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:cc4f9d54efd50090545c5127f9601a623dd700d8f45d9aca3f2281be4ee022bb
+oid sha256:f07dece5cb593f7a4bde202867ba6f00417be8f3d6848abf6e17478a5bc142cc
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7174dd1561fbb06a5c7c5e66100ec35167108c49824a29d6e9f41076c4d2170e
+oid sha256:7d8aae07029699d419290367b7ff26890b46e62d5ca2f4511cad4e54cb573caa
 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": 0.0016909744240118367,
+  "epoch": 0.0033819488480236735,
   "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": 6.1368,
       "step": 9
+    },
+    {
+      "epoch": 0.002029169308814204,
+      "grad_norm": 7.634250164031982,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.3308,
+      "step": 12
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "grad_norm": 3.4595627784729004,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.1192,
+      "step": 15
+    },
+    {
+      "epoch": 0.002705559078418939,
+      "eval_loss": 1.3730992078781128,
+      "eval_runtime": 171.2537,
+      "eval_samples_per_second": 14.54,
+      "eval_steps_per_second": 7.27,
+      "step": 16
+    },
+    {
+      "epoch": 0.0030437539632213063,
+      "grad_norm": 2.6122586727142334,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.4754,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3267323221770240.0,
+  "total_flos": 6534646443540480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null