Training in progress, step 2400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dfeffd5b70b240cf2e2d2863da88eee1aa83f787540436f9ab733c8f7de2bec
+oid sha256:3daa573e6c713aaba8eac212b616972e27300562149c5a86cf161a20a2986ab7
 size 3826461296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40948a2d1802a19363fb766e414eb283cbde5c248e2166918a98f5c11d88b13c
+oid sha256:ecb57a7b1bc6df393a4d72695c3003da6933e5235a702cfb45b794fb4c7477bb
 size 2479955235

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c615193f9ae8a09e4b00ab7eadeaae7a871753d733db99177a1dcef6ff1f33b3
+oid sha256:db5e98494f4088139d10e50b166d461cb7e004fb4e01c00728b39a7d5b780d91
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b73cf65e0ad93ae93850e87c8976f968fc0604f876f55ae715db103a1834c6d
+oid sha256:a2e9f05b210aeadfc93d7bb7ed80d64988a89f8306f57d2f4dda99778443c8e5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.92,
+  "epoch": 0.96,
   "eval_steps": 500,
-  "global_step": 2300,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1618,6 +1618,76 @@
       "learning_rate": 4.119774919614148e-06,
       "loss": 0.2503,
       "step": 2300
+    },
+    {
+      "epoch": 0.924,
+      "grad_norm": 8.718388557434082,
+      "learning_rate": 3.918810289389068e-06,
+      "loss": 0.2793,
+      "step": 2310
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 11.070220947265625,
+      "learning_rate": 3.7178456591639876e-06,
+      "loss": 0.2585,
+      "step": 2320
+    },
+    {
+      "epoch": 0.932,
+      "grad_norm": 7.7603759765625,
+      "learning_rate": 3.516881028938907e-06,
+      "loss": 0.5099,
+      "step": 2330
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 15.190449714660645,
+      "learning_rate": 3.3159163987138267e-06,
+      "loss": 0.2601,
+      "step": 2340
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.578422546386719,
+      "learning_rate": 3.1149517684887463e-06,
+      "loss": 0.264,
+      "step": 2350
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 10.097108840942383,
+      "learning_rate": 2.913987138263666e-06,
+      "loss": 0.6162,
+      "step": 2360
+    },
+    {
+      "epoch": 0.948,
+      "grad_norm": 8.5523042678833,
+      "learning_rate": 2.7130225080385853e-06,
+      "loss": 0.2649,
+      "step": 2370
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 8.127545356750488,
+      "learning_rate": 2.512057877813505e-06,
+      "loss": 0.4394,
+      "step": 2380
+    },
+    {
+      "epoch": 0.956,
+      "grad_norm": 8.142045021057129,
+      "learning_rate": 2.311093247588425e-06,
+      "loss": 0.2339,
+      "step": 2390
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 6.302300930023193,
+      "learning_rate": 2.1101286173633444e-06,
+      "loss": 0.2135,
+      "step": 2400
     }
   ],
   "logging_steps": 10,
@@ -1637,7 +1707,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.150543064863334e+16,
+  "total_flos": 4.334241751385702e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null