Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c4cae5e8c4d0aade31a3209b446d6b00cde97f514b766222d9bc98569476d5
+oid sha256:31039ae079f09a1b104f48cbb66f2666b9c1a1fb741081774af357a45d793dbc
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:036ded04c2ed1bcb697415aa291bcf9709958c3303a435ace996b271982020a7
+oid sha256:bd24ff47432c8a9e0927320aadeea3545af04dc2ef4ea80d33d0a3f0d34249e1
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:710622f4a334eb6afc7152f2c8c2bcaebfe678e2f64b03828bf0cc306501b51f
+oid sha256:f7bad38b6510dcfd435e5e047c00ab3bb954cd2dc192cb4716bc78ccd281cb39
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00049063701038515,
+  "epoch": 0.0009812740207703,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 46.831,
       "eval_steps_per_second": 23.425,
       "step": 3
+    },
+    {
+      "epoch": 0.0006541826805135334,
+      "grad_norm": 13.49551010131836,
+      "learning_rate": 8e-05,
+      "loss": 24.767,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008177283506419167,
+      "grad_norm": 12.945690155029297,
+      "learning_rate": 0.0001,
+      "loss": 23.433,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009812740207703,
+      "grad_norm": 15.52833366394043,
+      "learning_rate": 0.00012,
+      "loss": 23.7126,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009812740207703,
+      "eval_loss": 5.364927768707275,
+      "eval_runtime": 55.3052,
+      "eval_samples_per_second": 46.56,
+      "eval_steps_per_second": 23.289,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 195884797132800.0,
+  "total_flos": 391769594265600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null