Training in progress, step 24500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e75f6f68216d5e0a0d45524bf05e000b598469ccd018a2917bfcf70749be2e
+oid sha256:64e48208631beaba01ec3963505840059eb9517304978bbdd41d949e84f0740f
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6094231b675aee692a8990e8d614035b63ad59307c785bb5adfd09bc0782c8c8
+oid sha256:714fa26825407623414b35b1a439da9dae45cc279b9c9cab2f80bfb83e3a0cab
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d1b2da445bdc8c10c1c9019867ae159eaa5e9b0a6d5d406fc41a87fe242c82a
+oid sha256:2de9e6dd078635a8f2782848159447ee5b019d45587bf8f5a096a6ad31f54191
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbfd02ecdfa77e07a5c5c5775ffb7d8cd45a7a90d826fb1bf2e1490611fed3c2
+oid sha256:a319bc7f962088537012b429029576d050b6a773e4215777decd55cccf7ad374
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbacae0d6cb0e8059690fc23044d3b67866df9cffa20a105496953daa6152e9
+oid sha256:aaa49f4130d1fd130f796dda9467335d1eeb9c721890d531cd0b284f77224b61
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.000566666666666,
+  "epoch": 8.000766666666667,
   "eval_steps": 500,
-  "global_step": 24000,
+  "global_step": 24500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3368,6 +3368,76 @@
       "learning_rate": 2.968858748386437e-06,
       "loss": 0.6377016830444336,
       "step": 24000
+    },
+    {
+      "epoch": 3.0024,
+      "grad_norm": 1.3275223970413208,
+      "learning_rate": 2.9213288241672647e-06,
+      "loss": 0.36499958038330077,
+      "step": 24050
+    },
+    {
+      "epoch": 3.0040666666666667,
+      "grad_norm": 1.76749587059021,
+      "learning_rate": 2.8741413631038877e-06,
+      "loss": 0.3513433837890625,
+      "step": 24100
+    },
+    {
+      "epoch": 3.005733333333333,
+      "grad_norm": 1.3912204504013062,
+      "learning_rate": 2.8272977030890675e-06,
+      "loss": 0.35687347412109377,
+      "step": 24150
+    },
+    {
+      "epoch": 3.0074,
+      "grad_norm": 1.466273546218872,
+      "learning_rate": 2.7807991722678895e-06,
+      "loss": 0.35906410217285156,
+      "step": 24200
+    },
+    {
+      "epoch": 3.0090666666666666,
+      "grad_norm": 1.5847675800323486,
+      "learning_rate": 2.734647089000072e-06,
+      "loss": 0.34384849548339846,
+      "step": 24250
+    },
+    {
+      "epoch": 3.0107333333333335,
+      "grad_norm": 1.3546370267868042,
+      "learning_rate": 2.688842761822607e-06,
+      "loss": 0.4250868988037109,
+      "step": 24300
+    },
+    {
+      "epoch": 3.0124,
+      "grad_norm": 1.9650839567184448,
+      "learning_rate": 2.6433874894126654e-06,
+      "loss": 0.5334797668457031,
+      "step": 24350
+    },
+    {
+      "epoch": 3.0140666666666664,
+      "grad_norm": 1.6792277097702026,
+      "learning_rate": 2.5982825605507595e-06,
+      "loss": 0.6985765075683594,
+      "step": 24400
+    },
+    {
+      "epoch": 3.0157333333333334,
+      "grad_norm": 1.343593955039978,
+      "learning_rate": 2.553529254084207e-06,
+      "loss": 0.7399945068359375,
+      "step": 24450
+    },
+    {
+      "epoch": 4.000933333333333,
+      "grad_norm": 1.3937770128250122,
+      "learning_rate": 2.509128838890883e-06,
+      "loss": 0.5113412094116211,
+      "step": 24500
     }
   ],
   "logging_steps": 50,
@@ -3387,7 +3457,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1432735901659464e+18,
+  "total_flos": 2.1897882493782098e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null