Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89094a0860c201bfa7b510e2952b4209c91c85be98ace53acb59731d712c5c5a
+oid sha256:7403b64e964b8d7e97e919d53021a6f80301f7f189253c93544cff0479b1979b
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f68fcb63914119b6518be9306360134d6406f2834dd8275b0d0d307839c102
+oid sha256:fd2e6e9c04c35b21c61b26885f2bfd7fb48e6b3dec78e690604470f2bef26c11
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a07c66a8bbda035c71637231362589b93f6d10c6d5ad4f8f3c1facfda53ac13
+oid sha256:653a7d79cc851bf5423ac30748a3285a94a397664d2f1baf19c62f5e6cbf4c2d
 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": 0.0010283657554203446,
+  "epoch": 0.0015425486331305167,
   "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": 15.319,
       "eval_steps_per_second": 7.663,
       "step": 6
+    },
+    {
+      "epoch": 0.0011997600479904018,
+      "grad_norm": 0.6245144009590149,
+      "learning_rate": 0.00014,
+      "loss": 4.9164,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013711543405604593,
+      "grad_norm": 0.6565183997154236,
+      "learning_rate": 0.00016,
+      "loss": 4.8597,
+      "step": 8
+    },
+    {
+      "epoch": 0.0015425486331305167,
+      "grad_norm": 0.7676700353622437,
+      "learning_rate": 0.00018,
+      "loss": 4.2699,
+      "step": 9
+    },
+    {
+      "epoch": 0.0015425486331305167,
+      "eval_loss": 1.2163201570510864,
+      "eval_runtime": 160.2337,
+      "eval_samples_per_second": 15.334,
+      "eval_steps_per_second": 7.67,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2632959708364800.0,
+  "total_flos": 3906972470476800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null