Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:608b8fe86cb000ba10f130ce26f5820df8db4a51bfaff2ec70695f4cc94eda33
+oid sha256:15f68a02d7c84ce57e607aa8da51a84c9a017fd335da2ea608038023646346b0
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aefaca43bf6dd7b35edc6c5cda6d10db8530d161511bde7609320c4ce8a5c737
+oid sha256:915b171270da7d787d7eecebf6d9b2d0195106a2c9361cf693bf0a4358206682
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c0fc870a765abf0182c20ebdcf8d42dc726d33859cc657f77c100ae15a6c9f
+oid sha256:a11a1375777d57e625fdc32e2f9f547ac59706c1926af9227df8f015961b0a4b
 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": 0.022482825619318577,
+  "epoch": 0.024980917354798418,
   "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": 9.192,
       "eval_steps_per_second": 1.15,
       "step": 81
+    },
+    {
+      "epoch": 0.023315522864478522,
+      "grad_norm": 0.1734035611152649,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.35,
+      "step": 84
+    },
+    {
+      "epoch": 0.02414822010963847,
+      "grad_norm": 0.17395810782909393,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.3584,
+      "step": 87
+    },
+    {
+      "epoch": 0.024980917354798418,
+      "grad_norm": 0.16377660632133484,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.3624,
+      "step": 90
+    },
+    {
+      "epoch": 0.024980917354798418,
+      "eval_loss": 0.3525063097476959,
+      "eval_runtime": 660.2929,
+      "eval_samples_per_second": 9.19,
+      "eval_steps_per_second": 1.149,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7580823137170227e+17,
+  "total_flos": 1.9712891151817114e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null