Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20121e8d86ef8e179d0bdc240b15df0ee8a16d7ca825aefc76189f06c0bed381
+oid sha256:6a63559a9984b3f341547f700adaa222b3a0230be32493e56bcf895d12c64c95
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47b30d14b732bfff11160747037b744d13c1aabd16b7e6a66ae747a21551fc70
+oid sha256:ab0601ff334e953e996fc924db32b04d351949fa66dda10fde3419c92a92cd69
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a9051632611b5858fe918c6c5dc146c471b18a259103a59cbc10474ccaeb85
+oid sha256:b37eb23c7db03165d9b298533a106ef93fbe349e32cf744565e4d6da5d2b28dc
 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": 0.0002243577758665819,
+  "epoch": 0.0003365366637998729,
   "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": 75.078,
       "eval_steps_per_second": 37.543,
       "step": 6
+    },
+    {
+      "epoch": 0.0002617507385110122,
+      "grad_norm": 0.5297170877456665,
+      "learning_rate": 0.00014,
+      "loss": 2.4877,
+      "step": 7
+    },
+    {
+      "epoch": 0.00029914370115544255,
+      "grad_norm": 0.7077357769012451,
+      "learning_rate": 0.00016,
+      "loss": 3.1547,
+      "step": 8
+    },
+    {
+      "epoch": 0.0003365366637998729,
+      "grad_norm": 0.5892812013626099,
+      "learning_rate": 0.00018,
+      "loss": 2.7252,
+      "step": 9
+    },
+    {
+      "epoch": 0.0003365366637998729,
+      "eval_loss": 0.6855435967445374,
+      "eval_runtime": 125.6436,
+      "eval_samples_per_second": 89.627,
+      "eval_steps_per_second": 44.817,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 14855901806592.0,
+  "total_flos": 21222716866560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null