Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b714f3bb76255b258671ec0a8c390e57121f1dd91c57e6f6474ea463ab88f9
+oid sha256:916e533f7ff18bed52c57bae4984dfb01d821e2739218550e9c6eefc420c886b
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d7b2c1abbe39def64ee2eaba736ab140106afc0a7626ef63b679d8d4f98e39
+oid sha256:029aeb43f5f7c57bbc82d3853b7a73df252cc72767723aadf863b09823a40546
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54229bca258cfdad1e1660f8d54129189d2b0f72b0bf930abddaec4a6f237e6b
+oid sha256:ae27f7b41ce550bc2f2daf16c7d3f7ba4ba093c2050f241d7f74c271f07b0995
 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": 0.00020155702804162154,
+  "epoch": 0.0004031140560832431,
   "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": 10.2177,
       "step": 9
+    },
+    {
+      "epoch": 0.00024186843364994582,
+      "grad_norm": 305.9400634765625,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 8.9782,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003023355420624323,
+      "grad_norm": 197.7496795654297,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 8.913,
+      "step": 15
+    },
+    {
+      "epoch": 0.00032249124486659445,
+      "eval_loss": 1.9983162879943848,
+      "eval_runtime": 710.6411,
+      "eval_samples_per_second": 29.396,
+      "eval_steps_per_second": 14.698,
+      "step": 16
+    },
+    {
+      "epoch": 0.00036280265047491873,
+      "grad_norm": 5.757598400115967,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 9.1496,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 174438318342144.0,
+  "total_flos": 364045186105344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null