Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1539e3eb3ed1329d59c6782d056d9df93b95532964975b20e2e8f1e112faded0
+oid sha256:c08076ca3c7735b300728b9e7fa0aae79cf9e342bb6439df5d97f61404f6efdb
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d503f3c692b86a326ba43245fc8e4dc4230f03e4aaf401ccac3064bcdf0f758
+oid sha256:2a3567d45eb91c163c751004dfdf68d0b2ea641201553e1454fc29f1b50e6bf3
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18dc613ec9bceaa03cc7b4c996c5c216d4df491a4b13fb66bb46e47fc9c02b42
+oid sha256:0e24d535c5c1523f0486038b5930228f33566ca520ba04d10e88741a42965211
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012774247117810493,
+  "epoch": 0.0025548494235620987,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 11.3893,
       "step": 9
+    },
+    {
+      "epoch": 0.0015329096541372594,
+      "grad_norm": 11.2367525100708,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.6279,
+      "step": 12
+    },
+    {
+      "epoch": 0.0019161370676715741,
+      "grad_norm": 9.639863014221191,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 4.6616,
+      "step": 15
+    },
+    {
+      "epoch": 0.002043879538849679,
+      "eval_loss": 1.1346616744995117,
+      "eval_runtime": 184.0071,
+      "eval_samples_per_second": 17.918,
+      "eval_steps_per_second": 8.962,
+      "step": 16
+    },
+    {
+      "epoch": 0.002299364481205889,
+      "grad_norm": 7.165860176086426,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.3663,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3267291009515520.0,
+  "total_flos": 6534582019031040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null