Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a01300fab4216026f7d5d3dd40ec53b4966c5ab173189b66736be6227127cff3
+oid sha256:8d3fb15f9888108da5871576ab1d5a08e4fa6fd90e815fe2e450e909d8b91c42
 size 16794864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5928de7938c3d390b8c1b5dd8a6b57495f9f8dc1c60159a440b5776a2602339d
+oid sha256:2cc04a52cdc19d6958743e47d313f08557e6b987515a676551acbfe972c4d579
 size 8671162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4789694b0dfbba236adc1e0423cccff54c291754e75185fa5ae6a3664fb3ce4a
+oid sha256:832ded70908c9963ab955f29ee60dc5db43fe03d8fd12b850a50e21c3b1d2b47
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024663251754885223,
+  "epoch": 0.003699487763232783,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 86.809,
       "eval_steps_per_second": 43.414,
       "step": 26
+    },
+    {
+      "epoch": 0.0028457598178713715,
+      "grad_norm": 1.8926585912704468,
+      "learning_rate": 5e-05,
+      "loss": 9.4168,
+      "step": 30
+    },
+    {
+      "epoch": 0.003699487763232783,
+      "eval_loss": 2.3647139072418213,
+      "eval_runtime": 51.0728,
+      "eval_samples_per_second": 86.915,
+      "eval_steps_per_second": 43.467,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1166710551871488.0,
+  "total_flos": 1733238271770624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null