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:e187291cbfc65f8599d8a66a0d4e6a06d63247eb3c3fcedb242e9c8b0e2a2acc
+oid sha256:98ea01ec53484c007a96238d8fabd6ba4cc40c22b0aea8f219691d4a7019f9aa
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c243d26ff2a4aebaadcf698641f11f3105fe29f16ed2ec1d5e9779a47f7803
+oid sha256:8f22a8c3f1540e44f74b760e5cb5f0d204f6d24c03e40330b99bf38987b3bdc8
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872b92a8e18143d05b82fd6171c4237313edde99402b17f14ebad5594b451656
+oid sha256:cfbf6b84eafc16b75329a008654c608bbbb4763f339107eca51386c43f126cb7
 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": 2.0,
+  "epoch": 2.2222222222222223,
   "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": 68.393,
       "eval_steps_per_second": 8.921,
       "step": 81
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.20115576684474945,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 2.0542,
+      "step": 84
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.1773402839899063,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 2.0123,
+      "step": 87
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.20624512434005737,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.9569,
+      "step": 90
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_loss": 1.8960562944412231,
+      "eval_runtime": 1.0098,
+      "eval_samples_per_second": 68.33,
+      "eval_steps_per_second": 8.913,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5144957858611200.0,
+  "total_flos": 5717061280727040.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null