Training in progress, step 260, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f317c2f9c0e1904127f0b0ce934aa07af2b7229ad58b9705ab9439b52063d79b
+oid sha256:f7061fadd3c867263d87e12e8b7e280976ce200378e43b87f0081a278d4383e7
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef4793eaa5e68cb9e4770c48af11f8b45736f6d545fc0af49f5658489d799143
-size 255265850
+oid sha256:24d91ac5539ceabfcf15fbf9d84527d1e791ae4cea2693dbcd256bead5c4bf6a
+size 255266042

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc199d50ee7acd60b0e618740a19710d9cb29c2225fb47541ee35fdc79228cad
+oid sha256:e79c164d22927fe2b6be7170e235646a9aaf6d63ba0191dae0d9fe729f5a4a83
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f87fdf6af8f44bb6d6b07cf2d135d04fedbac4a4a784047f9932793daf148b
+oid sha256:bc59c27066bac68aa57567d315b438b10f99b59c00a49fca645305936456a77f
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108ec0968af236f6199c1f716a40487225162213cb414b717c6f1aeb82bcbc29
+oid sha256:d3a36d0f4565e0cd31cd0465a8062a29bd158a6ba54be5d6acec2d94425b0892
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.0,
+  "epoch": 21.666666666666668,
   "eval_steps": 40,
-  "global_step": 240,
+  "global_step": 260,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 144.537,
       "eval_steps_per_second": 2.311,
       "step": 240
+    },
+    {
+      "epoch": 20.833333333333332,
+      "grad_norm": 3.890625,
+      "learning_rate": 0.00013506375551927547,
+      "loss": 3.0297,
+      "step": 250
+    },
+    {
+      "epoch": 21.666666666666668,
+      "grad_norm": 3.96875,
+      "learning_rate": 0.00012985148110016947,
+      "loss": 2.9882,
+      "step": 260
     }
   ],
   "logging_steps": 10,
@@ -250,7 +264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5547920996630528e+16,
+  "total_flos": 1.686169733562368e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null