Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032dc9502f0af93637b7dcd0e3aef6784dae39be689063bebd00738f2d79fda7
+oid sha256:bf23732f9100d4f09b14457a378ffaf9eb46622a61a793a3def1c2de066f9ff3
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a2a2501057c9ab89126e15940746962aae966f96a8603b469f28815d4e1a69
+oid sha256:b0fc9279b4e4e172febc4dd5abba6e8f50a661b98eb1f8facbe539888e556d3e
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eece1d4d0b0c5cf475a608f4a69f986bfcf2b490c032d12bd994063c25d49dd4
+oid sha256:02da343f4d43f14fc335c9aac35ac23ef49eb91de2dac0dbf64531bc8b798b04
 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": 0.00011368157790030126,
+  "epoch": 0.0001705223668504519,
   "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": 28.967,
       "eval_steps_per_second": 14.484,
       "step": 6
+    },
+    {
+      "epoch": 0.00013262850755035147,
+      "grad_norm": 0.33067765831947327,
+      "learning_rate": 0.00014,
+      "loss": 0.0919,
+      "step": 7
+    },
+    {
+      "epoch": 0.00015157543720040168,
+      "grad_norm": 0.26524150371551514,
+      "learning_rate": 0.00016,
+      "loss": 0.0832,
+      "step": 8
+    },
+    {
+      "epoch": 0.0001705223668504519,
+      "grad_norm": 0.21210353076457977,
+      "learning_rate": 0.00018,
+      "loss": 0.0591,
+      "step": 9
+    },
+    {
+      "epoch": 0.0001705223668504519,
+      "eval_loss": 0.05260061100125313,
+      "eval_runtime": 766.1969,
+      "eval_samples_per_second": 29.004,
+      "eval_steps_per_second": 14.503,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 525102197243904.0,
+  "total_flos": 775150862598144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null