Training in progress, step 780, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf8cdd4fa216bd4c7f8e742e37dbe5d3cf9b6677692371f47c01ee2359a092f
+oid sha256:2df16ce8b561b352d3312652c40d477fbb877cd56ea970096f2dbaffa07fb552
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851c1edd126e12df0d623062321c6609c8b64c6756e2eeeb1490e4cea8239ad7
+oid sha256:6b6d76fc568477d34da53d466b9db1022be4baaf30111fac5d0d9a5be4fdbc49
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140fb37fd9e85fa1ebc4cf0cf5b0a29ddff69c0f41174cb65d6a4f64fdb5b957
+oid sha256:66230a2c3a0a8fe730262d29372e7febdc116b90ed069ff519fa96f8d1b53e9a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e0670aecb01576e1c66fe6495444d1847e93027019e1c292c2aa930fb3fa0e6
+oid sha256:3939cbd2421a0d3e4ed3c12b3cceaa472fcdb8fe6c9b60b2d2c772cdc28de91f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0608,
+  "epoch": 0.0624,
   "eval_steps": 500,
-  "global_step": 760,
+  "global_step": 780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,13 @@
       "learning_rate": 2.9994965304402304e-05,
       "loss": 3.7613,
       "step": 760
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 38.32442855834961,
+      "learning_rate": 2.999362805807425e-05,
+      "loss": 3.7586,
+      "step": 780
     }
   ],
   "logging_steps": 20,
@@ -280,7 +287,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1808852407615488.0,
+  "total_flos": 1847858637668352.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null