Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26db044503d9151cd5ffa51d67032d9144bf3e183302d8c134a5d289a4222f0f
+oid sha256:f156d5c5baa4fe8836f7eda151fb54f235c5eca407104ea014dbc29703680aab
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cada26df368a767af915c8578c2cddaf1770a23ea5c21c47cb3a341972ad334a
+oid sha256:d5e3dd9ae0c1865720a600b07ede1b6fc9f1a0f5b097988d5092d49a18d90763
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ec77bc659907e72bdaf1050c60ba5db8496e40f4dea86ee044c8a986e366c01
+oid sha256:55b39a78fe0128946befa9d21f7a47d47ba7d7ec46bc5537f8d642074db4b862
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0addd62454d87d49bfedc26e0b85659f0aaed290a84e144284ca9b72f10d6fc8
+oid sha256:27ca192899ed606f0971eef111fc1026e18024acb472ba59e8b2804c88f803cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.532347504621072,
+  "epoch": 0.7985212569316081,
   "eval_steps": 7,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,6 +38,21 @@
       "eval_samples_per_second": 17.249,
       "eval_steps_per_second": 2.194,
       "step": 14
+    },
+    {
+      "epoch": 0.5914972273567468,
+      "grad_norm": 0.8601843118667603,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6732,
+      "step": 20
+    },
+    {
+      "epoch": 0.6210720887245841,
+      "eval_loss": 1.449949026107788,
+      "eval_runtime": 13.2718,
+      "eval_samples_per_second": 17.179,
+      "eval_steps_per_second": 2.185,
+      "step": 21
     }
   ],
   "logging_steps": 10,
@@ -57,7 +72,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.723480310317056e+16,
+  "total_flos": 7.085220465475584e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null