": 1.749,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0683176883270451e+17,
+  "total_flos": 1.2018573993679258e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null