Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d5b7f97cf00e1585267ce7f91f2ddf74da03538fe19cb79201c42cb6435d14e
+oid sha256:b13612ad1011be4a7550516f4258284cdf56f55d549c85c3979825cf045b231c
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40862ced1da18c4fbea67ed6e36bca0aa2ccce45c097d0c289b2e5ba303b65e
+oid sha256:823e9c2821924ea205aaf208968717116f166bca10b09a9cf998c7b9e8f44d1c
 size 52046596

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f208a1b133e23db562910dd8d62af91a871a98625f1d43795785b962555b165
+oid sha256:a89df1f1058e66adfc9e9c81cb78b9184ce6a34c4d5b3dd6ec6856ec870130ba
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:998470fa5c8115b8d249e96e18986f84612a0e6cf47a8a9cd2a28321abea763f
+oid sha256:c72842717b2036b82a63b7b12be12f81cb3652b8a69815f17f509d3428f86bdb
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004406095098219203,
+  "epoch": 0.006609142647328804,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 6.692,
       "eval_steps_per_second": 1.674,
       "step": 6
+    },
+    {
+      "epoch": 0.005140444281255737,
+      "grad_norm": 0.5061175227165222,
+      "learning_rate": 0.00014,
+      "loss": 0.4653,
+      "step": 7
+    },
+    {
+      "epoch": 0.005874793464292271,
+      "grad_norm": 0.7058733105659485,
+      "learning_rate": 0.00016,
+      "loss": 0.4515,
+      "step": 8
+    },
+    {
+      "epoch": 0.006609142647328804,
+      "grad_norm": 0.6450387835502625,
+      "learning_rate": 0.00018,
+      "loss": 0.3974,
+      "step": 9
+    },
+    {
+      "epoch": 0.006609142647328804,
+      "eval_loss": 0.3535566031932831,
+      "eval_runtime": 171.1504,
+      "eval_samples_per_second": 6.702,
+      "eval_steps_per_second": 1.677,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7902460920201216.0,
+  "total_flos": 1.1853691380301824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null