Training in progress, step 2850, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96b2d10a844b11cf5b2544f35d93e70b315fececa5c2d3ca624e6dfead07a827
+oid sha256:c0abce668b3eb4d44dc784d9560c9e8eaf1d78e218c11316de74bb009145f23e
 size 5991064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1836d73c8a5897489d644f69854e2f687fca0e79b5b6c08dd2c8dbd2938ca9
+oid sha256:5af9af34cee614f2f3b9fcd4f30272cd7939d050f865cdf0b26c2e35e2ffb59c
 size 3875258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20654594740d79ce8368c8a1d84e3daa1b6c26318ed3b339b4307a9b85892639
+oid sha256:f0823cffba25b0205e4aaa4829d080da287f93b4b12f54638f5eb7ec2af7f34c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a0475b68e927911bcde368a8d1060fd9a7ea6fc58f735f74af0c4bfd6634af6
+oid sha256:b7f1cdaac6e6d07ba74169a3057ad987f49c993cbd8847dc15c52a36f581d092
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.184617413378169,
+  "epoch": 0.18791415290277916,
   "eval_steps": 500,
-  "global_step": 2800,
+  "global_step": 2850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1968,6 +1968,41 @@
       "learning_rate": 0.0002,
       "loss": 0.7594,
       "step": 2800
+    },
+    {
+      "epoch": 0.18527676128309103,
+      "grad_norm": 1.489174246788025,
+      "learning_rate": 0.0002,
+      "loss": 0.696,
+      "step": 2810
+    },
+    {
+      "epoch": 0.18593610918801307,
+      "grad_norm": 2.3775784969329834,
+      "learning_rate": 0.0002,
+      "loss": 0.7494,
+      "step": 2820
+    },
+    {
+      "epoch": 0.1865954570929351,
+      "grad_norm": 1.5026384592056274,
+      "learning_rate": 0.0002,
+      "loss": 0.7631,
+      "step": 2830
+    },
+    {
+      "epoch": 0.18725480499785713,
+      "grad_norm": 2.0681509971618652,
+      "learning_rate": 0.0002,
+      "loss": 0.7628,
+      "step": 2840
+    },
+    {
+      "epoch": 0.18791415290277916,
+      "grad_norm": 1.44792640209198,
+      "learning_rate": 0.0002,
+      "loss": 0.7436,
+      "step": 2850
     }
   ],
   "logging_steps": 10,
@@ -1987,7 +2022,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4845174148349952.0,
+  "total_flos": 4931223928266240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null