Training in progress, step 2200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44b60552954a3eb7b67cd9bb47c074f5bb2012c7a637b3c8cc3d9edcf8944b3
+oid sha256:0dc14ab8f69ec65e7855224cd4b5b2dac50c96b2c4e24065af51a27d34a401e3
 size 3826461296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6cc5b7d6a2fac731ee6f768114be3787bc9d22aa5f028f118b2c784c9ffca1f
+oid sha256:befb290c48abb8a194408bc7e0220009e932a229a7b61920a999600f5d482797
 size 2479955235

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13dd54935d4d1876d05824ed5aab8e787b691f2aec583b5a7e328fd2bead633
+oid sha256:5a1d273ddb38f082f32c6d628e3728d6e9b70d01320b1dc05757751f2141f652
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f860d9af78aedd57dafcb10a7d7e5d5d6fe980f28aaf3455f7dda455f8cb9c1
+oid sha256:95ba5207589489cdf07784253d958ae087f570555b90d46b2edd73dcec34d4f5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.84,
+  "epoch": 0.88,
   "eval_steps": 500,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1478,6 +1478,76 @@
       "learning_rate": 8.118971061093248e-06,
       "loss": 0.3028,
       "step": 2100
+    },
+    {
+      "epoch": 0.844,
+      "grad_norm": 10.639591217041016,
+      "learning_rate": 7.918006430868168e-06,
+      "loss": 0.3065,
+      "step": 2110
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 4.760974884033203,
+      "learning_rate": 7.717041800643089e-06,
+      "loss": 0.2966,
+      "step": 2120
+    },
+    {
+      "epoch": 0.852,
+      "grad_norm": 11.585098266601562,
+      "learning_rate": 7.516077170418006e-06,
+      "loss": 0.3466,
+      "step": 2130
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 4.685300827026367,
+      "learning_rate": 7.315112540192927e-06,
+      "loss": 0.397,
+      "step": 2140
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 7.504604339599609,
+      "learning_rate": 7.1141479099678455e-06,
+      "loss": 0.2216,
+      "step": 2150
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 16.2221736907959,
+      "learning_rate": 6.913183279742766e-06,
+      "loss": 0.3863,
+      "step": 2160
+    },
+    {
+      "epoch": 0.868,
+      "grad_norm": 9.542070388793945,
+      "learning_rate": 6.732315112540192e-06,
+      "loss": 0.2478,
+      "step": 2170
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 12.575300216674805,
+      "learning_rate": 6.531350482315113e-06,
+      "loss": 0.3366,
+      "step": 2180
+    },
+    {
+      "epoch": 0.876,
+      "grad_norm": 12.5275297164917,
+      "learning_rate": 6.330385852090033e-06,
+      "loss": 0.42,
+      "step": 2190
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 7.2454514503479,
+      "learning_rate": 6.129421221864952e-06,
+      "loss": 0.2943,
+      "step": 2200
     }
   ],
   "logging_steps": 10,
@@ -1497,7 +1567,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.789296334928282e+16,
+  "total_flos": 3.972002478026342e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null