Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:837a85d5155abaa070d1f704b25d700527a6c09b2355549329fb0c062bdf10dc
+oid sha256:512f494c5aadb7f06522ea5ccf364c27b1034a318d7f8151d450f5c7bfaa34d2
 size 19593064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd229bc20208a28c33c6bd506f7b5644973d94f6cf44e49f48869efe5cd24f5
+oid sha256:146fa6143c10c0e9bb32b923385e55ff05907aa1c5d062e8d1bc5a9e1885d024
 size 11469420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3147677b0637f897702460796a64d7858fc8d3e870ca7bae093f7fd74c7da7c
+oid sha256:4eb2a57ee880a7e5e6816a3da3a29ffebab989146dd73c02addd843781aa88c3
 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": 0.052820345614607106,
+  "epoch": 0.05868927290511901,
   "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": 72.938,
       "eval_steps_per_second": 9.121,
       "step": 81
+    },
+    {
+      "epoch": 0.05477665471144441,
+      "grad_norm": 0.1431252807378769,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 1.3153,
+      "step": 84
+    },
+    {
+      "epoch": 0.05673296380828171,
+      "grad_norm": 0.1532163769006729,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 1.3877,
+      "step": 87
+    },
+    {
+      "epoch": 0.05868927290511901,
+      "grad_norm": 0.15569448471069336,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.4249,
+      "step": 90
+    },
+    {
+      "epoch": 0.05868927290511901,
+      "eval_loss": 1.3660001754760742,
+      "eval_runtime": 35.493,
+      "eval_samples_per_second": 72.775,
+      "eval_steps_per_second": 9.1,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2751937892057088.0,
+  "total_flos": 3024947603570688.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null