Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cce4be63c5f752cf95287bea1fdfc019c45f0420febeb230d01a477a83b7ddf
+oid sha256:6da35f8c87a665ea54754ba77ecb9b228a953fcacb6aeeb78f971da9d16f4019
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb41e1c442c213f7a0366cc3425a6f49341f918624fe7d8be95b26fca5017d5
+oid sha256:59c14a13fadd611ed4d677e5bfcafeceaddc0acc3933a18f81916d5c2929f47c
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c374c6562ebbd81ad3d8b3da8ef3358a94d20512db0e27ba8a9f959fd69d8cd7
+oid sha256:200e6fcd481c16b4f3d1cbb24a0867b14067141b424637d8e0b176938ed6cbb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008626887131560028,
+  "epoch": 0.012940330697340043,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 3.93,
       "eval_steps_per_second": 1.972,
       "step": 6
+    },
+    {
+      "epoch": 0.010064701653486701,
+      "grad_norm": 21.585725784301758,
+      "learning_rate": 0.00014,
+      "loss": 13.1111,
+      "step": 7
+    },
+    {
+      "epoch": 0.011502516175413372,
+      "grad_norm": 23.57619285583496,
+      "learning_rate": 0.00016,
+      "loss": 11.0064,
+      "step": 8
+    },
+    {
+      "epoch": 0.012940330697340043,
+      "grad_norm": 30.479141235351562,
+      "learning_rate": 0.00018,
+      "loss": 10.0326,
+      "step": 9
+    },
+    {
+      "epoch": 0.012940330697340043,
+      "eval_loss": 8.028653144836426,
+      "eval_runtime": 74.255,
+      "eval_samples_per_second": 3.946,
+      "eval_steps_per_second": 1.98,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1567522604187648.0,
+  "total_flos": 2351283906281472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null