Training in progress, step 690, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f67cbe9e89ea2da575b60c5410847310ec4df02b9c6d92a6859e332eacbb1a
+oid sha256:8da4a61f4ad08e274cdbf73ebb57438c58fd588d4c0fa3e41f3415fecff11a2a
 size 1976163472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c52059a0ace4821d5364e966b4df8b16f3e773b35b9b1efdd18136d59f9441
+oid sha256:50794c663f5c018c35812f32b3df9ca6b67d62b3ddbada7d522c08bb8bdf691b
 size 1816765835

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca202fc25cecd2e3dfae2a87978621e5f552f2c88fe716b567b699919d821583
+oid sha256:f7d5d33e43d9e54d35ed6ab24ad21ab50d80e1d6b8855d6a0d3c240494595653
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47597edb455ef686d71b9e2fdfad1e99b404dc1a854723bde359a0fdeff5c2f3
+oid sha256:94500ce5ab9390767daf1d7b015ce76c5d2ee92a8f74d860763427890a6af7b5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021583351387588757,
+  "epoch": 0.022564412814297337,
   "eval_steps": 500,
-  "global_step": 660,
+  "global_step": 690,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -470,6 +470,27 @@
       "learning_rate": 9.784499672988883e-06,
       "loss": 1.041367530822754,
       "step": 660
+    },
+    {
+      "epoch": 0.021910371863158282,
+      "grad_norm": 1.944808840751648,
+      "learning_rate": 9.781229561805102e-06,
+      "loss": 1.0567661285400392,
+      "step": 670
+    },
+    {
+      "epoch": 0.022237392338727808,
+      "grad_norm": 2.1537973880767822,
+      "learning_rate": 9.777959450621321e-06,
+      "loss": 1.0511420249938965,
+      "step": 680
+    },
+    {
+      "epoch": 0.022564412814297337,
+      "grad_norm": 1.7468407154083252,
+      "learning_rate": 9.774689339437542e-06,
+      "loss": 0.9636780738830566,
+      "step": 690
     }
   ],
   "logging_steps": 10,
@@ -489,7 +510,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.129457117633331e+16,
+  "total_flos": 2.2311643167830016e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null