Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0b715100e85e7098b0fad371e406ebea8996ae67a928c7125f709b2876053c
+oid sha256:a013899be0eb3a6d901b9fd448b1599c5e887d525014f6e71c255323d274cf63
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea8002c72d734607ded73cf96218ed10a0cc09b59d93aa1374d6421bc4d3310
+oid sha256:a03a3b0c64fc22d9775016c59439dd7e26bc1ddd34cff9a9d3622f8b5fda8560
 size 52046596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a885bd4ae9cee4432bbe3353be52f82c2245d374e8ac59d94d6d40a54be09132
+oid sha256:3c66fbaf22e8a612dc4bdf54801b189d03c19522b7b1dda120d304a377a24941
 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": 0.012926391382405745,
+  "epoch": 0.01436265709156194,
   "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": 23.096,
       "eval_steps_per_second": 2.889,
       "step": 81
+    },
+    {
+      "epoch": 0.013405146618791143,
+      "grad_norm": 0.4731264114379883,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 1.7055,
+      "step": 84
+    },
+    {
+      "epoch": 0.013883901855176541,
+      "grad_norm": 0.5054563879966736,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 1.5845,
+      "step": 87
+    },
+    {
+      "epoch": 0.01436265709156194,
+      "grad_norm": 0.46672162413597107,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.7207,
+      "step": 90
+    },
+    {
+      "epoch": 0.01436265709156194,
+      "eval_loss": 1.671474575996399,
+      "eval_runtime": 456.9871,
+      "eval_samples_per_second": 23.095,
+      "eval_steps_per_second": 2.888,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.465868733513728e+16,
+  "total_flos": 6.075016755019776e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null