Training in progress, step 490, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a6b59d01849a163702b8e50607c498745112dc6ced09ce72986bc17ec447c5
+oid sha256:6ca3af260a573b461cd342f7bf7afa505c4101cdfcb62508cb4679571ecbc02c
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c943a007ca820031ad467134581d9a1d6d566dbef8d77e1cbb5e854f9dbe6f0
+oid sha256:42b428390e9c7047edbe5f8c842a6e6a63099594ace45e1079150202b30097dd
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c2f577326b2b04f054023f26d112b121ac8ff4bf7c93ae38255948cc3a2c22
+oid sha256:2d4663104f7f8c9aa215e9202234c5afb320a2473b8dc4114eff264e4c02057b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f4b94f1a44c59895f464174a55ad4567f9ad6cb9a5184c25fed320934f9e0d
+oid sha256:c388993843f0e58c8f91775a4c14074f5b54c4aade244b7bc036cc4bac2f6b60
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6276285991588483,
+  "epoch": 0.634098997088321,
   "eval_steps": 386,
-  "global_step": 485,
+  "global_step": 490,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3418,6 +3418,41 @@
       "learning_rate": 9.681794913852746e-05,
       "loss": 0.989,
       "step": 485
+    },
+    {
+      "epoch": 0.6289226787447428,
+      "grad_norm": 0.7921927571296692,
+      "learning_rate": 9.68034602964518e-05,
+      "loss": 0.8748,
+      "step": 486
+    },
+    {
+      "epoch": 0.6302167583306373,
+      "grad_norm": 0.8911926746368408,
+      "learning_rate": 9.678893963235704e-05,
+      "loss": 1.0641,
+      "step": 487
+    },
+    {
+      "epoch": 0.6315108379165318,
+      "grad_norm": 0.8004783391952515,
+      "learning_rate": 9.677438715611586e-05,
+      "loss": 0.9681,
+      "step": 488
+    },
+    {
+      "epoch": 0.6328049175024264,
+      "grad_norm": 0.9230672717094421,
+      "learning_rate": 9.675980287762263e-05,
+      "loss": 0.9226,
+      "step": 489
+    },
+    {
+      "epoch": 0.634098997088321,
+      "grad_norm": 0.7298123240470886,
+      "learning_rate": 9.67451868067933e-05,
+      "loss": 0.7876,
+      "step": 490
     }
   ],
   "logging_steps": 1,
@@ -3437,7 +3472,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.421995282713805e+17,
+  "total_flos": 5.477892141298483e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null