Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abe0a462c1e0ca5a3b68930944cef3583c76709996ffad6724268682a769300
+oid sha256:96d74015691f4d81e671974fa14038368ae12b384c68e4ba4e51d03e24a5e52d
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2eee3d652a9893091cef4e326884c2885c2b9c9485c28aa000522b99e12b1c9
+oid sha256:1cf204f0186f0ab5641d62694c8e7e000410b3cc652da871914c0618d2d47d59
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5066b7dfe731942be4af3b1b28e679d0bf8d4a2fa0007add9f33d22921a55916
+oid sha256:ee04cda361f6941c5803fef5b388c8b8630c38a5748503a508eaf64a60fe897b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02691253426364316,
+  "epoch": 0.0299028158484924,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 22.908,
       "eval_steps_per_second": 2.865,
       "step": 81
+    },
+    {
+      "epoch": 0.02790929479192624,
+      "grad_norm": 4.23976993560791,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 5.7423,
+      "step": 84
+    },
+    {
+      "epoch": 0.02890605532020932,
+      "grad_norm": 5.665456295013428,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 4.8259,
+      "step": 87
+    },
+    {
+      "epoch": 0.0299028158484924,
+      "grad_norm": 7.587069988250732,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 6.1447,
+      "step": 90
+    },
+    {
+      "epoch": 0.0299028158484924,
+      "eval_loss": 1.5353803634643555,
+      "eval_runtime": 221.3193,
+      "eval_samples_per_second": 22.904,
+      "eval_steps_per_second": 2.865,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6704498844106752.0,
+  "total_flos": 7402252117475328.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null