Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:909de9056bede5798a4cea29c59bd0907334a70e47200c63aa061d2389597b6e
+oid sha256:6b9abbf2a9c02f94567263a85d024fd94528da6a7452c66190ca4095c1530b19
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63483957100095475b9cdeaa3eef9a0018b51ee23a9d05301eb3ab459414eae
+oid sha256:11b6c921dd15f1bab55ff0036295ef7dc583f1c8b157a3f42ede41c638481ddb
 size 1656058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e352f6dd3a590160062107c4c3db81ef9817dfec32c6c321e67d8ba9c2e8c56
+oid sha256:47a18c923adfc0a2704165e97788fe64268dfb64c404e76c05e50b2a47e3e5da
 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": 0.001834581868215869,
+  "epoch": 0.003669163736431738,
   "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": 33.432,
       "eval_steps_per_second": 16.74,
       "step": 3
+    },
+    {
+      "epoch": 0.002446109157621159,
+      "grad_norm": 717.8159790039062,
+      "learning_rate": 8e-05,
+      "loss": 27.3533,
+      "step": 4
+    },
+    {
+      "epoch": 0.0030576364470264487,
+      "grad_norm": 803.9835815429688,
+      "learning_rate": 0.0001,
+      "loss": 25.9769,
+      "step": 5
+    },
+    {
+      "epoch": 0.003669163736431738,
+      "grad_norm": 792.4016723632812,
+      "learning_rate": 0.00012,
+      "loss": 27.458,
+      "step": 6
+    },
+    {
+      "epoch": 0.003669163736431738,
+      "eval_loss": 6.677663326263428,
+      "eval_runtime": 20.6808,
+      "eval_samples_per_second": 33.316,
+      "eval_steps_per_second": 16.682,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26811870216192.0,
+  "total_flos": 53623740432384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null