Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32077b77ab6db668b003e88c024f388c8574400e96885848294143a92306947c
+oid sha256:0c2e967d68e96ccd61ee79881399c519ad4d18c6043e6ad8c12b0ea3b410d6ff
 size 792912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25b49e0734e96b8322d1d68ca6c321a218c79b13a7e21654e9c37e3953b0c7b
+oid sha256:10d462a6f24355a0abf88ff34c15521ba7ab72ac35ec3ce9941294abde06d2fb
 size 1613434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ab434eb413c22dfe68751d23f523b350e713befd5789cab3e4721ae4a95e77
+oid sha256:70d45509bd7bfc32e4469507a5c7cf52b55100292f3cdbadf46a01923d9eca71
 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": 0.018700327255726974,
+  "epoch": 0.03740065451145395,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 168.497,
       "eval_steps_per_second": 84.249,
       "step": 10
+    },
+    {
+      "epoch": 0.02244039270687237,
+      "grad_norm": 7629.75390625,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 38.3511,
+      "step": 12
+    },
+    {
+      "epoch": 0.028050490883590462,
+      "grad_norm": 6675.2470703125,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 37.0423,
+      "step": 15
+    },
+    {
+      "epoch": 0.028050490883590462,
+      "eval_loss": 9.183147430419922,
+      "eval_runtime": 1.3759,
+      "eval_samples_per_second": 164.259,
+      "eval_steps_per_second": 82.129,
+      "step": 15
+    },
+    {
+      "epoch": 0.033660589060308554,
+      "grad_norm": 12042.025390625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 35.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.03740065451145395,
+      "eval_loss": 8.979737281799316,
+      "eval_runtime": 1.3233,
+      "eval_samples_per_second": 170.783,
+      "eval_steps_per_second": 85.391,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3846344540160.0,
+  "total_flos": 7692689080320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null