Training in progress, step 1200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b0e9b3f4ea4bfa18d8649a6588e6f31e5c42ffd86b85f74f3759d40af7fe5ec
+oid sha256:68d10d6c77661a22b49f687a60f7c0595cbbc5bdafd8820a654f5e22542b0e33
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f83cff620522aa496468277a3bc22911f9c6f4bbc5118c2de2593b7cadedc59
+oid sha256:34eb8fd94484f12828f3079ddb1062719a88baf43040ad9bfe0255470c6e514a
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f81b1683bb9d9f30a4338a9869629a080b447f19358d02a2b979f0e40cf033
+oid sha256:526edfc17cc77c8e1a37fdb81a9a703de4513b58ba4b0dbf11906a54aab78396
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8a23e76bdb5af3bd48e8027611be72cb7ebf75d37e5954461baee2e16e1294
+oid sha256:c692682bd43a00387bd41dcd12b266427cdc8a4657c91543547ea08ad6b10378
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022,
+  "epoch": 0.024,
   "eval_steps": 500,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -778,6 +778,76 @@
       "learning_rate": 0.00029399398797595185,
       "loss": 68.12153930664063,
       "step": 1100
+    },
+    {
+      "epoch": 0.0222,
+      "grad_norm": 9.84087085723877,
+      "learning_rate": 0.0002939338677354709,
+      "loss": 73.03311767578126,
+      "step": 1110
+    },
+    {
+      "epoch": 0.0224,
+      "grad_norm": 8.5576171875,
+      "learning_rate": 0.00029387374749498995,
+      "loss": 67.728662109375,
+      "step": 1120
+    },
+    {
+      "epoch": 0.0226,
+      "grad_norm": 6.275845050811768,
+      "learning_rate": 0.000293813627254509,
+      "loss": 59.14338989257813,
+      "step": 1130
+    },
+    {
+      "epoch": 0.0228,
+      "grad_norm": 10.62365436553955,
+      "learning_rate": 0.00029375350701402804,
+      "loss": 68.015625,
+      "step": 1140
+    },
+    {
+      "epoch": 0.023,
+      "grad_norm": 10.124994277954102,
+      "learning_rate": 0.0002936933867735471,
+      "loss": 67.996630859375,
+      "step": 1150
+    },
+    {
+      "epoch": 0.0232,
+      "grad_norm": 9.192570686340332,
+      "learning_rate": 0.00029363326653306614,
+      "loss": 69.9107177734375,
+      "step": 1160
+    },
+    {
+      "epoch": 0.0234,
+      "grad_norm": 11.012198448181152,
+      "learning_rate": 0.00029357314629258513,
+      "loss": 72.0302978515625,
+      "step": 1170
+    },
+    {
+      "epoch": 0.0236,
+      "grad_norm": 8.58188533782959,
+      "learning_rate": 0.0002935130260521042,
+      "loss": 73.009423828125,
+      "step": 1180
+    },
+    {
+      "epoch": 0.0238,
+      "grad_norm": 11.214829444885254,
+      "learning_rate": 0.0002934529058116232,
+      "loss": 69.40020141601562,
+      "step": 1190
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 8.615409851074219,
+      "learning_rate": 0.0002933927855711423,
+      "loss": 73.381103515625,
+      "step": 1200
     }
   ],
   "logging_steps": 10,
@@ -797,7 +867,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.19190649908096e+16,
+  "total_flos": 1.253963749312512e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null