Checkpoint at step 220

checkpoints/{checkpoint-180 → checkpoint-220}/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01436b4d42fda5d0bd0d432be152b8e6daabace008a2a4da7d4c2e8a915bd5e3
+oid sha256:0576e3f3539a0e79d172894fe362678c80b44a28cda8147ddd89c81a5f31886e
 size 4997867120

checkpoints/{checkpoint-180 → checkpoint-220}/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b9ae8bf67c3bc47b9ab02d718c36a60a55e1c70c350263103f0ade87ffd9fea
+oid sha256:3a1605301ccd4f90faaf68572324a548bf4c5e73dcd6f90f475b808a1a247096
 size 3856242664

checkpoints/{checkpoint-180 → checkpoint-220}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771746457b9e30a4a761ccd9f8ff96ca483dc4254e444cf3492b51bae79c89f5
+oid sha256:361be11371d75e9b52d86c0ddaa928ba076a71f4b7a40ebd110351bd6b0d01c3
 size 25858571

checkpoints/{checkpoint-180 → checkpoint-220}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f3ab58c9031d91773d2c8c3447bb956d8f767db5abb240824f416347b50270
+oid sha256:1b3c0107f4752f47d660ab9481faad64ff112b078ad06a634204030d5c8d97e9
 size 1465

checkpoints/{checkpoint-180 → checkpoint-220}/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008830184514063909,
+  "epoch": 0.010792447739411444,
   "eval_steps": 500,
-  "global_step": 180,
+  "global_step": 220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -134,6 +134,34 @@
       "learning_rate": 2.9267495094833227e-06,
       "loss": 104.178,
       "step": 180
+    },
+    {
+      "epoch": 0.009320750320400792,
+      "grad_norm": 35.0,
+      "learning_rate": 3.090255068672335e-06,
+      "loss": 104.7224,
+      "step": 190
+    },
+    {
+      "epoch": 0.009811316126737676,
+      "grad_norm": 40.5,
+      "learning_rate": 3.253760627861348e-06,
+      "loss": 105.291,
+      "step": 200
+    },
+    {
+      "epoch": 0.01030188193307456,
+      "grad_norm": 51.5,
+      "learning_rate": 3.41726618705036e-06,
+      "loss": 104.8932,
+      "step": 210
+    },
+    {
+      "epoch": 0.010792447739411444,
+      "grad_norm": 40.5,
+      "learning_rate": 3.5807717462393727e-06,
+      "loss": 104.8132,
+      "step": 220
     }
   ],
   "logging_steps": 10,
@@ -153,7 +181,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.8289328236855296e+17,
+  "total_flos": 5.902029006726758e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

logs/events.out.tfevents.1756423478.a504719e5285.5303.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5944cae85a7f2e16f3337e67ae4abb612046cbe215fa9b725654b606220b44cd
-size 9416
+oid sha256:f6472b347a9da79af8fc242279b1a3bb6f9abf8abae934ed65d5aa4d8c8e57c0
+size 9838