Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e230c59a375c4130010d41a749b0998e466183976cd3e2a0739c080e1bf7b23
+oid sha256:eb5efe4924dd307dad02f6cc3c40e3214bbc5618a28a4cedcbf7d13f74573f07
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe5e02cff8800d240779451587b3823568c07bfb411ef754d5e2c490a5f5f747
+oid sha256:12ea4e1031dc7862d1518646e355d58ce6af24acc0642ae29c6334f2dfddc660
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
+oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
 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": 0.00045127202301487317,
+  "epoch": 0.0006769080345223098,
   "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": 435.212,
       "eval_steps_per_second": 217.645,
       "step": 6
+    },
+    {
+      "epoch": 0.0005264840268506853,
+      "grad_norm": 0.4780758321285248,
+      "learning_rate": 0.00014,
+      "loss": 44.3746,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006016960306864976,
+      "grad_norm": 0.4785214364528656,
+      "learning_rate": 0.00016,
+      "loss": 44.3519,
+      "step": 8
+    },
+    {
+      "epoch": 0.0006769080345223098,
+      "grad_norm": 0.5370668768882751,
+      "learning_rate": 0.00018,
+      "loss": 44.3743,
+      "step": 9
+    },
+    {
+      "epoch": 0.0006769080345223098,
+      "eval_loss": 11.090177536010742,
+      "eval_runtime": 12.8547,
+      "eval_samples_per_second": 435.559,
+      "eval_steps_per_second": 217.818,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4482662400.0,
+  "total_flos": 6723993600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null