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:dc62cce01975e06517c957c22832de4239f4136b3bdd5cb008a20d9a43b96235
+oid sha256:7a40776117220a2cadb3c2cb60ef81484fc45954a4421caac88d864efa2ba395
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f277af9ea4f8a91172e47ba164a243041b05fd204206948e1ea1f40721fc82be
+oid sha256:8268e016fd5929f7b4083c8bde48a6bdfb1ab7ee70f9d4707c1eef9e3ef50ecf
 size 6332154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0190c48acbac7fba03c62e2a2a9df68f5df9c200ead69af6631aa7c118ff881b
+oid sha256:b2ac488ce1f441ca1ae6806867cc0d824ea5a04d174d746efdffa5a728cba642
 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": 0.0017394329448599756,
+  "epoch": 0.003478865889719951,
   "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": 125.2086,
       "step": 9
+    },
+    {
+      "epoch": 0.0020873195338319706,
+      "grad_norm": 1662.098388671875,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 115.1138,
+      "step": 12
+    },
+    {
+      "epoch": 0.0026091494172899633,
+      "grad_norm": 1860.805419921875,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 104.8186,
+      "step": 15
+    },
+    {
+      "epoch": 0.002783092711775961,
+      "eval_loss": 31.02450180053711,
+      "eval_runtime": 15.2933,
+      "eval_samples_per_second": 158.305,
+      "eval_steps_per_second": 79.185,
+      "step": 16
+    },
+    {
+      "epoch": 0.0031309793007479564,
+      "grad_norm": 1440.878662109375,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 104.8424,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22343225180160.0,
+  "total_flos": 44686450360320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null