Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fccfe89586bf927bb2e6b63a9b1cc8c53e6736fbbed03b38d6dc9828525f59de
+oid sha256:98f7cc0df27b42faacb17ee8a065ec28367e4261d78510cfea42b1578da766f5
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2296d3100ab2465cf0fe6d5b9449e2a68ecc6795c38d384a517e9591cf1a67d4
+oid sha256:39e4a1150c1cfa610f53dc74ef94e82a5a96af126a0a1734d52f5861c1f2ec35
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d27065c456970240a93dd508456ad4cae86737b3d23ff535ff52a8c41bbae99
+oid sha256:e23e570a096e506720de336b086077d52febc7c90915813563d6f5969e0c68c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5393258426966292,
+  "epoch": 0.6292134831460674,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,21 @@
       "eval_samples_per_second": 95.493,
       "eval_steps_per_second": 24.381,
       "step": 30
+    },
+    {
+      "epoch": 0.5932584269662922,
+      "grad_norm": 0.44238442182540894,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 11.904,
+      "step": 33
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "eval_loss": 11.900728225708008,
+      "eval_runtime": 0.9786,
+      "eval_samples_per_second": 96.054,
+      "eval_steps_per_second": 24.524,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 283826257920.0,
+  "total_flos": 330829332480.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null