Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f3a7e6520d835426b83b923e2f1beb394a1836ae72b8491de7af459d62dbe04
+oid sha256:9e4a93850d61089111c25efe57e9baed7f7fd950ebe0324df0e8ca12c4c132e0
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a367fdee7b2a3962dae95e650ae8595cf3861d96a998c0e552c4221c6edecef
+oid sha256:b962faad8dba665a7745fb2ece137ce9624df9165c3338ec399b6ffc91c65cc8
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ac10dc48fdbd2df4773c8af7fc51afd6b5e578954636a687936ba809b9b611
+oid sha256:3fc14fefff006fb0dd1a8741d732ba7c5cb784dc3d38739d8e0258cc367de460
 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": 0.007326007326007326,
+  "epoch": 0.014652014652014652,
   "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": 51.661,
       "eval_steps_per_second": 25.98,
       "step": 3
+    },
+    {
+      "epoch": 0.009768009768009768,
+      "grad_norm": 9.052845001220703,
+      "learning_rate": 8e-05,
+      "loss": 1.492,
+      "step": 4
+    },
+    {
+      "epoch": 0.01221001221001221,
+      "grad_norm": 3.5522308349609375,
+      "learning_rate": 0.0001,
+      "loss": 0.8853,
+      "step": 5
+    },
+    {
+      "epoch": 0.014652014652014652,
+      "grad_norm": 10.843049049377441,
+      "learning_rate": 0.00012,
+      "loss": 1.8168,
+      "step": 6
+    },
+    {
+      "epoch": 0.014652014652014652,
+      "eval_loss": 0.8879690766334534,
+      "eval_runtime": 3.4123,
+      "eval_samples_per_second": 50.699,
+      "eval_steps_per_second": 25.496,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 153475186950144.0,
+  "total_flos": 306950373900288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null