Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b63ee0b92821990ac7bc4286d276b1ff7b65a38a7fc161a1313084a35b839b
+oid sha256:6454113023046638b3e2ebd0108d6cd1f0692dd0812f7d779a642df85bdd353a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541fcc6674eae5b36bcbe4656d442746c77ce5b9990472486535fcb6757b7ddf
+oid sha256:0223eb0199d8482f23fec34621ab38a98663bf22ab0dcce3aaed6d32bec35ac0
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc95f8ef66804917a60b19acbb3aaab5647926085d4ddb008103acb36348fb2
+oid sha256:0b65f1a0fab783030b9678af169570889794fb3146a39ba3945282029a965db4
 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": 0.0006774608766343743,
+  "epoch": 0.0013549217532687486,
   "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": 2.2757,
       "step": 9
+    },
+    {
+      "epoch": 0.0008129530519612493,
+      "grad_norm": 1.8487952947616577,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.2765,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010161913149515616,
+      "grad_norm": 0.7342104911804199,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.0505,
+      "step": 15
+    },
+    {
+      "epoch": 0.001083937402614999,
+      "eval_loss": 2.0274226665496826,
+      "eval_runtime": 534.2361,
+      "eval_samples_per_second": 11.635,
+      "eval_steps_per_second": 5.818,
+      "step": 16
+    },
+    {
+      "epoch": 0.0012194295779418738,
+      "grad_norm": 0.7179998755455017,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.099,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7604344656494592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null