Training in progress, step 295, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e2e87355763edd3d8d8fc9f16426a52b729ef470fa0ed35fdf6a0d34a1d19e
+oid sha256:303d3808899ee31f18d353a81aee545e536a2dcd4cbf6b967519fa2c85e216cf
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b0bf7861f08e4352dac63f09fddd6dae58be12ccfacd2673ea034a1c7bbb52
+oid sha256:cf82ca0d1c2a8b78b728f10513331085b2fa3972fe291e89f4a5f25e18d40d82
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4863ee1f3e4eb3a27956688d9477cddde272e35ff8d013a583ff2d67a2b5271
+oid sha256:85797b6736a862291678baca072e183198938fa2e531b073954ae497386d1e69
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ef35c880ce179d87a8b718acaf0bfe99028fc0acc2a163aedf97a2066df701
+oid sha256:afbdbed6f103600bb101032f12d2fcf21f68d620e7d74db4f36c50456df69b7e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37528307990941445,
+  "epoch": 0.3817534778388871,
   "eval_steps": 386,
-  "global_step": 290,
+  "global_step": 295,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2045,6 +2045,41 @@
       "learning_rate": 9.902412435583128e-05,
       "loss": 0.8627,
       "step": 290
+    },
+    {
+      "epoch": 0.37657715949530896,
+      "grad_norm": 0.8336161971092224,
+      "learning_rate": 9.901600195132627e-05,
+      "loss": 0.9815,
+      "step": 291
+    },
+    {
+      "epoch": 0.3778712390812035,
+      "grad_norm": 0.8170490264892578,
+      "learning_rate": 9.90078462204787e-05,
+      "loss": 0.8305,
+      "step": 292
+    },
+    {
+      "epoch": 0.379165318667098,
+      "grad_norm": 0.7367318868637085,
+      "learning_rate": 9.899965716883372e-05,
+      "loss": 0.8314,
+      "step": 293
+    },
+    {
+      "epoch": 0.3804593982529926,
+      "grad_norm": 0.8122355937957764,
+      "learning_rate": 9.899143480195913e-05,
+      "loss": 0.8369,
+      "step": 294
+    },
+    {
+      "epoch": 0.3817534778388871,
+      "grad_norm": 0.7415926456451416,
+      "learning_rate": 9.898317912544536e-05,
+      "loss": 0.8985,
+      "step": 295
     }
   ],
   "logging_steps": 1,
@@ -2064,7 +2099,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.242017797911347e+17,
+  "total_flos": 3.2979146564960256e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null