Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e739525a605197613b8e712741d416769ed5f57619fff2ba4f8511681ce890ed
+oid sha256:0f50dfec7b348b398b16d49e0dd1b5d02944005adb5fa282d41d880b7743a85f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c2b2a5410ff424a41e1a6cde39521ad45e7ac7555648b29eaff3b782134b0c
+oid sha256:25a47f14c217dde4efbeced6d0ecf1b11f4ee8587e56f4b26d3f7cdb603d5217
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf0d13686eae3e0c0f52410d677d657c1203d01171ca9804ddd94825765dcc7
+oid sha256:82f3f920fee151f842583919a34cd3a487b202dcc03fce7b250a1108c0d5893e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4e47b661f0982d98bcfee7c8a9db89091e3f5b040309ef2739e290fa07adec1
+oid sha256:3f157fb66e9f6bdea8c4e5f6e07a539c2ce54fcc9de0e2acd2a8bb7cdbb367f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6333333333333333,
+  "epoch": 0.6666666666666666,
   "eval_steps": 500,
-  "global_step": 9500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -672,6 +672,41 @@
       "learning_rate": 1.577911111111111e-05,
       "loss": 0.0635,
       "step": 9500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.1181679293513298,
+      "learning_rate": 1.5734666666666667e-05,
+      "loss": 0.0656,
+      "step": 9600
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 0.16007280349731445,
+      "learning_rate": 1.5690222222222226e-05,
+      "loss": 0.0678,
+      "step": 9700
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 0.34087005257606506,
+      "learning_rate": 1.564577777777778e-05,
+      "loss": 0.0637,
+      "step": 9800
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.27932071685791016,
+      "learning_rate": 1.5601333333333336e-05,
+      "loss": 0.0715,
+      "step": 9900
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.21511399745941162,
+      "learning_rate": 1.555688888888889e-05,
+      "loss": 0.0694,
+      "step": 10000
     }
   ],
   "logging_steps": 100,
@@ -691,7 +726,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.314039984128e+16,
+  "total_flos": 2.43583156224e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null