Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683bb5ae16318f1a495e1e6a9b8b4ab722ec99580d6c45eeee86a8b8386bb67a
+oid sha256:c8c2980fd6d884f7afbd59f6effb19057fc639cd36c8e55015916050e4022d9f
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2f8b98fb9a64e3a394ba8386fef70db3f8b4c3fc072eb94e0feeefbcf482dd
+oid sha256:8555fdfdb39b65685942f1681339907e64b5dc5f77e34b694d216001a5e1e272
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005493562231759657,
+  "epoch": 0.010987124463519314,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 97.596,
       "eval_steps_per_second": 48.798,
       "step": 2
+    },
+    {
+      "epoch": 0.008240343347639486,
+      "grad_norm": 2.901226282119751,
+      "learning_rate": 3e-05,
+      "loss": 3.7123,
+      "step": 3
+    },
+    {
+      "epoch": 0.010987124463519314,
+      "grad_norm": 2.9844248294830322,
+      "learning_rate": 4e-05,
+      "loss": 3.7242,
+      "step": 4
+    },
+    {
+      "epoch": 0.010987124463519314,
+      "eval_loss": 3.700958728790283,
+      "eval_runtime": 6.4961,
+      "eval_samples_per_second": 94.518,
+      "eval_steps_per_second": 47.259,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 259438606811136.0,
+  "total_flos": 518877213622272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null