Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95766318f847a674dec9a58caba562585ad85e3252faf2e30fcffced2cca6515
+oid sha256:d35ceb797726a35810cec4cc2696a3c5eaf20cb31033e88bbb1d362302e7e21e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87cf68cd73cc09d84eddf6b24047ae93ec7ea3179286a9d0dd608a941983944
+oid sha256:db7d7d25e590a8540351cd01d163ba0103a6a787bc68dba278337f4483f03a92
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d77b60a4a6ac9b1290011cfbb000725f2f3c555f2baada62884afb493a185f
+oid sha256:76d05d926a13e2b0db86e596e2ee777dcc8276585d379e27b6ca55897b2ce7fe
 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": 0.0008818666176740768,
+  "epoch": 0.0013227999265111152,
   "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": 11.585,
       "eval_steps_per_second": 5.795,
       "step": 6
+    },
+    {
+      "epoch": 0.0010288443872864229,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 1.2798,
+      "step": 7
+    },
+    {
+      "epoch": 0.0011758221568987691,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.5146,
+      "step": 8
+    },
+    {
+      "epoch": 0.0013227999265111152,
+      "grad_norm": 0.1688116192817688,
+      "learning_rate": 0.00018,
+      "loss": 0.8901,
+      "step": 9
+    },
+    {
+      "epoch": 0.0013227999265111152,
+      "eval_loss": NaN,
+      "eval_runtime": 247.1101,
+      "eval_samples_per_second": 11.594,
+      "eval_steps_per_second": 5.799,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3807949042483200.0,
+  "total_flos": 5711923563724800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null