Training in progress, step 21500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5808c4d4a871b3a3feef39008a78693f4b002bad6b751d4a55ecf03b18ce28d2
+oid sha256:aea1784883a5ff7695611f261bfe85640fcca1ad565f038d76c6c349343ca9bb
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3917c9a0b5a1a4684d0f418f0f18616f6c636c241010cfdfa0cab6ff0ea1ed
+oid sha256:f94d1fbc76e97985614b16c4c8ef7606c27c4c7e059e35176458375ca8d695f7
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:495527095ce64d42859bf28983716fbe3891476c1dd8d77f6b07b794fa6428e3
+oid sha256:0a5c11622183d87222d1ac6c441b6bba34fdcd36747c102761fbee73401f8dd3
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba426160bf784af2f74f1fee215f1c1e222f9b82fe4e028acd5d90af568a23c
+oid sha256:02bf9398b6a83e3ff431dbc5b80a1c42a0ec477a780a12382952446034ceddda
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f191eb532c66480b881d02a99bfe981f86631ebea22d7fa2c791adb20fea8a3f
+oid sha256:36e36eb7c381dd82408d529f8b5ed139d2ee4b2c250458b5cebd549d9fcf1684
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.0017,
+  "epoch": 8.000599999999999,
   "eval_steps": 500,
-  "global_step": 21000,
+  "global_step": 21500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2948,6 +2948,76 @@
       "learning_rate": 6.388649360227622e-06,
       "loss": 1.3686183166503907,
       "step": 21000
+    },
+    {
+      "epoch": 1.0016666666666667,
+      "grad_norm": 1.685487985610962,
+      "learning_rate": 6.323373997464244e-06,
+      "loss": 0.8170787811279296,
+      "step": 21050
+    },
+    {
+      "epoch": 1.0033333333333334,
+      "grad_norm": 1.7664726972579956,
+      "learning_rate": 6.25834464062976e-06,
+      "loss": 0.8275099945068359,
+      "step": 21100
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 1.848008155822754,
+      "learning_rate": 6.193563133483182e-06,
+      "loss": 0.8038805389404297,
+      "step": 21150
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 1.8948545455932617,
+      "learning_rate": 6.129031312756302e-06,
+      "loss": 0.7818323516845703,
+      "step": 21200
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 1.9466619491577148,
+      "learning_rate": 6.064751008101625e-06,
+      "loss": 0.7761798095703125,
+      "step": 21250
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 2.0793747901916504,
+      "learning_rate": 6.000724042040485e-06,
+      "loss": 0.7409461975097656,
+      "step": 21300
+    },
+    {
+      "epoch": 1.0116666666666667,
+      "grad_norm": 1.97606360912323,
+      "learning_rate": 5.936952229911398e-06,
+      "loss": 0.7577394866943359,
+      "step": 21350
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 2.0533604621887207,
+      "learning_rate": 5.873437379818551e-06,
+      "loss": 0.8345895385742188,
+      "step": 21400
+    },
+    {
+      "epoch": 1.015,
+      "grad_norm": 1.9522418975830078,
+      "learning_rate": 5.810181292580571e-06,
+      "loss": 0.9583216094970703,
+      "step": 21450
+    },
+    {
+      "epoch": 2.0004,
+      "grad_norm": 1.4512640237808228,
+      "learning_rate": 5.747185761679443e-06,
+      "loss": 0.8717018127441406,
+      "step": 21500
     }
   ],
   "logging_steps": 50,
@@ -2967,7 +3037,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8586919781536072e+18,
+  "total_flos": 1.9066366344807875e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null