Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26b5850dcf99ccb8959af553df53318b2a2379217be244ee293922fdbd590b0e
+oid sha256:ed182cfba10f32a256dba2e57c3237f99a84a43c747f40a7d3df958cf2c61f15
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d14b88b7c77d7b52697388e5b83aa2ccb67966d5a6df392a5979b4d6917150b2
+oid sha256:62fb5046a37f60de37bda587fa373e149dd913bc4528bb6950497b63a91e85f5
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:742d1e1e05e0b88af24bf73a3fabe335fdf1dacfbc69aeeff2cf369abc02b929
+oid sha256:40fe2cb579250223e5605209364eda9a1e54f87ddb866ab9aac82baf67f204b3
 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": 0.004081632653061225,
+  "epoch": 0.00816326530612245,
   "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": 4.5746,
       "step": 9
+    },
+    {
+      "epoch": 0.004897959183673469,
+      "grad_norm": 2.312330961227417,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 4.6686,
+      "step": 12
+    },
+    {
+      "epoch": 0.006122448979591836,
+      "grad_norm": 2.092863082885742,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 4.0921,
+      "step": 15
+    },
+    {
+      "epoch": 0.006530612244897959,
+      "eval_loss": 1.0457439422607422,
+      "eval_runtime": 71.3543,
+      "eval_samples_per_second": 14.463,
+      "eval_steps_per_second": 7.232,
+      "step": 16
+    },
+    {
+      "epoch": 0.007346938775510204,
+      "grad_norm": 1.790899395942688,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.1099,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5860137306685440.0,
+  "total_flos": 1.200613496979456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null