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:f000a3494e4f5b30528dcfb7d8ab92d5466df38a8a8af7d9c5db98e5bb125f3e
+oid sha256:e1e4de72ee40562136cd4623647eda4b3e2d8100931a564d40222bfa708c37ab
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbfa4e1addc5883c6f22b2fb0b481fc44ab8d79921906e240033510de50104e4
+oid sha256:caef1a8d2bc9533eea80c1156e3f3b7771926c0501e169ab561d155fa6e325ae
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54966f2465e62f3f23221c1b18d8d6c1829302b329b674439c498e34e1b28ba
+oid sha256:c8f9bfbb25b5742af971410f7969204872224492d0748212c97b7e3aec33a144
 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": 0.008344923504867872,
+  "epoch": 0.016689847009735744,
   "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": 185.09,
       "eval_steps_per_second": 92.545,
       "step": 3
+    },
+    {
+      "epoch": 0.011126564673157162,
+      "grad_norm": 0.006569739896804094,
+      "learning_rate": 8e-05,
+      "loss": 11.9374,
+      "step": 4
+    },
+    {
+      "epoch": 0.013908205841446454,
+      "grad_norm": 0.005256724078208208,
+      "learning_rate": 0.0001,
+      "loss": 11.9328,
+      "step": 5
+    },
+    {
+      "epoch": 0.016689847009735744,
+      "grad_norm": 0.009198017418384552,
+      "learning_rate": 0.00012,
+      "loss": 11.9323,
+      "step": 6
+    },
+    {
+      "epoch": 0.016689847009735744,
+      "eval_loss": 11.932042121887207,
+      "eval_runtime": 0.8366,
+      "eval_samples_per_second": 181.685,
+      "eval_steps_per_second": 90.843,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 679428096.0,
+  "total_flos": 1388396544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null