Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15097c24bd08aa44cdec3e2752e591d856c783471376bb8a33de7bf49c1326c3
+oid sha256:575b73dab3eea82abe0d44eb0a886c772679eec9de8c955800f65f27b5f43086
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111d9230f6ef96061eba094cdb3190b621eebb9d6ba9190e0241f01f7c1ebb07
+oid sha256:d803d5b32045bc570550fa75819369589f89e6c0e278290c839f351837dd2614
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5d410b3554f51a9e330e4afd32a4b9dfb61483b755d339ad915a14e3add09dd
+oid sha256:ae23c720e43827fac7ec9738d78285292b2b49a0ea5579feabe2dcfc07f544e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005862351975612616,
+  "epoch": 0.007034822370735139,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,28 @@
       "eval_samples_per_second": 6.546,
       "eval_steps_per_second": 0.818,
       "step": 25
+    },
+    {
+      "epoch": 0.006331340133661625,
+      "grad_norm": 1.4862679243087769,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 2.346,
+      "step": 27
+    },
+    {
+      "epoch": 0.007034822370735139,
+      "grad_norm": 1.4574503898620605,
+      "learning_rate": 5e-05,
+      "loss": 2.2429,
+      "step": 30
+    },
+    {
+      "epoch": 0.007034822370735139,
+      "eval_loss": 0.5047998428344727,
+      "eval_runtime": 1097.4525,
+      "eval_samples_per_second": 6.544,
+      "eval_steps_per_second": 0.818,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -130,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.4401180721152e+16,
+  "total_flos": 7.72814168653824e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null