Training in progress, step 5840, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2d12c00c3910f5c8aadf1c3043d575f58f0e94d4e1904af9295d91088e5ba8
+oid sha256:9a05d66290a553ce7e5848692f87b4d47dd70832cd730d3e060d68efb842c89b
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f018a91942bfac6141fce26126b81cc10d8b6d03258988a8ed48ad7a147fb9c
+oid sha256:c55dfcbb3adece00c0495fe03185267c02807bfaa50cb1106c5f7e6137980a8d
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ca75c8c20354aa6121b583b0e2d1196548a9e950e5c54e2824364c1617a488
+oid sha256:d37eee1f275542e53d152c87d42b36d0933fa3b25d32e8265c1afb8163e08bdb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffeee657eab485848cc5e4a398e8908b8f07d67a077ba1a196eb593774ff8630
+oid sha256:b5ff425dd13fc2cddef013a46a6108a94fb4fb857872d9633c68069377e39e8a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4656,
+  "epoch": 0.4672,
   "eval_steps": 500,
-  "global_step": 5820,
+  "global_step": 5840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2044,6 +2044,13 @@
       "learning_rate": 2.495243304591236e-05,
       "loss": 3.561,
       "step": 5820
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 43.67660140991211,
+      "learning_rate": 2.4916033320336263e-05,
+      "loss": 3.3979,
+      "step": 5840
     }
   ],
   "logging_steps": 20,
@@ -2051,7 +2058,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3779205011996672e+16,
+  "total_flos": 1.3829463670063104e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null