Training in progress, step 900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61b1b69e894c3a7080e6a303a3f756090e3480cd7e3be305a93cc66efecd1d2c
+oid sha256:8768e79529253ec6a4a9c9ac4ed31fdfdbd11d2032b8c45d8b47efa9c9d546c7
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eedc85193f945c1312ff227d4d3c069d5e5469515ec4a1e7dd01999c483db02
+oid sha256:b359910b5fd17aadf25fd00b37f0d204cc86fee7b829ec01ab07ad0364a48e0c
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1347e41739e6d97d50d223900089b55b6dd4a02d2dc85ec6e9aa6a312e93005a
+oid sha256:779676ad450eae2b6879d7f004a716095853f54998471414edbab1cbed9cedac
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10f9e65a9c24c381ff534d5df3cf5fdc8a240cae768aed7007c78e044f60c2a
+oid sha256:653cba8a20af8c5396af38192396529e15aba7f27a53a1c15a4069355b1b5a35
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016,
+  "epoch": 0.018,
   "eval_steps": 500,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -568,6 +568,76 @@
       "learning_rate": 0.00029579759519038075,
       "loss": 68.58425903320312,
       "step": 800
+    },
+    {
+      "epoch": 0.0162,
+      "grad_norm": 9.43658447265625,
+      "learning_rate": 0.00029573747494989974,
+      "loss": 71.80587158203124,
+      "step": 810
+    },
+    {
+      "epoch": 0.0164,
+      "grad_norm": 7.688558578491211,
+      "learning_rate": 0.0002956773547094188,
+      "loss": 73.39664916992187,
+      "step": 820
+    },
+    {
+      "epoch": 0.0166,
+      "grad_norm": 9.346514701843262,
+      "learning_rate": 0.00029561723446893784,
+      "loss": 73.8046142578125,
+      "step": 830
+    },
+    {
+      "epoch": 0.0168,
+      "grad_norm": 7.071310997009277,
+      "learning_rate": 0.0002955571142284569,
+      "loss": 69.04111938476562,
+      "step": 840
+    },
+    {
+      "epoch": 0.017,
+      "grad_norm": 10.125195503234863,
+      "learning_rate": 0.00029549699398797593,
+      "loss": 69.92824096679688,
+      "step": 850
+    },
+    {
+      "epoch": 0.0172,
+      "grad_norm": 8.768003463745117,
+      "learning_rate": 0.000295436873747495,
+      "loss": 74.65200805664062,
+      "step": 860
+    },
+    {
+      "epoch": 0.0174,
+      "grad_norm": 8.981837272644043,
+      "learning_rate": 0.000295376753507014,
+      "loss": 72.95183715820312,
+      "step": 870
+    },
+    {
+      "epoch": 0.0176,
+      "grad_norm": 9.743247032165527,
+      "learning_rate": 0.000295316633266533,
+      "loss": 68.19429321289063,
+      "step": 880
+    },
+    {
+      "epoch": 0.0178,
+      "grad_norm": 7.722388744354248,
+      "learning_rate": 0.00029525651302605207,
+      "loss": 71.07997436523438,
+      "step": 890
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 7.273824214935303,
+      "learning_rate": 0.0002951963927855711,
+      "loss": 71.75267333984375,
+      "step": 900
     }
   ],
   "logging_steps": 10,
@@ -587,7 +657,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.00786682359296e+16,
+  "total_flos": 1.071637991053056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null