Training in progress, step 2300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc14ab8f69ec65e7855224cd4b5b2dac50c96b2c4e24065af51a27d34a401e3
+oid sha256:3dfeffd5b70b240cf2e2d2863da88eee1aa83f787540436f9ab733c8f7de2bec
 size 3826461296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:befb290c48abb8a194408bc7e0220009e932a229a7b61920a999600f5d482797
+oid sha256:40948a2d1802a19363fb766e414eb283cbde5c248e2166918a98f5c11d88b13c
 size 2479955235

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a1d273ddb38f082f32c6d628e3728d6e9b70d01320b1dc05757751f2141f652
+oid sha256:c615193f9ae8a09e4b00ab7eadeaae7a871753d733db99177a1dcef6ff1f33b3
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95ba5207589489cdf07784253d958ae087f570555b90d46b2edd73dcec34d4f5
+oid sha256:5b73cf65e0ad93ae93850e87c8976f968fc0604f876f55ae715db103a1834c6d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.88,
+  "epoch": 0.92,
   "eval_steps": 500,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1548,6 +1548,76 @@
       "learning_rate": 6.129421221864952e-06,
       "loss": 0.2943,
       "step": 2200
+    },
+    {
+      "epoch": 0.884,
+      "grad_norm": 5.587230682373047,
+      "learning_rate": 5.928456591639871e-06,
+      "loss": 0.2124,
+      "step": 2210
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 12.111313819885254,
+      "learning_rate": 5.727491961414791e-06,
+      "loss": 0.4733,
+      "step": 2220
+    },
+    {
+      "epoch": 0.892,
+      "grad_norm": 13.287424087524414,
+      "learning_rate": 5.526527331189711e-06,
+      "loss": 0.3033,
+      "step": 2230
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 16.977447509765625,
+      "learning_rate": 5.325562700964631e-06,
+      "loss": 0.3256,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 6.201746463775635,
+      "learning_rate": 5.12459807073955e-06,
+      "loss": 0.1995,
+      "step": 2250
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 10.706707954406738,
+      "learning_rate": 4.92363344051447e-06,
+      "loss": 0.3303,
+      "step": 2260
+    },
+    {
+      "epoch": 0.908,
+      "grad_norm": 14.989971160888672,
+      "learning_rate": 4.7226688102893895e-06,
+      "loss": 0.2842,
+      "step": 2270
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 15.570676803588867,
+      "learning_rate": 4.521704180064309e-06,
+      "loss": 0.212,
+      "step": 2280
+    },
+    {
+      "epoch": 0.916,
+      "grad_norm": 3.9141690731048584,
+      "learning_rate": 4.320739549839229e-06,
+      "loss": 0.263,
+      "step": 2290
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 6.531361103057861,
+      "learning_rate": 4.119774919614148e-06,
+      "loss": 0.2503,
+      "step": 2300
     }
   ],
   "logging_steps": 10,
@@ -1567,7 +1637,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.972002478026342e+16,
+  "total_flos": 4.150543064863334e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null