Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a1fe853c7e6b7aeed25f80e1dd314f504aa0ab314029aaa9422722a3f84bc79
+oid sha256:e1cbf55743cc3b9d6b99c82ed22447ad8ea2dd0d86404b6ab4ac0380900d9f1e
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f77c2ca05d9a6996cb4da0d47319125887d41c9c8f558f495675d73b4dd63e
+oid sha256:564ed2993d6c139f41b5dfe894237e10f34698d42dde5baba6d4b618b27cd8b5
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129f401558a2ef42690e8a8f042033c43e9f56c214cd3d972a79fbc143acc338
+oid sha256:b3ce5ef9acff86ae6374f269f37432b1bde430e53865dd5ffb83ec737a6238e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002911914583838874,
+  "epoch": 0.005823829167677748,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 97.779,
       "eval_steps_per_second": 48.889,
       "step": 3
+    },
+    {
+      "epoch": 0.003882552778451832,
+      "grad_norm": 3.3053483963012695,
+      "learning_rate": 8e-05,
+      "loss": 4.7285,
+      "step": 4
+    },
+    {
+      "epoch": 0.0048531909730647905,
+      "grad_norm": 3.4134633541107178,
+      "learning_rate": 0.0001,
+      "loss": 4.7789,
+      "step": 5
+    },
+    {
+      "epoch": 0.005823829167677748,
+      "grad_norm": 3.0485000610351562,
+      "learning_rate": 0.00012,
+      "loss": 4.5668,
+      "step": 6
+    },
+    {
+      "epoch": 0.005823829167677748,
+      "eval_loss": 4.634877681732178,
+      "eval_runtime": 4.613,
+      "eval_samples_per_second": 94.083,
+      "eval_steps_per_second": 47.041,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 14574376452096.0,
+  "total_flos": 30006069166080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null