Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db964d5273caec605737c0abbdd743fcda2c2f5af647b326924209acdcb6f1f9
+oid sha256:1612b25f4d5743f4c6d0124894422913b743bc181af10b80cf45c1cb3ba66e72
 size 692169624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e13b97502f0cac264c282569ba3fd29a774602fc7a6102e8ce5a5fcaa0fc94b
+oid sha256:431a3b504dc842e06d51268a4f4a1b89ebb79ee7b2f4373d5df408fb83abf530
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7734cb6e1786e57532cc69e3ce2c2aeac52a5aa1aa29a95d90dfddc0cb91ddb3
+oid sha256:fc1f0873e5f5f49bc708cd2c3f2a815109de453adb8ceb0b17b708db9c1600b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11049723756906077,
+  "epoch": 0.12154696132596685,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 6.677,
       "eval_steps_per_second": 0.837,
       "step": 90
+    },
+    {
+      "epoch": 0.1141804788213628,
+      "grad_norm": 2.291185140609741,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 2.1224,
+      "step": 93
+    },
+    {
+      "epoch": 0.11786372007366483,
+      "grad_norm": 2.3587148189544678,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 2.3583,
+      "step": 96
+    },
+    {
+      "epoch": 0.12154696132596685,
+      "grad_norm": 2.1020097732543945,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 2.1685,
+      "step": 99
+    },
+    {
+      "epoch": 0.12154696132596685,
+      "eval_loss": 0.574731171131134,
+      "eval_runtime": 205.3596,
+      "eval_samples_per_second": 6.681,
+      "eval_steps_per_second": 0.838,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5312705439072256e+17,
+  "total_flos": 2.784397598297948e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null