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:df25dec836a9b22bb60582bfb8404ac200e4d22e84c22debbde7dbbac1a4005f
+oid sha256:8b7404f3d4ce61490ad1b894c1ab76ae93fb71f7ff45d1d00dfef6b706fd0b2b
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a018b2b0e5a1243542fe7a15744fd45c809ebe83e12ece52b2d1cc605b69aec
+oid sha256:d064e8f44ef8536e3526dc7dd58266d7f0988e265cc192645df13f786ff07e80
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d86d7748603e74c3bf815f9d30ac21739445a06b76d12dd5a238ef2ce4cee42
+oid sha256:1e6fa4c3006488197a10f4953ae691c0aa1c0892276bf84037a2a2d7ac9636df
 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": 0.046620046620046623,
+  "epoch": 0.09324009324009325,
   "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": 0.8539,
       "step": 9
+    },
+    {
+      "epoch": 0.055944055944055944,
+      "grad_norm": 0.37416017055511475,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.7767,
+      "step": 12
+    },
+    {
+      "epoch": 0.06993006993006994,
+      "grad_norm": 0.3611030876636505,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.7492,
+      "step": 15
+    },
+    {
+      "epoch": 0.07459207459207459,
+      "eval_loss": 0.7391844391822815,
+      "eval_runtime": 24.8047,
+      "eval_samples_per_second": 3.669,
+      "eval_steps_per_second": 1.854,
+      "step": 16
+    },
+    {
+      "epoch": 0.08391608391608392,
+      "grad_norm": 0.42007654905319214,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6869,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3430655559991296.0,
+  "total_flos": 6697946569506816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null