Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8927683e0409ef21ad2b9bc8cc13c6800cfb5590a23142ced607e08869d074fb
+oid sha256:9230a8f1667356b7ad63b361e8fff561dc479c69811d39b580b9a55743136501
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3219639986ad86e4811f92ac562e0c772d743df77fd611625fcebdb38339be0
+oid sha256:1589c4d786a9ec20e39e5d8cd54b1caca272380901a11607662ecea8e3582353
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f2115101af4d4b5e45b0940e0c622ad77b0a5d2f224127198cef7127193e2f8
+oid sha256:9b57e66d927cb63d49164c233351ff4f91afc1c694e0198261b327f8e4910ca2
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca19c73ed66fbba4990e15bea507703b1f5228216fc2abeb22d8d074d1228662
+oid sha256:1ad037ff70efcc9b0b2a0dc7ac7e0d0f1a8eebe556624b17336fdf4fa1dfdb3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7995625683486955,
+  "epoch": 2.9995313232307454,
   "eval_steps": 500,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -121,6 +121,21 @@
       "learning_rate": 9.066666666666667e-05,
       "loss": 1.3047,
       "step": 1400
+    },
+    {
+      "epoch": 2.9995313232307454,
+      "grad_norm": 0.13826213777065277,
+      "learning_rate": 9e-05,
+      "loss": 1.3061,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9995313232307454,
+      "eval_loss": 1.1681571006774902,
+      "eval_runtime": 781.2456,
+      "eval_samples_per_second": 19.868,
+      "eval_steps_per_second": 2.484,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -140,7 +155,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.185031282893783e+18,
+  "total_flos": 2.3411062540819497e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null